no code implementations • EMNLP 2020 • Meixi Wu, Wenya Wang, Sinno Jialin Pan
Though deep learning has achieved significant success in various NLP tasks, most deep learning models lack the capability of encoding explicit domain knowledge to model complex causal relationships among different types of variables.
no code implementations • CL (ACL) 2021 • Wenya Wang, Sinno Jialin Pan
Various deep neural networks have been proposed to jointly perform entity extraction and relation prediction, which only propagate information implicitly via representation learning.
no code implementations • ACL 2022 • Wenya Wang, Sinno Pan
Multi-hop reading comprehension requires an ability to reason across multiple documents.
1 code implementation • 21 May 2024 • Hang Chen, Xinyu Yang, Jiaying Zhu, Wenya Wang
Empirical results show that (1) our method gives consistent measurements which align with existing observations based on performance metrics, validating the effectiveness of our emergence quantification; (2) our proposed metric uncovers novel emergence patterns such as the correlations between the variance of our metric and the number of ``shots'' in ICL, which further suggests a new way of interpreting hallucinations in LLMs; (3) we offer a potential solution towards estimating the emergence of larger and closed-resource LMs via smaller LMs like GPT-2.
no code implementations • 11 Apr 2024 • Quanyu Long, Yin Wu, Wenya Wang, Sinno Jialin Pan
Counter-intuitively, we find that the demonstrations have a marginal impact on provoking discriminative knowledge of language models.
no code implementations • 25 Mar 2024 • Ziyan Wang, Yingpeng Du, Zhu Sun, Haoyan Chua, Kaidong Feng, Wenya Wang, Jie Zhang
However, the former methods struggle with optimal prompts to elicit the correct reasoning of LLMs due to the lack of task-specific feedback, leading to unsatisfactory recommendations.
1 code implementation • 22 Feb 2024 • Qiyuan He, Yizhong Wang, Wenya Wang
Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training.
1 code implementation • 21 Feb 2024 • Quanyu Long, Yue Deng, Leilei Gan, Wenya Wang, Sinno Jialin Pan
To achieve this, we propose a perilous backdoor attack triggered by grammar errors in dense passage retrieval.
1 code implementation • 12 Feb 2024 • Hui Liu, Wenya Wang, Haoru Li, Haoliang Li
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia.
1 code implementation • 6 Feb 2024 • Chengyu Huang, Zeqiu Wu, Yushi Hu, Wenya Wang
While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources.
no code implementations • 6 Feb 2024 • Soumya Sanyal, Tianyi Xiao, Jiacheng Liu, Wenya Wang, Xiang Ren
Finally, we use this model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.
1 code implementation • 24 Nov 2023 • Hui Liu, Wenya Wang, Hao Sun, Anderson Rocha, Haoliang Li
We also propose a framework that simultaneously considers application scenarios of domain generalization (in which the target domain data is unavailable) and domain adaptation (in which unlabeled target domain data is available).
no code implementations • 20 Nov 2023 • Quanyu Long, Wenya Wang, Sinno Jialin Pan
Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning.
2 code implementations • 10 May 2023 • Hui Liu, Wenya Wang, Haoliang Li
Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information.
1 code implementation • 5 May 2023 • Jiacheng Liu, Wenya Wang, Dianzhuo Wang, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi
Despite the much discussed capabilities of today's language models, they are still prone to silly and unexpected commonsense failures.
1 code implementation • 7 Oct 2022 • Hui Liu, Wenya Wang, Haoliang Li
In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attention mechanism and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm.
1 code implementation • 2 Sep 2022 • Wenya Wang, Vivek Srikumar, Hanna Hajishirzi, Noah A. Smith
In question answering requiring common sense, language models (e. g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance.
no code implementations • NAACL 2022 • Quanyu Long, Tianze Luo, Wenya Wang, Sinno Jialin Pan
In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach.
no code implementations • 16 Jun 2020 • Tao Liang, Wenya Wang, Fengmao Lv
Specifically, the aspect category information is used to construct pivot knowledge for transfer with assumption that the interactions between sentence-level aspect category and token-level aspect terms are invariant across domains.
no code implementations • 6 Dec 2019 • Wenya Wang, Sinno Jialin Pan
To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner.
1 code implementation • NeurIPS 2019 • Shangyu Chen, Wenya Wang, Sinno Jialin Pan
However, these methods only heuristically make training-based quantization applicable, without further analysis on how the approximated gradients can assist training of a quantized network.
no code implementations • CL 2019 • Wenya Wang, Sinno Jialin Pan
In this article, we explore the constructions of recursive neural networks based on the dependency tree of each sentence for associating syntactic structure with feature learning.
no code implementations • ACL 2018 • Wenya Wang, Sinno Jialin Pan
Fine-grained opinion analysis aims to extract aspect and opinion terms from each sentence for opinion summarization.
no code implementations • AAAI 2017 • Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao
To achieve this task, one effective approach is to exploit relations between aspect terms and opinion terms by parsing syntactic structure for each sentence.
no code implementations • 6 Feb 2017 • Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier
This problem involves the identification of aspect and opinion terms within each sentence, as well as the categorization of the identified terms.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • EMNLP 2016 • Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao
Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)