Search Results for author: Kang Liu

Found 167 papers, 56 papers with code

Augmentation, Retrieval, Generation: Event Sequence Prediction with a Three-Stage Sequence-to-Sequence Approach

no code implementations COLING 2022 Bo Zhou, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, Jiexin Xu, XiaoJian Jiang, Qiuxia Li

Currently existing approach models this task as a statistical induction problem, to predict a sequence of events by exploring the similarity between the given goal and the known sequences of events.

Retrieval

Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation

no code implementations TU (COLING) 2022 Minjun Zhu, Yixuan Weng, Bin Li, Shizhu He, Kang Liu, Jun Zhao

In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks.

Dialogue Understanding Knowledge Distillation +2

Generating Temporally-ordered Event Sequences via Event Optimal Transport

no code implementations COLING 2022 Bo Zhou, Yubo Chen, Kang Liu, Jun Zhao, Jiexin Xu, XiaoJian Jiang, Qiuxia Li

The other issue is that the model adopts a word-level objective to model events in texts, failing to evaluate the predicted results of the model from the perspective of event sequence.

CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities

no code implementations SemEval (NAACL) 2022 Jia Fu, Zhen Gan, Zhucong Li, Sirui Li, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao

This paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition, Track 9 - Chinese.

Chinese Named Entity Recognition Data Augmentation +3

CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers

1 code implementation COLING 2022 Yiming Ju, Weikang Wang, Yuanzhe Zhang, Suncong Zheng, Kang Liu, Jun Zhao

To bridge the gap, we propose a new task: conditional question answering with hierarchical multi-span answers, where both the hierarchical relations and the conditions need to be extracted.

Question Answering

CroAno : A Crowd Annotation Platform for Improving Label Consistency of Chinese NER Dataset

no code implementations EMNLP (ACL) 2021 Baoli Zhang, Zhucong Li, Zhen Gan, Yubo Chen, Jing Wan, Kang Liu, Jun Zhao, Shengping Liu, Yafei Shi

2) Inconsistency Detector: CroAno employs a detector to locate corpus-level label inconsistency and provides users an interface to correct inconsistent entities in batches.

Chinese Named Entity Recognition Management +3

Event Extraction as Machine Reading Comprehension

no code implementations EMNLP 2020 Jian Liu, Yubo Chen, Kang Liu, Wei Bi, Xiaojiang Liu

ii) Our model is excelled in the data-scarce scenario, for example, obtaining 49. 8{\%} in F1 for event argument extraction with only 1{\%} data, compared with 2. 2{\%} of the previous method.

Event Argument Extraction Event Extraction +5

Scene Restoring for Narrative Machine Reading Comprehension

no code implementations EMNLP 2020 Zhixing Tian, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yantao Jia, Zhicheng Sheng

Inspired by this behavior of humans, we propose a method to let the machine imagine a scene during reading narrative for better comprehension.

Cloze Test Machine Reading Comprehension +1

Set Generation Networks for End-to-End Knowledge Base Population

no code implementations EMNLP 2021 Dianbo Sui, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, Wei Bi

In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts.

Decoder Knowledge Base Population +2

Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing

no code implementations ACL 2022 Runxin Sun, Shizhu He, Chong Zhu, Yaohan He, Jinlong Li, Jun Zhao, Kang Liu

Text-to-SQL aims to parse natural language questions into SQL queries, which is valuable in providing an easy interface to access large databases.

SQL Parsing Text-To-SQL

Biomedical Concept Normalization by Leveraging Hypernyms

1 code implementation EMNLP 2021 Cheng Yan, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yafei Shi, Shengping Liu

Biomedical Concept Normalization (BCN) is widely used in biomedical text processing as a fundamental module.

Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification

1 code implementation EMNLP 2021 Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, Jun Zhao

Moreover, we propose an Uncertain Information Aggregation module to leverage the global structure for integrating the local information.

Sentence

Knowledge Localization: Mission Not Accomplished? Enter Query Localization!

no code implementations23 May 2024 YuHeng Chen, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

This theory is based on the knowledge localization (KL) assumption, which suggests that a fact can be localized to a few knowledge storage units, namely knowledge neurons.

Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation

1 code implementation23 May 2024 Kang Liu, Zhuoqi Ma, Xiaolu Kang, Zhusi Zhong, Zhicheng Jiao, Grayson Baird, Harrison Bai, Qiguang Miao

This process allows the text decoder to attend to discriminative features of X-ray images, assimilate historical diagnostic information from similar cases, and understand the examination intention of patients.

Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation

1 code implementation15 May 2024 Kang Liu, Zhuoqi Ma, Mengmeng Liu, Zhicheng Jiao, Xiaolu Kang, Qiguang Miao, Kun Xie

Additionally, existing methods for similar historical cases retrieval face suboptimal performance owing to the modal gap issue.

Medical Report Generation Retrieval +3

Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling

no code implementations5 May 2024 Jinmin Li, Tao Dai, Jingyun Zhang, Kang Liu, Jun Wang, Shaoming Wang, Shu-Tao Xia, rizen guo

Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling.

Generative Adversarial Network SSIM

SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings

no code implementations25 Apr 2024 Kang Liu

Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework.

Contrastive Learning Information Retrieval +5

KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering

no code implementations24 Apr 2024 Xinxin Zheng, Feihu Che, Jinyang Wu, Shuai Zhang, Shuai Nie, Kang Liu, JianHua Tao

Large language models (LLMs) suffer from the hallucination problem and face significant challenges when applied to knowledge-intensive tasks.

Hallucination Question Answering +2

Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering

1 code implementation23 Apr 2024 Yao Xu, Shizhu He, Jiabei Chen, ZiHao Wang, Yangqiu Song, Hanghang Tong, Kang Liu, Jun Zhao

To simulate real-world scenarios and evaluate the ability of LLMs to integrate internal and external knowledge, in this paper, we propose leveraging LLMs for QA under Incomplete Knowledge Graph (IKGQA), where the given KG doesn't include all the factual triples involved in each question.

Graph Question Answering Hallucination +2

CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning

no code implementations1 Apr 2024 Xiaoxiao Liang, HaoYu Yang, Kang Liu, Bei Yu, Yuzhe ma

Optical proximity correction (OPC) is a vital step to ensure printability in modern VLSI manufacturing.

reinforcement-learning

Continual Few-shot Event Detection via Hierarchical Augmentation Networks

1 code implementation26 Mar 2024 Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao

The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples.

Event Detection

Imagination Augmented Generation: Learning to Imagine Richer Context for Question Answering over Large Language Models

1 code implementation22 Mar 2024 Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Kang Liu, Shengping Liu, Jun Zhao

Retrieval-Augmented-Generation and Gener-ation-Augmented-Generation have been proposed to enhance the knowledge required for question answering over Large Language Models (LLMs).

Open-Domain Question Answering

GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture

no code implementations18 Mar 2024 Shanglong Yang, Zhipeng Yuan, Shunbao Li, Ruoling Peng, Kang Liu, Po Yang

In the rapidly evolving field of artificial intelligence (AI), the application of large language models (LLMs) in agriculture, particularly in pest management, remains nascent.

Management

ItD: Large Language Models Can Teach Themselves Induction through Deduction

no code implementations9 Mar 2024 Wangtao Sun, Haotian Xu, Xuanqing Yu, Pei Chen, Shizhu He, Jun Zhao, Kang Liu

Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction.

From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs

no code implementations8 Mar 2024 Wangtao Sun, Shizhu He, Jun Zhao, Kang Liu

With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support.

Knowledge Graphs Link Prediction

SimuCourt: Building Judicial Decision-Making Agents with Real-world Judgement Documents

1 code implementation5 Mar 2024 Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, XiaoJian Jiang, Kang Liu, Jun Zhao

In this paper, (1) we introduce SimuCourt, a judicial benchmark that encompasses 420 judgment documents from real-world, spanning the three most common types of judicial cases, and a novel task Judicial Decision-Making to evaluate the judicial analysis and decision-making power of agents.

Decision Making Information Retrieval

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models

no code implementations28 Feb 2024 Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, XiaoJian Jiang, Kang Liu, Jun Zhao

Moreover, we reveal that the pivotal point at which knowledge conflicts emerge in LMs is the integration of inconsistent information flows by memory heads and context heads.

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning

no code implementations28 Feb 2024 Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).

