Knowledge Base Question Answering via Encoding of Complex Query Graphs
Answering complex questions that involve multiple entities and multiple relations using a standard knowledge base is an open and challenging task. Most existing KBQA approaches focus on simpler questions and do not work very well on complex questions because they were not able to simultaneously represent the question and the corresponding complex query structure. In this work, we encode such complex query structure into a uniform vector representation, and thus successfully capture the interactions between individual semantic components within a complex question. This approach consistently outperforms existing methods on complex questions while staying competitive on simple questions.
Code (1)
Tasks
Knowledge Base Question AnsweringQuestion AnsweringSemantic ParsingSimilar Papers 제목 키워드 기반
Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering
Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Encoding Explanatory Knowledge for Zero-shot Science Question Answering
This paper describes N-XKT (Neural encoding based on eXplanatory Knowledge Transfer), a novel method for the automatic transfer of explanatory knowledge through neural encoding mechanisms. We demonstrate that N-XKT is ab…
Question AnsweringScience Question AnsweringTransfer LearningZero-shot GeneralizationSTL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering
Chart Question Answering (CQA) is the task of answering natural language questions about visualisations in the chart image. Recent solutions, inspired by VQA approaches, rely on image-based attention for question/answeri…
Chart Question AnsweringQuestion AnsweringVisual Question Answering (VQA)A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering
Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever …
DecoderKnowledge DistillationQuestion AnsweringRetrieval+2FusionMind -- 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