paper-with-me

Papers

Question-Answer Sentence Graph for Joint Modeling Answer Selection

2022-02-16 · Roshni G. Iyer, Thuy Vu, Alessandro Moschitti, Yizhou Sun

This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems. During offline learning, our model constructs a small-scale relevant training graph per question in an unsupervised manner, and integrates with Graph Neural Networks. Graph nodes are question sentence to answer sentence pairs. We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs, and use thresholding on relevance scores for creating graph edges. Online inference is then performed to solve the AS2 task on unseen queries. Experiments on two well-known academic benchmarks and a real-world dataset show that our approach consistently outperforms SOTA QA baseline models.

📄 PDF Abstract BibTeX arXiv:2203.03549

Code (0)

등록된 구현이 없습니다.

Tasks

Answer SelectionQuestion AnsweringRetrievalSentence

Similar Papers 제목 키워드 기반

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering

2026-01-06 · Junli Liang, Pengfei Zhou, Wangqiu Zhou, Wenjie Qing 외 arxiv

Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combin…

Multi-hop Question AnsweringAnswer Generation

Joint Models for Answer Verification in Question Answering Systems

2021-07-09 · ACL 2021 5 · Zeyu Zhang, Thuy Vu, Alessandro Moschitti

This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. …

Question AnsweringRetrievalSentence

Aspect-based Sentiment Analysis in Question Answering Forums

2021-11-01 · Findings (EMNLP) 2021 11 · Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing 외

Aspect-based sentiment analysis (ABSA) typically focuses on extracting aspects and predicting their sentiments on individual sentences such as customer reviews. Recently, another kind of opinion sharing platform, namely …

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Question AnsweringSentence+1

SRLGRN: Semantic Role Labeling Graph Reasoning Network

2020-10-07 · EMNLP 2020 11 · Chen Zheng, Parisa Kordjamshidi

This work deals with the challenge of learning and reasoning over multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasonin…

Multi-hop Question AnsweringQuestion AnsweringSemantic Role LabelingSentence

Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension

2020-05-12 · ACL 2020 6 · Bo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan 외

Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). D…

Graph AttentionMachine Reading ComprehensionNatural QuestionsReading Comprehension