no code implementations • 30 Oct 2023 • Xuefeng Bai, Jialong Wu, Yulong Chen, Zhongqing Wang, Yue Zhang
Constituency parsing is a fundamental yet unsolved natural language processing task.
1 code implementation • 8 Jul 2023 • Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Michael Zhu, Yue Zhang
Additionally, based on the same intuition, we propose a 2-Step method, which takes both conversation and summary as input to simulate human annotation process.
1 code implementation • 26 May 2023 • Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, Yue Zhang
The Open-Domain Question Answering (ODQA) task involves retrieving and subsequently generating answers from fine-grained relevant passages within a database.
no code implementations • 10 May 2023 • Yun Luo, Zhen Yang, Xuefeng Bai, Fandong Meng, Jie zhou, Yue Zhang
Intuitively, the representation forgetting can influence the general knowledge stored in pre-trained language models (LMs), but the concrete effect is still unclear.
1 code implementation • 22 Oct 2022 • Xuefeng Bai, Seng Yang, Leyang Cui, Linfeng Song, Yue Zhang
Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively.
1 code implementation • COLING 2022 • Xuefeng Bai, Linfeng Song, Yue Zhang
However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context.
2 code implementations • 1 May 2022 • Yulong Chen, Ming Zhong, Xuefeng Bai, Naihao Deng, Jing Li, Xianchao Zhu, Yue Zhang
We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation.
Abstractive Dialogue Summarization Cross-Lingual Abstractive Summarization +3
2 code implementations • ACL 2022 • Xuefeng Bai, Yulong Chen, Yue Zhang
To our knowledge, we are the first to consider pre-training on semantic graphs.
Ranked #1 on AMR-to-Text Generation on Bio (BLEU metric, using extra training data)
1 code implementation • ACL 2021 • Xuefeng Bai, Yulong Chen, Linfeng Song, Yue Zhang
Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities.
Ranked #8 on Dialog Relation Extraction on DialogRE
1 code implementation • EMNLP 2020 • Xuefeng Bai, Linfeng Song, Yue Zhang
AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph.
Ranked #9 on AMR-to-Text Generation on LDC2017T10
1 code implementation • 22 Feb 2020 • Xuefeng Bai, Pengbo Liu, Yue Zhang
Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts.
Ranked #1 on Aspect-Based Sentiment Analysis (ABSA) on MAMS
no code implementations • 3 Sep 2019 • Xuefeng Bai, Yue Zhang, Hailong Cao, Tiejun Zhao
Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation.