QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. In this work, we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph neural networks. We evaluate our model on QA benchmarks in the commonsense (CommonsenseQA, OpenBookQA) and biomedical (MedQA-USMLE) domains. QA-GNN outperforms existing LM and LM+KG models, and exhibits capabilities to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.
Code (6)
Tasks
Common Sense ReasoningGraph Representation LearningKnowledge GraphsLanguage ModellingMedQAMulti-hop Question AnsweringNegationQuestion AnsweringRiddle SenseMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Language Model-Guided Knowledge Subgraphs for Question Answering
Knowledge graphs for question answering can provide subgraphs based on different combinations of questions and answers for multiple reasoning chains, in which humans often find the answer for a question. In this p…
Knowledge GraphsLanguage ModelingLanguage Modellingmodel+1Graph Reasoning for Question Answering with Triplet Retrieval
Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph n…
Knowledge GraphsQuestion AnsweringRetrievalTripletTriggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks
Despite readily memorizing world knowledge about entities, pre-trained language models (LMs) struggle to compose together two or more facts to perform multi-hop reasoning in question-answering tasks. In this work, we pro…
Knowledge GraphsQuestion AnsweringWorld KnowledgeScalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
Existing work on augmenting question answering (QA) models with external knowledge (e.g., knowledge graphs) either struggle to model multi-hop relations efficiently, or lack transparency into the model's prediction ratio…
Knowledge GraphsQuestion AnsweringRelational ReasoningRelation NetworkFusionMind -- Improving question and answering with external context fusion
Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compared LMs (fine-tuned for the task) with t…
Knowledge GraphsMultiple-choiceQuestion Answering