Position

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models

no code implementations22 Feb 2024 Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, XiaoJian Jiang, Jiexin Xu, Qiuxia Li, Jun Zhao

Then, we investigate the behavior and preference of RALMs from the following two perspectives: (1) Conflicts between internal memory and external sources: We find that stronger RALMs emerge with the Dunning-Kruger effect, persistently favoring their faulty internal memory even when correct evidence is provided.

Retrieval

The Da Vinci Code of Large Pre-trained Language Models: Deciphering Degenerate Knowledge Neurons

no code implementations21 Feb 2024 YuHeng Chen, Pengfei Cao, Yubo Chen, Yining Wang, Shengping Liu, Kang Liu, Jun Zhao

This paper provides a comprehensive definition of DKNs that covers both structural and functional aspects, pioneering the study of structures in PLMs' factual knowledge storage units.

BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models

no code implementations18 Feb 2024 Kun Luo, Zheng Liu, Shitao Xiao, Kang Liu

In this work, we proposeExtensible Embedding, which realizes high-quality extension of LLM's context with strong flexibility and cost-effectiveness.

Chunking Language Modelling +1

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing

no code implementations16 Feb 2024 Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge.

knowledge editing

Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering

no code implementations15 Feb 2024 Jiaxiang Liu, Tong Zhou, Yubo Chen, Kang Liu, Jun Zhao

In summary, our results pave the way for enhancing LLMs by incorporating Pseudo- and Multisource-KGs, particularly in the context of open-ended questions.

Graph Generation Knowledge Graphs +1

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

no code implementations29 Dec 2023 Xin Gao, Tianheng Qiu, Xinyu Zhang, Hanlin Bai, Kang Liu, Xuan Huang, Hu Wei, Guoying Zhang, Huaping Liu

Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence.

Computational Efficiency Deblurring

Oasis: Data Curation and Assessment System for Pretraining of Large Language Models

1 code implementation21 Nov 2023 Tong Zhou, Yubo Chen, Pengfei Cao, Kang Liu, Jun Zhao, Shengping Liu

To this end, we present a pretraining corpus curation and assessment platform called Oasis -- a one-stop system for data quality improvement and quantification with user-friendly interactive interfaces.

Language Modelling Large Language Model

Assessing Knowledge Editing in Language Models via Relation Perspective

2 code implementations15 Nov 2023 Yifan Wei, Xiaoyan Yu, Huanhuan Ma, Fangyu Lei, Yixuan Weng, Ran Song, Kang Liu

Knowledge Editing (KE) for modifying factual knowledge in Large Language Models (LLMs) has been receiving increasing attention.

knowledge editing Relation

ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook

1 code implementation13 Nov 2023 Wangtao Sun, Xuanqing Yu, Shizhu He, Jun Zhao, Kang Liu

Black-box Large Language Models (LLMs) have shown great power in solving various tasks and are considered general problem solvers.

S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models

2 code implementations23 Oct 2023 Fangyu Lei, Qian Liu, Yiming Huang, Shizhu He, Jun Zhao, Kang Liu

The rapid development of Large Language Models (LLMs) has led to great strides in model capabilities like long-context understanding and reasoning.

Long-Context Understanding

TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering

no code implementations23 Oct 2023 Fangyu Lei, Tongxu Luo, Pengqi Yang, Weihao Liu, Hanwen Liu, Jiahe Lei, Yiming Huang, Yifan Wei, Shizhu He, Jun Zhao, Kang Liu

Table-based question answering (TableQA) is an important task in natural language processing, which requires comprehending tables and employing various reasoning ways to answer the questions.

Question Answering

Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs

1 code implementation17 Oct 2023 Yao Xu, Shizhu He, Cunguang Wang, Li Cai, Kang Liu, Jun Zhao

However, these methods train KG embeddings and neural set operators concurrently on both simple (one-hop) and complex (multi-hop and logical) queries, which causes performance degradation on simple queries and low training efficiency.

Complex Query Answering

Generative Calibration for In-context Learning

1 code implementation16 Oct 2023 Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jun Zhao, Kang Liu

In this paper, we for the first time theoretically and empirically identify that such a paradox is mainly due to the label shift of the in-context model to the data distribution, in which LLMs shift the label marginal $p(y)$ while having a good label conditional $p(x|y)$.

