Context-guided Triple Matching for Multiple Choice Question Answering
The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the \emph{triple} of the passage, question and answer. Despite the general research interest in this regard, existing methods decouple the process into several pair-wise or \emph{dual} matching steps, that limited the ability of assessing cases with multiple evidence sentences. To alleviate this issue, this paper introduces a novel \textbf{C}ontext-guided \textbf{T}riple \textbf{M}atching algorithm, which is achieved by integrating a Triple Matching (TM) module and a Contrastive Regularization (CR). The former is designed to enumerate one component from the triple as the background context, and estimate its semantic matching with the other two. Additionally, the contrastive term is further proposed to capture the dissimilarity between the correct answer and distractive ones. We validate the proposed algorithm on several benchmarking MCQA datasets, which exhibits competitive performances against state-of-the-arts.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingMultiple-choiceMultiple Choice Question Answering (MCQA)Question AnsweringSimilar Papers 제목 키워드 기반
Context-guided Triple Matching for Multiple Choice Question Answering
The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer. Despite the g…
BenchmarkingMultiple-choiceMultiple Choice Question Answering (MCQA)Question AnsweringStructured Triplet Learning with POS-tag Guided Attention for Visual Question Answering
Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, ge…
Multiple-choicePOSQuestion AnsweringTAG+3TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve un…
Multi-hop Question AnsweringSemantic SimilarityStructure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task
We explore the use of self-training and acceptability classifiers with pre-trained models for natural language generation in structure-to-text settings using three GEM datasets (E2E, WebNLG-en, Schema-Guided Dialog). Wit…
Text GenerationFull Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphs
Knowledge graphs (KGs) are powerful tools for representing and reasoning over structured information. Their main components include schema, identity, and context. While schema and identity matching are well-established i…
Knowledge Graphs