1 code implementation • EMNLP 2021 • Hao Zhou, Minlie Huang, Yong liu, Wei Chen, Xiaoyan Zhu
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
1 code implementation • NAACL 2022 • Zhexin Zhang, Jiaxin Wen, Jian Guan, Minlie Huang
In this paper, we aim to control the protagonist’s persona in story generation, i. e., generating a story from a leading context and a persona description, where the protagonist should exhibit the specified personality through a coherent event sequence.
no code implementations • ACL (ECNLP) 2021 • Runze Liang, Ryuichi Takanobu, Feng-Lin Li, Ji Zhang, Haiqing Chen, Minlie Huang
To this end, we formalize the turn-level satisfaction estimation as a reinforcement learning problem, in which the model can be optimized with only session-level satisfaction labels.
1 code implementation • EMNLP (insights) 2021 • Qi Zhu, Yuxian Gu, Lingxiao Luo, Bing Li, Cheng Li, Wei Peng, Minlie Huang, Xiaoyan Zhu
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
1 code implementation • 25 Apr 2024 • Chujie Zheng, Ziqi Wang, Heng Ji, Minlie Huang, Nanyun Peng
Suppose we have a moderately trained LLM (e. g., trained to align with human preference) in hand, can we further exploit its potential and cheaply acquire a stronger model?
no code implementations • 8 Apr 2024 • Shen Gao, Hao Li, Zhengliang Shi, Chengrui Huang, Quan Tu, Zhiliang Tian, Minlie Huang, Shuo Shang
The framework employs a novel 360{\deg} performance assessment method for multi-perspective performance evaluation with fine-grained assessment.
no code implementations • 1 Apr 2024 • Zhenyu Hou, Yilin Niu, Zhengxiao Du, Xiaohan Zhang, Xiao Liu, Aohan Zeng, Qinkai Zheng, Minlie Huang, Hongning Wang, Jie Tang, Yuxiao Dong
The work presents our practices of aligning LLMs with human preferences, offering insights into the challenges and solutions in RLHF implementations.
no code implementations • 27 Feb 2024 • Yuxian Gu, Li Dong, Yaru Hao, Qingxiu Dong, Minlie Huang, Furu Wei
This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance.
no code implementations • 26 Feb 2024 • Yiping Song, Juhua Zhang, Zhiliang Tian, Yuxin Yang, Minlie Huang, Dongsheng Li
As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA).
1 code implementation • 26 Feb 2024 • Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner.
no code implementations • 25 Feb 2024 • Hao Wang, Hao Li, Minlie Huang, Lei Sha
The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties.
1 code implementation • 23 Feb 2024 • Zhuang Chen, Jincenzi Wu, Jinfeng Zhou, Bosi Wen, Guanqun Bi, Gongyao Jiang, Yaru Cao, Mengting Hu, Yunghwei Lai, Zexuan Xiong, Minlie Huang
Theory of Mind (ToM) is the cognitive capability to perceive and ascribe mental states to oneself and others.
1 code implementation • 19 Feb 2024 • Sahand Sabour, Siyang Liu, Zheyuan Zhang, June M. Liu, Jinfeng Zhou, Alvionna S. Sunaryo, Juanzi Li, Tatia M. C. Lee, Rada Mihalcea, Minlie Huang
Recent advances in Large Language Models (LLMs) have highlighted the need for robust, comprehensive, and challenging benchmarks.
no code implementations • 2 Feb 2024 • Jian Guan, Wei Wu, Zujie Wen, Peng Xu, Hongning Wang, Minlie Huang
We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process.
2 code implementations • 1 Feb 2024 • Haozhe Ji, Cheng Lu, Yilin Niu, Pei Ke, Hongning Wang, Jun Zhu, Jie Tang, Minlie Huang
We prove that EXO is guaranteed to optimize in the same direction as the RL algorithms asymptotically for arbitary parametrization of the policy, while enables efficient optimization by circumventing the complexities associated with RL algorithms.
1 code implementation • 31 Jan 2024 • Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie zhou, Kai-Wei Chang, Minlie Huang, Nanyun Peng
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) from complying with queries that contain harmful intents.
2 code implementations • 30 Nov 2023 • Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Zhuoer Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang
We will provide public APIs for evaluating AlignBench with CritiqueLLM to facilitate the evaluation of LLMs' Chinese alignment.
2 code implementations • 30 Nov 2023 • Pei Ke, Bosi Wen, Zhuoer Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
Since the natural language processing (NLP) community started to make large language models (LLMs), such as GPT-4, act as a critic to evaluate the quality of generated texts, most of them only train a critique generation model of a specific scale on specific datasets.
1 code implementation • 29 Nov 2023 • Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, Minlie Huang
While recent studies primarily focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, we show that LLMs can generate diverse implicit toxic outputs that are exceptionally difficult to detect via simply zero-shot prompting.
1 code implementation • 28 Nov 2023 • Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Libiao Peng, Jiaming Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Jie Tang, Minlie Huang
In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters.
1 code implementation • 15 Nov 2023 • Zhexin Zhang, Junxiao Yang, Pei Ke, Minlie Huang
We hope our work could contribute to the comprehension of jailbreaking attacks and defenses, and shed light on the relationship between LLMs' capability and safety.