In-Context Learning text-classification +1

MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models

1 code implementation8 Oct 2023 Yifan Wei, Yisong Su, Huanhuan Ma, Xiaoyan Yu, Fangyu Lei, Yuanzhe Zhang, Jun Zhao, Kang Liu

As a result, it is natural for people to believe that LLMs have also mastered abilities such as time understanding and reasoning.

counterfactual

MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images

no code implementations9 Sep 2023 Weihao Liu, Fangyu Lei, Tongxu Luo, Jiahe Lei, Shizhu He, Jun Zhao, Kang Liu

Most importantly, we propose a Type-specific In-context Learning Strategy for MMHQA, enabling LLMs to leverage their powerful performance in this task.

In-Context Learning Question Answering +1

Unsupervised Text Style Transfer with Deep Generative Models

no code implementations31 Aug 2023 Zhongtao Jiang, Yuanzhe Zhang, Yiming Ju, Kang Liu

We present a general framework for unsupervised text style transfer with deep generative models.

Sentence Style Transfer +2

Interpreting Sentiment Composition with Latent Semantic Tree

1 code implementation31 Aug 2023 Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jiansong Chen, Jun Zhao, Kang Liu

As the key to sentiment analysis, sentiment composition considers the classification of a constituent via classifications of its contained sub-constituents and rules operated on them.

Classification Domain Adaptation +1

ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models

no code implementations28 Aug 2023 Baoli Zhang, Haining Xie, Pengfan Du, JunHao Chen, Pengfei Cao, Yubo Chen, Shengping Liu, Kang Liu, Jun Zhao

To this end, we propose the ZhuJiu benchmark, which has the following strengths: (1) Multi-dimensional ability coverage: We comprehensively evaluate LLMs across 7 ability dimensions covering 51 tasks.

Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons

1 code implementation25 Aug 2023 YuHeng Chen, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact.

Fact Checking knowledge editing

LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models

1 code implementation20 Aug 2023 Yixuan Weng, Zhiqi Wang, Huanxuan Liao, Shizhu He, Shengping Liu, Kang Liu, Jun Zhao

With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to increase.

Multilingual Lexical Simplification via Paraphrase Generation

1 code implementation28 Jul 2023 Kang Liu, Jipeng Qiang, Yun Li, Yunhao Yuan, Yi Zhu, Kaixun Hua

After feeding the input sentence into the encoder of paraphrase modeling, we generate the substitutes based on a novel decoding strategy that concentrates solely on the lexical variations of the complex word.

Lexical Simplification Machine Translation +3

Sentence Simplification Using Paraphrase Corpus for Initialization

no code implementations31 May 2023 Kang Liu, Jipeng Qiang

We train three different neural SS methods with our initialization, which can obtain substantial improvements on the available WikiLarge data compared with themselves without initialization.

Sentence

Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database

no code implementations23 May 2023 Minjun Zhu, Yixuan Weng, Shizhu He, Kang Liu, Jun Zhao

In Textual question answering (TQA) systems, complex questions often require retrieving multiple textual fact chains with multiple reasoning steps.

Question Answering Retrieval

S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering

1 code implementation19 May 2023 Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner.

Question Answering Reading Comprehension

ParaLS: Lexical Substitution via Pretrained Paraphraser

1 code implementation14 May 2023 Jipeng Qiang, Kang Liu, Yun Li, Yunhao Yuan, Yi Zhu

Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence.

Sentence

Large Language Models Need Holistically Thought in Medical Conversational QA

1 code implementation9 May 2023 Yixuan Weng, Bin Li, Fei Xia, Minjun Zhu, Bin Sun, Shizhu He, Kang Liu, Jun Zhao

The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care.

Conversational Question Answering

Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question

1 code implementation5 May 2023 Yifan Wei, Fangyu Lei, Yuanzhe Zhang, Jun Zhao, Kang Liu

Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task.

Decoder Graph Representation Learning +2

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

3 code implementations4 Apr 2023 Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Kang Liu, Jun Zhao

Our work highlights the potential of seamlessly unifying explicit rule learning via CoNNs and implicit pattern learning in LMs, paving the way for true symbolic comprehension capabilities.

Arithmetic Reasoning Language Modelling

Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules

no code implementations7 Jan 2023 Yinyu Lan, Shizhu He, Kang Liu, Jun Zhao

The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs.

Knowledge Graph Embeddings Question Answering

Large Language Models are Better Reasoners with Self-Verification

1 code implementation19 Dec 2022 Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, Jun Zhao

By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score.

Arithmetic Reasoning Common Sense Reasoning +3

Generating Hierarchical Explanations on Text Classification Without Connecting Rules

no code implementations24 Oct 2022 Yiming Ju, Yuanzhe Zhang, Kang Liu, Jun Zhao

The opaqueness of deep NLP models has motivated the development of methods for interpreting how deep models predict.

Clustering text-classification +1

PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction

no code implementations18 Oct 2022 Yuancheng Sun, Yimeng Chen, Weizhi Ma, Wenhao Huang, Kang Liu, ZhiMing Ma, Wei-Ying Ma, Yanyan Lan

In our implementation, we adopt both the state-of-the-art molecule embedding models under the supervised learning paradigm and the pretraining paradigm as the molecule representation module of PEMP, respectively.

Drug Discovery Molecular Property Prediction +2

ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains

no code implementations17 Oct 2022 Minjun Zhu, Yixuan Weng, Shizhu He, Kang Liu, Jun Zhao

Recently, natural language database (NLDB) conducts complex QA in knowledge base with textual evidences rather than structured representations, this task attracts a lot of attention because of the flexibility and richness of textual evidence.

Answer Generation Question Answering +1

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

1 code implementation14 Oct 2022 Kang Liu, Feng Xue, Dan Guo, Le Wu, Shujie Li, Richang Hong

This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences.

Collaborative Filtering Image Classification

Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation

1 code implementation10 Oct 2022 Kang Liu, Feng Xue, Xiangnan He, Dan Guo, Richang Hong

In this work, we propose to model multi-grained popularity features and jointly learn them together with high-order connectivity, to match the differentiation of user preferences exhibited in popularity features.

Collaborative Filtering Recommendation Systems

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

1 code implementation COLING 2022 Fangyu Lei, Shizhu He, Xiang Li, Jun Zhao, Kang Liu

In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challenging problems.

Decoder Models Alignment +1

MALICE: Manipulation Attacks on Learned Image ComprEssion

no code implementations26 May 2022 Kang Liu, Di wu, Yiru Wang, Dan Feng, Benjamin Tan, Siddharth Garg

To characterize the robustness of state-of-the-art learned image compression, we mount white-box and black-box attacks.

Image Compression Image Reconstruction

LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

1 code implementation20 Apr 2022 Fei Xia, Bin Li, Yixuan Weng, Shizhu He, Kang Liu, Bin Sun, Shutao Li, Jun Zhao

The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic.

Conversational Question Answering Dialogue Generation +3

Logic Traps in Evaluating Attribution Scores

no code implementations ACL 2022 Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu, Jun Zhao

Meanwhile, since the reasoning process of deep models is inaccessible, researchers design various evaluation methods to demonstrate their arguments.

Lifelong Intent Detection via Multi-Strategy Rebalancing

no code implementations10 Aug 2021 Qingbin Liu, Xiaoyan Yu, Shizhu He, Kang Liu, Jun Zhao

In this paper, we propose Lifelong Intent Detection (LID), which continually trains an ID model on new data to learn newly emerging intents while avoiding catastrophically forgetting old data.

Intent Detection Knowledge Distillation

A Large-Scale Chinese Multimodal NER Dataset with Speech Clues

1 code implementation ACL 2021 Dianbo Sui, Zhengkun Tian, Yubo Chen, Kang Liu, Jun Zhao

In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents.

named-entity-recognition Named Entity Recognition +1

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

no code implementations ACL 2021 Pengfei Cao, Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao, Yuguang Chen, Weihua Peng

Specifically, to make use of the descriptive knowledge, we devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge.

