Search Results for author: Bang Liu

Found 46 papers, 23 papers with code

EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

1 code implementation2 May 2024 Shengyao Lu, Bang Liu, Keith G. Mills, Jiao He, Di Niu

Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness.

OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following

no code implementations5 Mar 2024 Haochen Shi, Zhiyuan Sun, Xingdi Yuan, Marc-Alexandre Côté, Bang Liu

Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions.

Instruction Following

Resonance RoPE: Improving Context Length Generalization of Large Language Models

1 code implementation29 Feb 2024 Suyuchen Wang, Ivan Kobyzev, Peng Lu, Mehdi Rezagholizadeh, Bang Liu

This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with out-of-distribution (OOD) token positions in longer sequences.

Language Modelling Position

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

1 code implementation26 Jan 2024 Shengyao Lu, Keith G. Mills, Jiao He, Bang Liu, Di Niu

Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability.

Attribute Decision Making

Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games

no code implementations1 Dec 2023 Dekun Wu, Haochen Shi, Zhiyuan Sun, Bang Liu

In this study, we explore the application of Large Language Models (LLMs) in \textit{Jubensha}, a Chinese detective role-playing game and a novel area in Artificial Intelligence (AI) driven gaming.

In-Context Learning Language Modelling +2

HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science

1 code implementation12 Oct 2023 Yu Song, Santiago Miret, huan zhang, Bang Liu

We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee).

Language Modelling

Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models

no code implementations27 May 2023 Zhong Zhang, Bang Liu, Junming Shao

Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs.

MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling

1 code implementation14 May 2023 Yu Song, Santiago Miret, Bang Liu

Our experiments in this low-resource training setting show that language models pretrained on scientific text outperform BERT trained on general text.

named-entity-recognition Named Entity Recognition +2

SkillQG: Learning to Generate Question for Reading Comprehension Assessment

no code implementations8 May 2023 Xiaoqiang Wang, Bang Liu, Siliang Tang, Lingfei Wu

We present $\textbf{$\texttt{SkillQG}$}$: a question generation framework with controllable comprehension types for assessing and improving machine reading comprehension models.

Machine Reading Comprehension Question Answering +2

MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction

1 code implementation21 Oct 2022 Wangjie Jiang, Zhihao Ye, Zijing Ou, Ruihui Zhao, Jianguang Zheng, Yi Liu, Siheng Li, Bang Liu, Yujiu Yang, Yefeng Zheng

In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples.

Optical Character Recognition Optical Character Recognition (OCR) +1

Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

1 code implementation9 Oct 2022 Yi Cheng, Wenge Liu, Wenjie Li, Jiashuo Wang, Ruihui Zhao, Bang Liu, Xiaodan Liang, Yefeng Zheng

Providing Emotional Support (ES) to soothe people in emotional distress is an essential capability in social interactions.

Dialogue Generation

DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization

1 code implementation ICCV 2023 Xinlin Li, Bang Liu, Rui Heng Yang, Vanessa Courville, Chao Xing, Vahid Partovi Nia

We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance.

Quantization Transfer Learning

Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoning

no code implementations17 May 2022 Ailisi Li, Xueyao Jiang, Bang Liu, Jiaqing Liang, Yanghua Xiao

Math Word Problems (MWP) is an important task that requires the ability of understanding and reasoning over mathematical text.


R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning

1 code implementation ICLR 2022 Shengyao Lu, Bang Liu, Keith G. Mills, Shangling Jui, Di Niu

Systematicity, i. e., the ability to recombine known parts and rules to form new sequences while reasoning over relational data, is critical to machine intelligence.

Relation Relational Reasoning

QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance

no code implementations29 Apr 2022 Xiaoqiang Wang, Bang Liu, Siliang Tang, Lingfei Wu

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated questions and input contexts.

Question Generation Question-Generation +1

Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision

1 code implementation28 Mar 2022 Sijie Cheng, Zhouhong Gu, Bang Liu, Rui Xie, Wei Wu, Yanghua Xiao

Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.

Contrastive Learning Taxonomy Expansion

MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering

1 code implementation CVPR 2022 Yang Ding, Jing Yu, Bang Liu, Yue Hu, Mingxin Cui, Qi Wu

Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding.

Implicit Relations Question Answering +2

Feeding What You Need by Understanding What You Learned

no code implementations ACL 2022 Xiaoqiang Wang, Bang Liu, Fangli Xu, Bo Long, Siliang Tang, Lingfei Wu

In this paper, we argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data based on its learning status.

Machine Reading Comprehension

Deep learning enhanced Rydberg multifrequency microwave recognition

no code implementations28 Feb 2022 Zong-Kai Liu, Li-Hua Zhang, Bang Liu, Zheng-Yuan Zhang, Guang-Can Guo, Dong-Sheng Ding, Bao-Sen Shi

Recognition of multifrequency microwave (MW) electric fields is challenging because of the complex interference of multifrequency fields in practical applications.

Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation

no code implementations13 Jan 2022 Yuyan Chen, Yanghua Xiao, Bang Liu

In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models.

Informativeness Question Answering +2

Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning

no code implementations10 Jan 2022 Martin Weyssow, Houari Sahraoui, Bang Liu

The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures.