1 code implementation • 7 Nov 2023 • Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang
However, these models are often not well aligned with human intents, which calls for additional treatments on them, that is, the alignment problem.
1 code implementation • 23 Oct 2023 • Jian Guan, Jesse Dodge, David Wadden, Minlie Huang, Hao Peng
Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs).
no code implementations • 9 Oct 2023 • Siyang Liu, Naihao Deng, Sahand Sabour, Yilin Jia, Minlie Huang, Rada Mihalcea
We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health.
no code implementations • 2 Oct 2023 • Haozhe Ji, Pei Ke, Hongning Wang, Minlie Huang
And most importantly, we prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts.
1 code implementation • 29 Sep 2023 • Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Minlie Huang, Nan Duan, Weizhu Chen
Large language models have made significant progress in various language tasks, yet they still struggle with complex mathematics.
Ranked #11 on Math Word Problem Solving on MATH (using extra training data)
1 code implementation • 13 Sep 2023 • Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, Minlie Huang
Notably, SafetyBench also incorporates both Chinese and English data, facilitating the evaluation in both languages.
1 code implementation • 7 Sep 2023 • Chujie Zheng, Hao Zhou, Fandong Meng, Jie zhou, Minlie Huang
This work shows that modern LLMs are vulnerable to option position changes in MCQs due to their inherent "selection bias", namely, they prefer to select specific option IDs as answers (like "Option A").
1 code implementation • 7 Aug 2023 • Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, Jie Tang
We present AgentBench, a multi-dimensional evolving benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities in a multi-turn open-ended generation setting.
1 code implementation • 16 Jul 2023 • Jinfeng Zhou, Zhuang Chen, Bo wang, Minlie Huang
Experiments verify the superiority of Supporter in achieving positive emotion elicitation during responding while maintaining conversational goals including coherence.
1 code implementation • 13 Jul 2023 • Pei Ke, Fei Huang, Fei Mi, Yasheng Wang, Qun Liu, Xiaoyan Zhu, Minlie Huang
Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
1 code implementation • 10 Jul 2023 • Zhexin Zhang, Jiaxin Wen, Minlie Huang
In this paper, we propose a method named Ethicist for targeted training data extraction through loss smoothed soft prompting and calibrated confidence estimation, investigating how to recover the suffix in the training data when given a prefix.
1 code implementation • 4 Jul 2023 • Jian Guan, Minlie Huang
Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation.
2 code implementations • 14 Jun 2023 • Yuxian Gu, Li Dong, Furu Wei, Minlie Huang
In this work, we propose a KD approach that distills LLMs into smaller language models.
1 code implementation • 6 Jun 2023 • Chujie Zheng, Pei Ke, Zheng Zhang, Minlie Huang
It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition.
no code implementations • 5 Jun 2023 • Mengting Hu, Zhen Zhang, Shiwan Zhao, Minlie Huang, Bingzhe Wu
Therefore, in this survey, we provide a comprehensive review of uncertainty-relevant works in the NLP field.
1 code implementation • 1 Jun 2023 • Mengting Hu, Yinhao Bai, Yike Wu, Zhen Zhang, Liqi Zhang, Hang Gao, Shiwan Zhao, Minlie Huang
We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens.
1 code implementation • 29 May 2023 • Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang, Haotian Wang, Lemao Liu, Zhirui Zhang, Zhe Liu, Bingzhe Wu
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments.
no code implementations • 24 May 2023 • Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, Weizhu Chen
In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner.
1 code implementation • 16 May 2023 • Yuxian Gu, Li Dong, Furu Wei, Minlie Huang
In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community.
no code implementations • 9 May 2023 • Jincenzi Wu, Zhuang Chen, Jiawen Deng, Sahand Sabour, Minlie Huang
To empower AI systems with the ToM ability and narrow the gap between them and humans, in this paper, we propose COKE: the first cognitive knowledge graph for machine theory of mind.
1 code implementation • 4 May 2023 • Jiaxin Wen, Hao Zhou, Jian Guan, Minlie Huang
However, the pre-trained dialogue model's ability to utilize long-range context is limited due to the scarcity of long-turn dialogue sessions.
1 code implementation • 24 Apr 2023 • Fei Huang, Pei Ke, Minlie Huang
Non-AutoRegressive (NAR) text generation models have drawn much attention because of their significantly faster decoding speed and good generation quality in machine translation.
2 code implementations • 20 Apr 2023 • Hao Sun, Zhexin Zhang, Jiawen Deng, Jiale Cheng, Minlie Huang
To further promote the safe deployment of LLMs, we develop a Chinese LLM safety assessment benchmark.
1 code implementation • 26 Feb 2023 • Haozhe Ji, Pei Ke, Zhipeng Hu, Rongsheng Zhang, Minlie Huang
The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method.
no code implementations • 18 Feb 2023 • Jiawen Deng, Jiale Cheng, Hao Sun, Zhexin Zhang, Minlie Huang
This survey presents a framework for safety research pertaining to large models, delineating the landscape of safety risks as well as safety evaluation and improvement methods.
no code implementations • 1 Feb 2023 • Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, Weizhu Chen
However, the quality of the prompts depends on the demonstrations given to the models, and creating many of them by hand is costly.
