Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities. To explicitly capture the entities' relatedness, KGNN utilizes relational facts in knowledge graph to build the entity graph. The experimental results show that KGNN outperforms in both distractor and full wiki settings than baselines methods on HotpotQA dataset. And our further analysis illustrates KGNN is effective and robust with more retrieved paragraphs.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkOpen-Domain Question AnsweringQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-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 AnsweringRetrievalSentenceTree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
Multi-hop question answering is a knowledge-intensive complex problem. Large Language Models (LLMs) use their Chain of Thoughts (CoT) capability to reason complex problems step by step, and retrieval-augmentation can eff…
DiversityMulti-hop Question AnsweringQuestion AnsweringResponse Generation+1GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning
Video Paragraph Captioning (VPC) aims to generate paragraph captions that summarises key events within a video. Despite recent advancements, challenges persist, notably in effectively utilising multimodal signals inheren…
Caption GenerationDecoderExplicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering
Current graph-neural-network-based (GNN-based) approaches to multi-hop questions integrate clues from scattered paragraphs in an entity graph, achieving implicit reasoning by synchronous update of graph node representati…
Graph Neural NetworkMulti-hop Question AnsweringQuestion AnsweringSentenceTowards Interpretable Reasoning over Paragraph Effects in Situation
We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing…