Is Graph Structure Necessary for Multi-hop Question Answering?
Recently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we investigate whether the graph structure is necessary for multi-hop question answering. Our analysis is centered on HotpotQA. We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for multi-hop question answering. We point out that both graph structure and adjacency matrix are task-related prior knowledge, and graph-attention can be considered as a special case of self-attention. Experiments and visualized analysis demonstrate that graph-attention or the entire graph structure can be replaced by self-attention or Transformers.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph AttentionMulti-hop Question AnsweringQuestion AnsweringSimilar Papers 제목 키워드 기반
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA syste…
Knowledge GraphsMedical Question AnsweringMedQANegation+3BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions
Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedicated to retrieving single modality information, mainly text; while for …
Information RetrievalQuestion AnsweringRAGRetrieval+1Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. W…
Open-Domain Question AnsweringQuestion AnsweringRetrievalSentenceGreaseLM: Graph REASoning Enhanced Language Models
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA syste…
Knowledge GraphsMedical Question AnsweringMedQANegation+3Multimodal Multihop Source Retrieval for Web Question Answering
This work deals with the challenge of learning and reasoning over multi-modal multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to learn multi-source…
Multi-hop Question AnsweringQuestion AnsweringRetrieval