Code Search Language Modelling

TAG: Toward Accurate Social Media Content Tagging with a Concept Graph

no code implementations13 Oct 2021 Jiuding Yang, Weidong Guo, Bang Liu, Yakun Yu, Chaoyue Wang, Jinwen Luo, Linglong Kong, Di Niu, Zhen Wen

Although conceptualization has been widely studied in semantics and knowledge representation, it is still challenging to find the most accurate concept phrases to characterize the main idea of a text snippet on the fast-growing social media.

Dependency Parsing Graph Matching +4

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

1 code implementation12 Oct 2021 Jiayuan Ding, Tong Xiang, Zijing Ou, Wangyang Zuo, Ruihui Zhao, Chenghua Lin, Yefeng Zheng, Bang Liu

In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query.

$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks

1 code implementation NeurIPS 2021 Xinlin Li, Bang Liu, YaoLiang Yu, Wulong Liu, Chunjing Xu, Vahid Partovi Nia

Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural networks.

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction

no code implementations Findings (ACL) 2021 Zhexue Chen, Hong Huang, Bang Liu, Xuanhua Shi, Hai Jin

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment.

Aspect Sentiment Triplet Extraction Sentence

Attend and select: A segment selective transformer for microblog hashtag generation

1 code implementation6 Jun 2021 Qianren Mao, Xi Li, Bang Liu, Shu Guo, Peng Hao, JianXin Li, Lihong Wang

These tokens or phrases may originate from primary fragmental textual pieces (e. g., segments) in the original text and are separated into different segments.

Noised Consistency Training for Text Summarization

no code implementations28 May 2021 Junnan Liu, Qianren Mao, Bang Liu, Hao Peng, Hongdong Zhu, JianXin Li

In this paper, we argue that this limitation can be overcome by a semi-supervised approach: consistency training which is to leverage large amounts of unlabeled data to improve the performance of supervised learning over a small corpus.

Abstractive Text Summarization

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

no code implementations ACL 2021 Yi Cheng, SiYao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels.

Question Answering Question Generation +1

S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks

no code implementations NeurIPS 2021 Xinlin Li, Bang Liu, YaoLiang Yu, Wulong Liu, Chunjing Xu, Vahid Partovi Nia

Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy-efficient compared to conventional neural networks.

Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management

1 code implementation NAACL 2021 Zhengxu Hou, Bang Liu, Ruihui Zhao, Zijing Ou, Yafei Liu, Xi Chen, Yefeng Zheng

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs.

Management reinforcement-learning +1

QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications

no code implementations27 Oct 2020 Mingjun Zhao, ShengLi Yan, Bang Liu, Xinwang Zhong, Qian Hao, Haolan Chen, Di Niu, Bowei Long, Weidong Guo

In this paper, we present QBSUM, a high-quality large-scale dataset consisting of 49, 000+ data samples for the task of Chinese query-based document summarization.

Document Summarization Machine Reading Comprehension

GIANT: Scalable Creation of a Web-scale Ontology

1 code implementation5 Apr 2020 Bang Liu, Weidong Guo, Di Niu, Jinwen Luo, Chaoyue Wang, Zhen Wen, Yu Xu

These services will benefit from a highly structured and web-scale ontology of entities, concepts, events, topics and categories.

News Recommendation

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus

2 code implementations27 Jan 2020 Bang Liu, Haojie Wei, Di Niu, Haolan Chen, Yancheng He

In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions.

Answer Generation Chatbot +5

A User-Centered Concept Mining System for Query and Document Understanding at Tencent

no code implementations21 May 2019 Bang Liu, Weidong Guo, Di Niu, Chaoyue Wang, Shunnan Xu, Jinghong Lin, Kunfeng Lai, Yu Xu

We further present our techniques to tag documents with user-centered concepts and to construct a topic-concept-instance taxonomy, which has helped to improve search as well as news feeds recommendation in Tencent QQ Browser.

document understanding TAG

Multiresolution Graph Attention Networks for Relevance Matching

no code implementations27 Feb 2019 Ting Zhang, Bang Liu, Di Niu, Kunfeng Lai, Yu Xu

In this paper, we are especially interested in relevance matching between a piece of short text and a long document, which is critical to problems like query-document matching in information retrieval and web searching.

Graph Attention Information Retrieval +4

Learning to Generate Questions by Learning What not to Generate

no code implementations27 Feb 2019 Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu

In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation.

Multi-Task Learning Question Answering +2

Growing Story Forest Online from Massive Breaking News

1 code implementation1 Mar 2018 Bang Liu, Di Niu, Kunfeng Lai, Linglong Kong, Yu Xu

We describe our experience of implementing a news content organization system at Tencent that discovers events from vast streams of breaking news and evolves news story structures in an online fashion.

Graph Generation Information Threading

Matching Natural Language Sentences with Hierarchical Sentence Factorization

no code implementations1 Mar 2018 Bang Liu, Ting Zhang, Fred X. Han, Di Niu, Kunfeng Lai, Yu Xu

The proposed sentence factorization technique leads to the invention of: 1) a new unsupervised distance metric which calculates the semantic distance between a pair of text snippets by solving a penalized optimal transport problem while preserving the logical relationship of words in the reordered sentences, and 2) new multi-scale deep learning models for supervised semantic training, based on factorized sentence hierarchies.

Paraphrase Identification Sentence

Matching Article Pairs with Graphical Decomposition and Convolutions

1 code implementation ACL 2019 Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu

Identifying the relationship between two articles, e. g., whether two articles published from different sources describe the same breaking news, is critical to many document understanding tasks.

document understanding Question Answering +2

Cannot find the paper you are looking for? You can Submit a new open access paper.