no code implementations • LT4HALA (LREC) 2022 • Wei Xinyuan, Liu Weihao, Qing Zong, Zhang Shaoqing, Baotian Hu
We participate in the LT4HALA2022 shared task EvaHan.
no code implementations • EMNLP 2020 • Dongfang Li, Baotian Hu, Qingcai Chen, Weihua Peng, Anqi Wang
Machine reading comprehension (MRC) has achieved significant progress on the open domain in recent years, mainly due to large-scale pre-trained language models.
1 code implementation • 17 Apr 2024 • Dongfang Li, Zhenyu Liu, Xinshuo Hu, Zetian Sun, Baotian Hu, Min Zhang
In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector.
no code implementations • 27 Mar 2024 • Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content.
1 code implementation • 26 Feb 2024 • Liangxin Liu, Xuebo Liu, Derek F. Wong, Dongfang Li, Ziyi Wang, Baotian Hu, Min Zhang
In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself.
no code implementations • 22 Feb 2024 • Xinshuo Hu, Baotian Hu, Dongfang Li, Xiaoguang Li, Lifeng Shang
The present study introduces the knowledge-augmented generator, which is specifically designed to produce information that remains grounded in contextual knowledge, regardless of alterations in the context.
no code implementations • 21 Feb 2024 • Yunxin Li, Xinyu Chen, Baotian Hu, Haoyuan Shi, Min Zhang
Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e. g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i. e., connecting visuals to their relevant knowledge.
1 code implementation • 21 Feb 2024 • Yunxin Li, Baotian Hu, Wenhan Luo, Lin Ma, Yuxin Ding, Min Zhang
For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description.
no code implementations • 29 Dec 2023 • Dongfang Li, Baotian Hu, Qingcai Chen, Shan He
Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI.
no code implementations • 27 Nov 2023 • Yunxin Li, Baotian Hu, Wei Wang, Xiaochun Cao, Min Zhang
These models predominantly map visual information into language representation space, leveraging the vast knowledge and powerful text generation abilities of LLMs to produce multimodal instruction-following responses.
no code implementations • 15 Nov 2023 • Ziyang Chen, Dongfang Li, Xiang Zhao, Baotian Hu, Min Zhang
In this paper, we tackle the significant challenge of temporal knowledge reasoning in Large Language Models (LLMs), an area where such models frequently encounter difficulties.
1 code implementation • 14 Nov 2023 • Zhenran Xu, Senbao Shi, Baotian Hu, Jindi Yu, Dongfang Li, Min Zhang, Yuxiang Wu
Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks.
no code implementations • 13 Nov 2023 • Yunxin Li, Longyue Wang, Baotian Hu, Xinyu Chen, Wanqi Zhong, Chenyang Lyu, Wei Wang, Min Zhang
The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA).
1 code implementation • 7 Nov 2023 • Dongfang Li, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Ziyang Chen, Baotian Hu, Aiguo Wu, Min Zhang
Open-domain generative systems have gained significant attention in the field of conversational AI (e. g., generative search engines).
1 code implementation • 19 Oct 2023 • Yulin Chen, Zhenran Xu, Baotian Hu, Min Zhang
Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base.
1 code implementation • 19 Oct 2023 • Zhenran Xu, Yulin Chen, Baotian Hu, Min Zhang
Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability.
1 code implementation • 16 Aug 2023 • Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang
To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.
1 code implementation • 22 Jun 2023 • Senbao Shi, Zhenran Xu, Baotian Hu, Min Zhang
Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base.
1 code implementation • 22 May 2023 • Dongfang Li, Jindi Yu, Baotian Hu, Zhenran Xu, Min Zhang
As ChatGPT and GPT-4 spearhead the development of Large Language Models (LLMs), more researchers are investigating their performance across various tasks.
1 code implementation • 8 May 2023 • Yunxin Li, Baotian Hu, Xinyu Chen, Yuxin Ding, Lin Ma, Min Zhang
This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues.
1 code implementation • 5 May 2023 • Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Yong Xu, Min Zhang
LMEye addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic visual information interaction.
1 code implementation • 3 May 2023 • Yunxin Li, Baotian Hu, Yuxin Ding, Lin Ma, Min Zhang
Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR.
1 code implementation • 16 Dec 2022 • Qian Yang, Qian Chen, Wen Wang, Baotian Hu, Min Zhang
Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low.
no code implementations • COLING 2022 • Dongfang Li, Baotian Hu, Qingcai Chen
To address these challenges, we propose Prompt-based Text Entailment (PTE) for low-resource named entity recognition, which better leverages knowledge in the PLMs.
Low Resource Named Entity Recognition named-entity-recognition +3
1 code implementation • 6 Nov 2022 • Dongfang Li, Baotian Hu, Qingcai Chen
We conduct extensive experiments on six datasets with two popular pre-trained language models in the in-domain and out-of-domain settings.
1 code implementation • 30 Oct 2022 • Yuxiang Wu, Yu Zhao, Baotian Hu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel
Experiments on various knowledge-intensive tasks such as question answering and dialogue datasets show that, simply augmenting parametric models (T5-base) using our method produces more accurate results (e. g., 25. 8 -> 44. 3 EM on NQ) while retaining a high throughput (e. g., 1000 queries/s on NQ).
Ranked #4 on Question Answering on KILT: ELI5
1 code implementation • 26 Jul 2022 • Zhenran Xu, Zifei Shan, Yuxin Li, Baotian Hu, Bing Qin
We then establish a strong baseline that scores a R@1 of 46. 2% on Few-Shot and 76. 6% on Zero-Shot on our dataset.
1 code implementation • 23 Jul 2022 • Qian Yang, Yunxin Li, Baotian Hu, Lin Ma, Yuxing Ding, Min Zhang
CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr.
no code implementations • 17 Jun 2022 • Yu Zhao, Yunxin Li, Yuxiang Wu, Baotian Hu, Qingcai Chen, Xiaolong Wang, Yuxin Ding, Min Zhang
To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i. e., knowledge-aware dialogue graph encoder and recall-enhanced generator.
no code implementations • 17 Jun 2022 • Yu Zhao, Xinshuo Hu, Yunxin Li, Baotian Hu, Dongfang Li, Sichao Chen, Xiaolong Wang
In this paper, we propose a general Multi-Skill Dialog Framework, namely MSDF, which can be applied in different dialog tasks (e. g. knowledge grounded dialog and persona based dialog).
1 code implementation • 20 Dec 2021 • Dongfang Li, Baotian Hu, Qingcai Chen, Tujie Xu, Jingcong Tao, Yunan Zhang
Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification.
no code implementations • 4 Jul 2021 • Yunxin Li, Qian Yang, Qingcai Chen, Lin Ma, Baotian Hu, Xiaolong Wang, Yuxin Ding
Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance.
no code implementations • 1 Jul 2021 • Yunxin Li, Yu Zhao, Baotian Hu, Qingcai Chen, Yang Xiang, Xiaolong Wang, Yuxin Ding, Lin Ma
Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters.
1 code implementation • ACL 2021 • Shuoran Jiang, Qingcai Chen, Xin Liu, Baotian Hu, Lisai Zhang
In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer.
no code implementations • 27 Mar 2021 • Dongfang Li, Jingcong Tao, Qingcai Chen, Baotian Hu
The experimental results show that the proposed approach can generate reasonable explanations for its predictions even with a small-scale training corpus.
no code implementations • 1 Jan 2021 • Zhaobin Xu, Baotian Hu, Buzhou Tang
It has two major parts.
no code implementations • COLING 2020 • Youcheng Pan, Qingcai Chen, Weihua Peng, Xiaolong Wang, Baotian Hu, Xin Liu, Junying Chen, Wenxiu Zhou
To exploit the domain knowledge to guarantee the correctness of generated text has been a hot topic in recent years, especially for high professional domains such as medical.
no code implementations • 16 Apr 2020 • Kai Chen, Fayuan Li, Baotian Hu, Weihua Peng, Qingcai Chen, Hong Yu
We further design a reconstruction mechanism with a novel objective function that can reconstruct the whole entry of the used data sequentially from the hidden states of the decoder, which aids the accuracy of the generated text.
no code implementations • 7 Apr 2020 • Xin Liu, Qingcai Chen, Yan Liu, Joanna Siebert, Baotian Hu, Xiang-Ping Wu, Buzhou Tang
We propose a Capsule network-based method to Decompose the unsupervised word Embedding of an ambiguous word into context specific Sense embedding, called CapsDecE2S.
1 code implementation • 7 Apr 2020 • Lisai Zhang, Qingcai Chen, Baotian Hu, Shuoran Jiang
To fulfill such a task, we propose a novel inpainting model named Text-Guided Dual Attention Inpainting Network (TDANet).
no code implementations • WS 2019 • Dongfang Li, Ying Xiong, Baotian Hu, Hanyang Du, Buzhou Tang, Qingcai Chen
In this paper, we present our approaches for trigger word detection (task 1) and the identification of its thematic role (task 2) in AGAC track of BioNLP Open Shared Task 2019.
no code implementations • NAACL 2018 • Tu Vu, Baotian Hu, Tsendsuren Munkhdalai, Hong Yu
Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications.
Ranked #1 on Text Simplification on PWKP / WikiSmall
no code implementations • 19 Apr 2018 • Yuxiang Wu, Baotian Hu
As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns.
Ranked #3 on Text Summarization on CNN / Daily Mail (Anonymized)
no code implementations • 13 Oct 2016 • Baotian Hu, Xin Liu, Xiang-Ping Wu, Qingcai Chen
In this paper, we propose a novel model, named Stroke Sequence-dependent Deep Convolutional Neural Network (SSDCNN), using the stroke sequence information and eight-directional features for Online Handwritten Chinese Character Recognition (OLHCCR).
no code implementations • IJCNLP 2015 • Xiaoqiang Zhou, Baotian Hu, Qingcai Chen, Buzhou Tang, Xiaolong Wang
In this paper, the answer selection problem in community question answering (CQA) is regarded as an answer sequence labeling task, and a novel approach is proposed based on the recurrent architecture for this problem.
3 code implementations • EMNLP 2015 • Baotian Hu, Qingcai Chen, Fangze Zhu
Automatic text summarization is widely regarded as the highly difficult problem, partially because of the lack of large text summarization data set.
Ranked #1 on Text Summarization on LCSTS
2 code implementations • NeurIPS 2014 • Baotian Hu, Zhengdong Lu, Hang Li, Qingcai Chen
Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic, RetrievalQA}.
Ranked #3 on Question Answering on SemEvalCQA
no code implementations • IJCNLP 2015 • Zhaopeng Tu, Baotian Hu, Zhengdong Lu, Hang Li
We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages.