UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

no code implementations • 17 May 2023 • Ping Yang, Junyu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Jiaxing Zhang, Pingjian Zhang

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis.

Event Extraction named-entity-recognition +3

Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension

1 code implementation • 27 Feb 2023 • Nuo Chen, Hongguang Li, Yinan Bao, Junqing He, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li

Thus, model's comprehension ability towards real scenarios are hard to evaluate reasonably.

Machine Reading Comprehension

TCBERT: A Technical Report for Chinese Topic Classification BERT

no code implementations • 21 Nov 2022 • Ting Han, Kunhao Pan, Xinyu Chen, Dingjie Song, Yuchen Fan, Xinyu Gao, Ruyi Gan, Jiaxing Zhang

Bidirectional Encoder Representations from Transformers or BERT~\cite{devlin-etal-2019-bert} has been one of the base models for various NLP tasks due to its remarkable performance.

Classification Contrastive Learning +1

Solving Math Word Problems via Cooperative Reasoning induced Language Models

1 code implementation • 28 Oct 2022 • Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

This inspires us to develop a cooperative reasoning-induced PLM for solving MWPs, called Cooperative Reasoning (CoRe), resulting in a human-like reasoning architecture with system 1 as the generator and system 2 as the verifier.

Arithmetic Reasoning

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective

1 code implementation • 16 Oct 2022 • Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

We propose a new paradigm for zero-shot learners that is format agnostic, i. e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and sentiment analysis.

Coreference Resolution Multiple-choice +5

Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence

1 code implementation • 7 Sep 2022 • Jiaxing Zhang, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Lin Zhang, Ping Yang, Xinyu Gao, Ziwei Wu, Xiaoqun Dong, Junqing He, Jianheng Zhuo, Qi Yang, Yongfeng Huang, Xiayu Li, Yanghan Wu, Junyu Lu, Xinyu Zhu, Weifeng Chen, Ting Han, Kunhao Pan, Rui Wang, Hao Wang, XiaoJun Wu, Zhongshen Zeng, Chongpei Chen

We hope that this project will be the foundation of Chinese cognitive intelligence.

Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss

1 code implementation • 5 Aug 2022 • Junjie Wang, Yuxiang Zhang, Ping Yang, Ruyi Gan

This report describes a pre-trained language model Erlangshen with propensity-corrected loss, the No. 1 in CLUE Semantic Matching Challenge.

Language Modelling Masked Language Modeling

Unified BERT for Few-shot Natural Language Understanding

no code implementations • 24 Jun 2022 • Junyu Lu, Ping Yang, Ruyi Gan, Jing Yang, Jiaxing Zhang

Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas.

Natural Language Understanding

BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model

1 code implementation • BioNLP (ACL) 2022 • Hongyi Yuan, Zheng Yuan, Ruyi Gan, Jiaxing Zhang, Yutao Xie, Sheng Yu

Furthermore, we conduct ablation studies on the pretraining tasks for BioBART and find that sentence permutation has negative effects on downstream tasks.

Entity Linking Language Modelling +5