1 code implementation • 21 Dec 2022 • Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang
In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems.
1 code implementation • 19 Dec 2022 • Jiale Cheng, Sahand Sabour, Hao Sun, Zhuang Chen, Minlie Huang
As previous studies have demonstrated that seekers' persona is an important factor for effective support, we investigate whether there are benefits to modeling such information in dialogue models for support.
no code implementations • 4 Dec 2022 • Qi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang, Yitong Li, Xin Jiang, Qun Liu, Xiaoyan Zhu, Minlie Huang
For the former, the grounding knowledge consists of keywords extracted from the response.
1 code implementation • 4 Dec 2022 • Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang
In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing workers, or automatic generation to construct adversarial contexts that are likely to induce toxic generations.
1 code implementation • 30 Nov 2022 • Qi Zhu, Christian Geishauser, Hsien-Chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gašić, Minlie Huang
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants.
1 code implementation • 29 Nov 2022 • Jiaxin Wen, Yeshuang Zhu, Jinchao Zhang, Jie zhou, Minlie Huang
Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models' reliance on spurious features and improving their generalizability.
no code implementations • 29 Nov 2022 • Zhihong Shao, Fei Huang, Minlie Huang
Given that rich information is hidden behind ubiquitous numbers in text, numerical reasoning over text should be an essential skill of AI systems.
no code implementations • 5 Nov 2022 • Jinfeng Zhou, Bo wang, Minlie Huang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations.
1 code implementation • 17 Oct 2022 • Yuxian Gu, Pei Ke, Xiaoyan Zhu, Minlie Huang
Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks.
1 code implementation • 16 Oct 2022 • Chujie Zheng, Jinfeng Zhou, Yinhe Zheng, Libiao Peng, Zhen Guo, Wenquan Wu, ZhengYu Niu, Hua Wu, Minlie Huang
Dialogue contradiction is a critical issue in open-domain dialogue systems.
no code implementations • 21 Sep 2022 • Sahand Sabour, Wen Zhang, Xiyao Xiao, Yuwei Zhang, Yinhe Zheng, Jiaxin Wen, Jialu Zhao, Minlie Huang
In this study, we analyze the effectiveness of Emohaa in reducing symptoms of mental distress.
no code implementations • 18 Sep 2022 • Jianzhu Yao, Ziqi Liu, Jian Guan, Minlie Huang
We build a new dataset DialStory, which consists of 105k Chinese stories with a large amount of dialogue weaved into the plots to support the evaluation.
1 code implementation • 29 Aug 2022 • Xuekai Zhu, Jian Guan, Minlie Huang, Juan Liu
Moreover, to enhance content preservation, we design a mask-and-fill framework to explicitly fuse style-specific keywords of source texts into generation.
1 code implementation • 18 Aug 2022 • Jinfeng Zhou, Chujie Zheng, Bo wang, Zheng Zhang, Minlie Huang
Empathetic conversation is psychologically supposed to be the result of conscious alignment and interaction between the cognition and affection of empathy.
no code implementations • 16 Aug 2022 • Ryuichi Takanobu, Hao Zhou, Yankai Lin, Peng Li, Jie zhou, Minlie Huang
Modeling these subtasks is consistent with the human agent's behavior patterns.
1 code implementation • 8 Aug 2022 • Jian Guan, Zhenyu Yang, Rongsheng Zhang, Zhipeng Hu, Minlie Huang
Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news.
no code implementations • 13 Jun 2022 • Fei Huang, Tianhua Tao, Hao Zhou, Lei LI, Minlie Huang
Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to reduce the decoding latency by predicting the whole sentences in parallel.
1 code implementation • 6 Jun 2022 • Pei Ke, Haozhe Ji, Zhenyu Yang, Yi Huang, Junlan Feng, Xiaoyan Zhu, Minlie Huang
Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text generation tasks.
1 code implementation • 29 May 2022 • YiRong Chen, Weiquan Fan, Xiaofen Xing, Jianxin Pang, Minlie Huang, Wenjing Han, Qianfeng Tie, Xiangmin Xu
Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation.
Ranked #1 on Emotion Recognition in Conversation on CPED
no code implementations • 23 May 2022 • Yi Song, Yuxian Gu, Minlie Huang
In this work, we formulate \textbf{T}ext \textbf{C}lassification as a \textbf{M}atching problem between the text and the labels, and propose a simple yet effective framework named TCM.
1 code implementation • 16 May 2022 • Fei Huang, Hao Zhou, Yang Liu, Hang Li, Minlie Huang
Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel.
1 code implementation • 22 Apr 2022 • Zhexin Zhang, Jiaxin Wen, Jian Guan, Minlie Huang
Endowing the protagonist with a specific personality is essential for writing an engaging story.
1 code implementation • NAACL 2022 • Jian Guan, Ziqi Liu, Minlie Huang
Teaching morals is one of the most important purposes of storytelling.
1 code implementation • NAACL 2022 • Haozhe Ji, Rongsheng Zhang, Zhenyu Yang, Zhipeng Hu, Minlie Huang
Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling.
1 code implementation • ACL 2022 • Pei Ke, Hao Zhou, Yankai Lin, Peng Li, Jie zhou, Xiaoyan Zhu, Minlie Huang
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
no code implementations • 26 Mar 2022 • Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, HuaWei Shen, HUI ZHANG, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan YAO, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, LiWei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
no code implementations • 23 Mar 2022 • Yequan Wang, Xuying Meng, Yiyi Liu, Aixin Sun, Yao Wang, Yinhe Zheng, Minlie Huang
These models hence are not optimized for dialog-level emotion detection, i. e. to predict the emotion category of a dialog as a whole.
1 code implementation • 17 Mar 2022 • Yuxian Gu, Jiaxin Wen, Hao Sun, Yi Song, Pei Ke, Chujie Zheng, Zheng Zhang, Jianzhu Yao, Lei Liu, Xiaoyan Zhu, Minlie Huang
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.
1 code implementation • ACL 2022 • Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.
1 code implementation • ICLR 2022 • Chencheng Xu, Zhiwei Hong, Minlie Huang, Tao Jiang
Here, we propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage by regularizing locally trained parameters with the loss on generated pseudo data, which encode the knowledge of previous training data learned by the global model.
1 code implementation • ACL 2022 • Siyang Liu, Sahand Sabour, Yinhe Zheng, Pei Ke, Xiaoyan Zhu, Minlie Huang
We provide both empirical and theoretical evidence to show that our method effectively removes the biases existing in the original distinct score.
1 code implementation • 26 Feb 2022 • Chujie Zheng, Sahand Sabour, Jiaxin Wen, Zheng Zhang, Minlie Huang
Applying this approach, we construct AugESC, an augmented dataset for the ESC task, which largely extends the scale and topic coverage of the crowdsourced ESConv corpus.
1 code implementation • 16 Feb 2022 • Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng
The research of open-domain dialog systems has been greatly prospered by neural models trained on large-scale corpora, however, such corpora often introduce various safety problems (e. g., offensive languages, biases, and toxic behaviors) that significantly hinder the deployment of dialog systems in practice.
no code implementations • EMNLP 2020 • Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang
In the lyrics generation process, \textit{Youling} supports traditional one pass full-text generation mode as well as an interactive generation mode, which allows users to select the satisfactory sentences from generated candidates conditioned on preceding context.
1 code implementation • 16 Jan 2022 • Jiawen Deng, Jingyan Zhou, Hao Sun, Chujie Zheng, Fei Mi, Helen Meng, Minlie Huang
To this end, we propose a benchmark --COLD for Chinese offensive language analysis, including a Chinese Offensive Language Dataset --COLDATASET and a baseline detector --COLDETECTOR which is trained on the dataset.
no code implementations • 27 Dec 2021 • Yuan YAO, Qingxiu Dong, Jian Guan, Boxi Cao, Zhengyan Zhang, Chaojun Xiao, Xiaozhi Wang, Fanchao Qi, Junwei Bao, Jinran Nie, Zheni Zeng, Yuxian Gu, Kun Zhou, Xuancheng Huang, Wenhao Li, Shuhuai Ren, Jinliang Lu, Chengqiang Xu, Huadong Wang, Guoyang Zeng, Zile Zhou, Jiajun Zhang, Juanzi Li, Minlie Huang, Rui Yan, Xiaodong He, Xiaojun Wan, Xin Zhao, Xu sun, Yang Liu, Zhiyuan Liu, Xianpei Han, Erhong Yang, Zhifang Sui, Maosong Sun
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
no code implementations • 1 Nov 2021 • Rongsheng Zhang, Yinhe Zheng, Xiaoxi Mao, Minlie Huang
However, fine-tuning all the parameters of the PrLM on a small domain-specific corpus distort the learned generic knowledge, and it is also expensive to deployment a whole fine-tuned PrLM for each domain.
1 code implementation • ACL 2022 • Zhihong Shao, Minlie Huang
Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers.
1 code implementation • Findings (ACL) 2022 • Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
1 code implementation • EMNLP 2021 • Haozhe Ji, Minlie Huang
Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models.
1 code implementation • EMNLP 2021 • Chen Henry Wu, Yinhe Zheng, Xiaoxi Mao, Minlie Huang
Grounded dialogue models generate responses that are grounded on certain concepts.
no code implementations • 14 Sep 2021 • Chujie Zheng, Minlie Huang
In this work, we focus on the few-shot learning for grounded dialog generation (GDG).
1 code implementation • 13 Sep 2021 • Sahand Sabour, Chujie Zheng, Minlie Huang
We evaluate our approach on EmpatheticDialogues, which is a widely-used benchmark dataset for empathetic response generation.
1 code implementation • ACL 2022 • Yuxian Gu, Xu Han, Zhiyuan Liu, Minlie Huang
To ensure the generalization of PPT, we formulate similar classification tasks into a unified task form and pre-train soft prompts for this unified task.
2 code implementations • 30 Aug 2021 • Jian Guan, Zhuoer Feng, Yamei Chen, Ruilin He, Xiaoxi Mao, Changjie Fan, Minlie Huang
Therefore, we propose a story-centric benchmark named LOT for evaluating Chinese long text modeling, which aggregates two understanding tasks and two generation tasks.