Descriptive Event Causality Identification

Alignment Rationale for Natural Language Inference

no code implementations ACL 2021 Zhongtao Jiang, Yuanzhe Zhang, Zhao Yang, Jun Zhao, Kang Liu

Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors.

feature selection Natural Language Inference

Document-level Event Extraction via Parallel Prediction Networks

2 code implementations ACL 2021 Hang Yang, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Taifeng Wang

We argue that sentence-level extractors are ill-suited to the DEE task where event arguments always scatter across sentences and multiple events may co-exist in a document.

Decoder Document-level Event Extraction +2

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

no code implementations ACL 2021 Xinyu Zuo, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Weihua Peng, Yuguang Chen

On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework and can interactively adjust the generation process to generate task-related sentences.

Data Augmentation Event Causality Identification

Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion

no code implementations27 May 2021 Yinyu Lan, Shizhu He, Xiangrong Zeng, Shengping Liu, Kang Liu, Jun Zhao

To address the above issues, this paper proposes two novel path-based reasoning methods to solve the sparsity issues of entity and path respectively, which adopts the textual semantic information of entities and paths for MedKGC.

Modeling Spatial Nonstationarity via Deformable Convolutions for Deep Traffic Flow Prediction

no code implementations8 Jan 2021 Wei Zeng, Chengqiao Lin, Kang Liu, Juncong Lin, Anthony K. H. Tung

Furthermore, to better fit with convolutions, we suggest to first aggregate traffic flows according to pre-conceived regions or self-organized regions based on traffic flows, then dispose to sequentially organized raster images for network input.

Traffic Prediction

Graph-Based Knowledge Integration for Question Answering over Dialogue

no code implementations COLING 2020 Jian Liu, Dianbo Sui, Kang Liu, Jun Zhao

Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e. g., relationships between speakers).

Machine Reading Comprehension Question Answering +1

Joint Entity and Relation Extraction with Set Prediction Networks

1 code implementation3 Nov 2020 Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Xiangrong Zeng, Shengping Liu

Compared with cross-entropy loss that highly penalizes small shifts in triple order, the proposed bipartite matching loss is invariant to any permutation of predictions; thus, it can provide the proposed networks with a more accurate training signal by ignoring triple order and focusing on relation types and entities.

Joint Entity and Relation Extraction Relation +1

KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision

no code implementations COLING 2020 Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao

Modern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora.

Data Augmentation

Towards Causal Explanation Detection with Pyramid Salient-Aware Network

no code implementations CCL 2020 Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao

PSAN can assist in causal explanation detection via capturing the salient semantics of discourses contained in their keywords with a bottom graph-based word-level salient network.

Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information

no code implementations22 Sep 2020 Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao

Event coreference resolution(ECR) is an important task in Natural Language Processing (NLP) and nearly all the existing approaches to this task rely on event argument information.

coreference-resolution Event Argument Extraction +1

Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images

no code implementations19 Sep 2020 Kang Liu, Benjamin Tan, Siddharth Garg

Unprecedented data collection and sharing have exacerbated privacy concerns and led to increasing interest in privacy-preserving tools that remove sensitive attributes from images while maintaining useful information for other tasks.

Facial Expression Recognition Facial Expression Recognition (FER) +1

Connecting Embeddings for Knowledge Graph Entity Typing

1 code implementation ACL 2020 Yu Zhao, Anxiang Zhang, Ruobing Xie, Kang Liu, Xiaojie Wang

In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge from KGs.

Entity Typing Knowledge Graph Completion +1

RGCF: Refined Graph Convolution Collaborative Filtering with concise and expressive embedding

1 code implementation7 Jul 2020 Kang Liu, Feng Xue, Richang Hong

In this work, we develop a new GCN-based Collaborative Filtering model, named Refined Graph convolution Collaborative Filtering(RGCF), where the construction of the embeddings of users (items) are delicately redesigned from several aspects during the aggregation on the graph.

Collaborative Filtering

Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks

no code implementations26 Apr 2020 Kang Liu, Benjamin Tan, Gaurav Rajavendra Reddy, Siddharth Garg, Yiorgos Makris, Ramesh Karri

Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection.

Data Augmentation

NNoculation: Catching BadNets in the Wild

1 code implementation19 Feb 2020 Akshaj Kumar Veldanda, Kang Liu, Benjamin Tan, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Brendan Dolan-Gavitt, Siddharth Garg

This paper proposes a novel two-stage defense (NNoculation) against backdoored neural networks (BadNets) that, repairs a BadNet both pre-deployment and online in response to backdoored test inputs encountered in the field.

Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots

no code implementations CONLL 2019 Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao

Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC.

Chatbot Decoder +1

Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking

no code implementations21 Aug 2019 Qingbin Liu, Shizhu He, Kang Liu, Shengping Liu, Jun Zhao

How to integrate the semantic information of pre-defined ontology and dialogue text (heterogeneous texts) to generate unknown values and improve performance becomes a severe challenge.

Decoder Dialogue State Tracking +1

AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing

no code implementations ACL 2019 Xiang Zhang, Shizhu He, Kang Liu, Jun Zhao

To keep the model aware of the underlying grammar in target sequences, many constrained decoders were devised in a multi-stage paradigm, which decode to the sketches or abstract syntax trees first, and then decode to target semantic tokens.

Decoder Semantic Parsing +1

Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation

no code implementations ACL 2019 Cao Liu, Shizhu He, Kang Liu, Jun Zhao

To tackle the above two problems, we present a Vocabulary Pyramid Network (VPN) which is able to incorporate multi-pass encoding and decoding with multi-level vocabularies into response generation.

Clustering Response Generation

Are Adversarial Perturbations a Showstopper for ML-Based CAD? A Case Study on CNN-Based Lithographic Hotspot Detection

no code implementations25 Jun 2019 Kang Liu, Hao-Yu Yang, Yuzhe ma, Benjamin Tan, Bei Yu, Evangeline F. Y. Young, Ramesh Karri, Siddharth Garg

There is substantial interest in the use of machine learning (ML) based techniques throughout the electronic computer-aided design (CAD) flow, particularly those based on deep learning.

Patch alignment manifold matting

no code implementations16 Apr 2019 Xuelong. Li, Kang Liu, Yongsheng Dong, DaCheng Tao

In this paper, a manifold matting framework named Patch Alignment Manifold Matting is proposed for image matting.

Image Matting

Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms

1 code implementation EMNLP 2018 Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, Yantao Jia

Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information.

Event Detection Sentence

Event Detection via Gated Multilingual Attention Mechanism

no code implementations AAAI-18 2018 Jian Liu, Yubo Chen, Kang Liu, Jun Zhao

In specific, to alleviate data scarcity problem, we exploit the consistent information in multilingual data via context attention mechanism.

Event Detection

Pattern-revising Enhanced Simple Question Answering over Knowledge Bases

no code implementations COLING 2018 Yanchao Hao, Hao liu, Shizhu He, Kang Liu, Jun Zhao

Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks.

Entity Linking Fact Selection +2

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

3 code implementations30 May 2018 Kang Liu, Brendan Dolan-Gavitt, Siddharth Garg

Our work provides the first step toward defenses against backdoor attacks in deep neural networks.

IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations

no code implementations IJCNLP 2017 Shangmin Guo, Kang Liu, Shizhu He, Cao Liu, Jun Zhao, Zhuoyu Wei

The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entrance Examination papers and CK12 website1.

Question Answering

Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning

no code implementations ACL 2017 Shizhu He, Cao Liu, Kang Liu, Jun Zhao

Generating answer with natural language sentence is very important in real-world question answering systems, which needs to obtain a right answer as well as a coherent natural response.

Decoder Question Answering +1

Which is the Effective Way for Gaokao: Information Retrieval or Neural Networks?

1 code implementation EACL 2017 Shangmin Guo, Xiangrong Zeng, Shizhu He, Kang Liu, Jun Zhao

As one of the most important test of China, Gaokao is designed to be difficult enough to distinguish the excellent high school students.

Information Retrieval Multiple-choice +4

Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information

no code implementations3 Jun 2016 Yuanzhe Zhang, Kang Liu, Shizhu He, Guoliang Ji, Zhanyi Liu, Hua Wu, Jun Zhao

With the rapid growth of knowledge bases (KBs) on the web, how to take full advantage of them becomes increasingly important.

Question Answering

How to Generate a Good Word Embedding?

2 code implementations20 Jul 2015 Siwei Lai, Kang Liu, Liheng Xu, Jun Zhao

We analyze three critical components of word embedding training: the model, the corpus, and the training parameters.

Word Embeddings