1 code implementation • EMNLP 2021 • Fei Mi, Wanhao Zhou, Fengyu Cai, Lingjing Kong, Minlie Huang, Boi Faltings
In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems.
2 code implementations • 3 Aug 2021 • Hao Zhou, Pei Ke, Zheng Zhang, Yuxian Gu, Yinhe Zheng, Chujie Zheng, Yida Wang, Chen Henry Wu, Hao Sun, Xiaocong Yang, Bosi Wen, Xiaoyan Zhu, Minlie Huang, Jie Tang
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
no code implementations • ACL 2021 • Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu
Equipped with GPT-2 and the latest GPT-3, AI Dungeon has been seen as a famous example of the powerful text generation capabilities of large-scale pre-trained language models, and a possibility for future games.
1 code implementation • SIGIR 2021 • Lizi Liao, Le Hong Long, Zheng Zhang, Minlie Huang, Tat-Seng Chua
Second, a set of benchmark results for dialogue state tracking, conversational recommendation, response generation as well as a unified model for multiple tasks are reported.
Ranked #2 on Dialogue State Tracking on MMConv
1 code implementation • 22 Jun 2021 • Silin Gao, Ryuichi Takanobu, Antoine Bosselut, Minlie Huang
To address this task, we propose a TOD system with semi-structured knowledge management, SeKnow, which extends the belief state to manage knowledge with both structured and unstructured contents.
2 code implementations • 20 Jun 2021 • Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan YAO, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun
We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference.
1 code implementation • Findings (ACL) 2021 • Pei Ke, Haozhe Ji, Yu Ran, Xin Cui, LiWei Wang, Linfeng Song, Xiaoyan Zhu, Minlie Huang
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Ranked #1 on KG-to-Text Generation on WebQuestions
1 code implementation • ACL 2021 • Zhihong Shao, Lifeng Shang, Qun Liu, Minlie Huang
This setting gives rise to the spurious solution problem: there may exist many spurious solutions that coincidentally derive the correct answer, but training on such solutions can hurt model performance (e. g., producing wrong solutions or answers).
no code implementations • 14 Jun 2021 • Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Yuan YAO, Ao Zhang, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
no code implementations • 6 Jun 2021 • Yinhe Zheng, Yida Wang, Pei Ke, Zhenyu Yang, Minlie Huang
This paper propose to combine pretrained language models with the modular dialogue paradigm for open-domain dialogue modeling.
1 code implementation • Findings (ACL) 2021 • Fei Huang, Zikai Chen, Chen Henry Wu, Qihan Guo, Xiaoyan Zhu, Minlie Huang
First, we observe that most words in the transferred sentence can be aligned with related words in the source sentence, so we explicitly model word alignments to suppress irrelevant words.
2 code implementations • Findings (ACL) 2021 • Hao Sun, Zhenru Lin, Chujie Zheng, Siyang Liu, Minlie Huang
In this paper, we propose PsyQA, a Chinese dataset of psychological health support in the form of question and answer pair.
1 code implementation • ACL 2021 • Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, Minlie Huang
Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats.
1 code implementation • ACL 2021 • Yilin Niu, Fei Huang, Jiaming Liang, Wenkai Chen, Xiaoyan Zhu, Minlie Huang
In this paper, we present a novel SEmantic-based Question Answering method (SEQA) for unsupervised commonsense question answering.
1 code implementation • ACL 2021 • Yida Wang, Yinhe Zheng, Yong Jiang, Minlie Huang
Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature.
1 code implementation • ACL 2021 • Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang
Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation.
1 code implementation • ACL 2021 • Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang
Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation.
no code implementations • Findings (ACL) 2021 • Xiangzhe Kong, Jialiang Huang, Ziquan Tung, Jian Guan, Minlie Huang
Current storytelling systems focus more ongenerating stories with coherent plots regard-less of the narration style, which is impor-tant for controllable text generation.
1 code implementation • Findings (ACL) 2021 • Chujie Zheng, Yong liu, Wei Chen, Yongcai Leng, Minlie Huang
However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling.
1 code implementation • Findings (ACL) 2021 • Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang
To address this task, we propose a TOD system with hybrid knowledge management, HyKnow.
no code implementations • 1 Jan 2021 • Fei Huang, Jian Guan, Pei Ke, Qihan Guo, Xiaoyan Zhu, Minlie Huang
Despite the great success of Generative Adversarial Networks (GANs) in generating high-quality images, GANs for text generation still face two major challenges: first, most text GANs are unstable in training mainly due to ineffective optimization of the generator, and they heavily rely on maximum likelihood pretraining; second, most text GANs adopt autoregressive generators without latent variables, which largely limits the ability to learn latent representations for natural language text.
1 code implementation • ACL 2021 • Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie zhou
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks.
2 code implementations • ACL 2021 • Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang
Most language understanding models in task-oriented dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution.
no code implementations • 18 Dec 2020 • Zhihong Shao, Zitao Liu, Jiyong Zhang, Zhongqin Wu, Minlie Huang
In this paper, we present AdvExpander, a method that crafts new adversarial examples by expanding text, which is complementary to previous substitution-based methods.
6 code implementations • 1 Dec 2020 • Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun
However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Jifan Yu, Chenyu Wang, Gan Luo, Lei Hou, Juanzi Li, Jie Tang, Minlie Huang, Zhiyuan Liu
Within the prosperity of Massive Open Online Courses (MOOCs), the education applications that automatically provide extracurricular knowledge for MOOC users become rising research topics.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • NeurIPS 2020 • Chencheng Xu, Qiao Liu, Minlie Huang, Tao Jiang
A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly.
Ranked #1 on Molecular Graph Generation on ZINC (QED Top-3 metric)
no code implementations • 12 Nov 2020 • Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro, Abhinav Rastogi, Yun-Nung Chen, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Chao-Wei Huang, Dilek Hakkani-Tür, Jinchao Li, Qi Zhu, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Runze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Minlie Huang, Jianfeng Gao, Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi, David Traum, Maxine Eskenazi, Ahmad Beirami, Eunjoon, Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba
Interactive evaluation of dialog, and 4.
1 code implementation • EMNLP 2021 • Wenchang Ma, Ryuichi Takanobu, Minlie Huang
Growing interests have been attracted in Conversational Recommender Systems (CRS), which explore user preference through conversational interactions in order to make appropriate recommendation.
Ranked #5 on Recommendation Systems on ReDial
3 code implementations • 12 Oct 2020 • Ting Han, Ximing Liu, Ryuichi Takanobu, Yixin Lian, Chongxuan Huang, Dazhen Wan, Wei Peng, Minlie Huang
In this paper, we introduce MultiWOZ 2. 3, in which we differentiate incorrect annotations in dialogue acts from dialogue states, identifying a lack of co-reference when publishing the updated dataset.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Fei Mi, LiangWei Chen, Mengjie Zhao, Minlie Huang, Boi Faltings
Natural language generation (NLG) is an essential component of task-oriented dialog systems.
1 code implementation • 27 Sep 2020 • Yinhe Zheng, Zikai Chen, Rongsheng Zhang, Shilei Huang, Xiaoxi Mao, Minlie Huang
However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the target style is embedded only in unpaired texts that cannot be directly used to train the dialogue model.
1 code implementation • EMNLP 2020 • Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, Xiaoyan Zhu, Minlie Huang
Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, Minlie Huang
Commonsense explanation generation aims to empower the machine's sense-making capability by generating plausible explanations to statements against commonsense.
1 code implementation • EMNLP 2020 • Rongsheng Zhang, Yinhe Zheng, Jianzhi Shao, Xiaoxi Mao, Yadong Xi, Minlie Huang
Further, a model-level distillation process is employed to distill a teacher model trained on high-quality paired data to augmented dialogue pairs, thereby preventing dialogue models from being affected by the noise in the augmented data.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Chujie Zheng, Yunbo Cao, Daxin Jiang, Minlie Huang
In a multi-turn knowledge-grounded dialog, the difference between the knowledge selected at different turns usually provides potential clues to knowledge selection, which has been largely neglected in previous research.
1 code implementation • EMNLP 2020 • Jian Guan, Minlie Huang
Experiments on two story datasets demonstrate that UNION is a reliable measure for evaluating the quality of generated stories, which correlates better with human judgments and is more generalizable than existing state-of-the-art metrics.
2 code implementations • 10 Aug 2020 • Yida Wang, Pei Ke, Yinhe Zheng, Kaili Huang, Yong Jiang, Xiaoyan Zhu, Minlie Huang
The cleaned dataset and the pre-training models will facilitate the research of short-text conversation modeling.
no code implementations • 29 Jul 2020 • Yuexiang Xie, Zhen Wang, Yaliang Li, Bolin Ding, Nezihe Merve Gürel, Ce Zhang, Minlie Huang, Wei. Lin, Jingren Zhou
Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.
no code implementations • 9 Jun 2020 • Mantong Zhou, Zhouxing Shi, Minlie Huang, Xiaoyan Zhu
During document retrieval, a candidate document is scored by considering its relationship to the question and other documents.
no code implementations • SIGDIAL (ACL) 2020 • Ryuichi Takanobu, Qi Zhu, Jinchao Li, Baolin Peng, Jianfeng Gao, Minlie Huang
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations.
1 code implementation • ACL 2020 • Yilin Niu, Fangkai Jiao, Mantong Zhou, Ting Yao, Jingfang Xu, Minlie Huang
Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Zheng Zhang, Lizi Liao, Xiaoyan Zhu, Tat-Seng Chua, Zitao Liu, Yan Huang, Minlie Huang
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
1 code implementation • ACL 2020 • Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.
1 code implementation • ACL 2020 • Ryuichi Takanobu, Runze Liang, Minlie Huang
To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning, which regards both the system and the user as the dialog agents.
no code implementations • 17 Mar 2020 • Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.
5 code implementations • NeurIPS 2020 • Kaidi Xu, Zhouxing Shi, huan zhang, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh
Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense.
2 code implementations • TACL 2020 • Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.
1 code implementation • ICLR 2020 • Zhouxing Shi, huan zhang, Kai-Wei Chang, Minlie Huang, Cho-Jui Hsieh
Robustness verification that aims to formally certify the prediction behavior of neural networks has become an important tool for understanding model behavior and obtaining safety guarantees.
1 code implementation • ACL 2020 • Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
1 code implementation • 3 Feb 2020 • Fei Huang, Dazhen Wan, Zhihong Shao, Pei Ke, Jian Guan, Yilin Niu, Xiaoyan Zhu, Minlie Huang
In text generation evaluation, many practical issues, such as inconsistent experimental settings and metric implementations, are often ignored but lead to unfair evaluation and untenable conclusions.
1 code implementation • TACL 2020 • Jian Guan, Fei Huang, Zhihao Zhao, Xiaoyan Zhu, Minlie Huang
To further capture the causal and temporal dependencies between the sentences in a reasonable story, we employ multi-task learning which combines a discriminative objective to distinguish true and fake stories during fine-tuning.
no code implementations • 16 Nov 2019 • Mantong Zhou, Minlie Huang, Xiaoyan Zhu
In this paper, we address the over-confidence issue and the over-sensitivity issue existing in current RC models simultaneously with the help of external linguistic knowledge.
no code implementations • 14 Nov 2019 • Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee, Adam Atkinson, Baolin Peng, Hannes Schulz, Jianfeng Gao, Jinchao Li, Mahmoud Adada, Minlie Huang, Luis Lastras, Jonathan K. Kummerfeld, Walter S. Lasecki, Chiori Hori, Anoop Cherian, Tim K. Marks, Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta
This paper introduces the Eighth Dialog System Technology Challenge.
2 code implementations • 12 Nov 2019 • Yinhe Zheng, Rongsheng Zhang, Xiaoxi Mao, Minlie Huang
Further, to incorporate the target persona in the decoding process and to balance its contribution, an attention routing structure is devised in the decoder to merge features extracted from the target persona and dialogue contexts using dynamically predicted weights.
1 code implementation • EMNLP 2020 • Pei Ke, Haozhe Ji, Siyang Liu, Xiaoyan Zhu, Minlie Huang
To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and sentiment polarity (inferred from SentiWordNet) into pre-trained models.
1 code implementation • 9 Sep 2019 • Yinhe Zheng, Guanyi Chen, Minlie Huang
Besides, we also demonstrate that the effectiveness of these pseudo OOD data can be further improved by efficiently utilizing unlabeled data.
Generative Adversarial Network Natural Language Understanding +2
no code implementations • Findings of the Association for Computational Linguistics 2020 • Zhouxing Shi, Minlie Huang
Revealing the robustness issues of natural language processing models and improving their robustness is important to their performance under difficult situations.
1 code implementation • IJCNLP 2019 • Ryuichi Takanobu, Hanlin Zhu, Minlie Huang
Many studies apply Reinforcement Learning to learn a dialog policy with the reward function which requires elaborate design and pre-specified user goals.
1 code implementation • IJCNLP 2019 • Pei Ke, Fei Huang, Minlie Huang, Xiaoyan Zhu
The generator is optimized with maximum likelihood estimation augmented by the discriminator's rewards instead of policy gradient.
2 code implementations • IJCNLP 2019 • Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu, Xiaoyan Zhu
Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions.
no code implementations • 25 Jun 2019 • Lizi Liao, Ryuichi Takanobu, Yunshan Ma, Xun Yang, Minlie Huang, Tat-Seng Chua
When traveling to a foreign country, we are often in dire need of an intelligent conversational agent to provide instant and informative responses to our various queries.
1 code implementation • ACL 2019 • Chujie Zheng, Minlie Huang, Aixin Sun
Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora.
no code implementations • 14 May 2019 • Fei Mi, Minlie Huang, Jiyong Zhang, Boi Faltings
Natural language generation (NLG) is an essential component of task-oriented dialogue systems.
no code implementations • 13 May 2019 • Minlie Huang, Xiaoyan Zhu, Jianfeng Gao
This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness.
2 code implementations • ACL 2019 • Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.
no code implementations • 27 Feb 2019 • Hao Zhou, Minlie Huang, Yishun Mao, Changlei Zhu, Peng Shu, Xiaoyan Zhu
Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywords, have no ads presented on their search result pages.
no code implementations • 24 Feb 2019 • Ryuichi Takanobu, Tao Zhuang, Minlie Huang, Jun Feng, Haihong Tang, Bo Zheng
In this paper, we investigate the task of aggregating search results from heterogeneous sources in an E-commerce environment.
Hierarchical Reinforcement Learning reinforcement-learning +3
3 code implementations • 28 Jan 2019 • Yinhe Zheng, Guanyi Chen, Minlie Huang, Song Liu, Xuan Zhu
In this paper, we investigate the problem of incorporating explicit personality traits in dialogue generation to deliver personalized dialogues.
1 code implementation • 1 Dec 2018 • Zhouxing Shi, Minlie Huang
This paper presents a deep sequential model for parsing discourse dependency structures of multi-party dialogues.
Ranked #6 on Discourse Parsing on STAC
2 code implementations • 9 Nov 2018 • Ryuichi Takanobu, Tianyang Zhang, Jiexi Liu, Minlie Huang
The whole extraction process is decomposed into a hierarchy of two-level RL policies for relation detection and entity extraction respectively, so that it is more feasible and natural to deal with overlapping relations.
Ranked #2 on Relation Extraction on NYT24
Entity Extraction using GAN Hierarchical Reinforcement Learning +4
no code implementations • 3 Nov 2018 • Jun Feng, Minlie Huang, Yijie Zhang, Yang Yang, Xiaoyan Zhu
Experimental results show that our model is effective to extract relation mentions from noisy data.
no code implementations • 25 Oct 2018 • Yilin Niu, chao qiao, Hang Li, Minlie Huang
Text similarity calculation is a fundamental problem in natural language processing and related fields.
no code implementations • 17 Sep 2018 • Jun Feng, Heng Li, Minlie Huang, Shichen Liu, Wenwu Ou, Zhirong Wang, Xiaoyan Zhu
The first one is lack of collaboration between scenarios meaning that each strategy maximizes its own objective but ignores the goals of other strategies, leading to a sub-optimal overall performance.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 30 Aug 2018 • Jian Guan, Yansen Wang, Minlie Huang
This task requires not only to understand the context clues which play an important role in planning the plot but also to handle implicit knowledge to make a reasonable, coherent story.
Ranked #3 on Image-guided Story Ending Generation on VIST-E
2 code implementations • 24 Aug 2018 • Jun Feng, Minlie Huang, Li Zhao, Yang Yang, Xiaoyan Zhu
In this paper, we propose a novel model for relation classification at the sentence level from noisy data.
no code implementations • COLING 2018 • Naitong Yu, Jie Zhang, Minlie Huang, Xiaoyan Zhu
Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression.
1 code implementation • ACL 2018 • Pei Ke, Jian Guan, Minlie Huang, Xiaoyan Zhu
Experiments show that our model outperforms state-of-the-art baselines, and it has the ability to generate responses with both controlled sentence function and informative content.
1 code implementation • ACL 2018 • Yansen Wang, Chen-Yi Liu, Minlie Huang, Liqiang Nie
Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched.
no code implementations • 1 May 2018 • Zheng Zhang, Minlie Huang, Zhongzhou Zhao, Feng Ji, Haiqing Chen, Xiaoyan Zhu
Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems.
1 code implementation • COLING 2018 • Mantong Zhou, Minlie Huang, Xiaoyan Zhu
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base.
no code implementations • 16 Sep 2017 • Tom Young, Erik Cambria, Iti Chaturvedi, Minlie Huang, Hao Zhou, Subham Biswas
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence.
no code implementations • ACL 2017 • Qiao Qian, Minlie Huang, Jinhao Lei, Xiaoyan Zhu
This paper deals with sentence-level sentiment classification.
1 code implementation • 9 Jun 2017 • Qiao Qian, Minlie Huang, Haizhou Zhao, Jingfang Xu, Xiaoyan Zhu
Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations.
6 code implementations • 4 Apr 2017 • Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, Bing Liu
Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents.
no code implementations • COLING 2016 • Hao Zhou, Minlie Huang, Xiaoyan Zhu
Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language.
1 code implementation • COLING 2016 • Jun Feng, Minlie Huang, Yang Yang, Xiaoyan Zhu
Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently.
no code implementations • COLING 2016 • Naitong Yu, Minlie Huang, Yuanyuan Shi, Xiaoyan Zhu
The main idea of our method is to leverage phrase properties to choose a subset of optimal phrases for generating the final summary.
no code implementations • 12 Nov 2016 • Qiao Qian, Minlie Huang, Jinhao Lei, Xiaoyan Zhu
In this paper, we propose simple models trained with sentence-level annotation, but also attempt to generating linguistically coherent representations by employing regularizers that model the linguistic role of sentiment lexicons, negation words, and intensity words.
no code implementations • 27 Aug 2016 • Han Xiao, Minlie Huang, Xiaoyan Zhu
Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple.
1 code implementation • 5 May 2016 • Minlie Huang, Yujie Cao, Chao Dong
Sentiment analysis on social media data such as tweets and weibo has become a very important and challenging task.
no code implementations • 17 Apr 2016 • Han Xiao, Minlie Huang, Xiaoyan Zhu
To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple.
no code implementations • 15 Dec 2015 • Han Xiao, Minlie Huang, Xiaoyan Zhu
Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space.
no code implementations • 18 Sep 2015 • Han Xiao, Minlie Huang, Yu Hao, Xiaoyan Zhu
Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence.
no code implementations • 18 Sep 2015 • Han Xiao, Minlie Huang, Yu Hao, Xiaoyan Zhu
Knowledge representation is a major topic in AI, and many studies attempt to represent entities and relations of knowledge base in a continuous vector space.
no code implementations • 20 May 2015 • Jun Feng, Mantong Zhou, Yu Hao, Minlie Huang, Xiaoyan Zhu
TransF regards relation as translation between head entity vector and tail entity vector with flexible magnitude.
no code implementations • 3 Mar 2015 • Biao Liu, Minlie Huang
Prior knowledge has been shown very useful to address many natural language processing tasks.