PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

2019-04-21 · IJCNLP 2019 11 · Haitian Sun, Tania Bedrax-Weiss, William W. Cohen

We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions that require non-trivial (e.g., `multi-hop'') reasoning. We describe PullNet, an integrated framework for (1) learning what to retrieve (from the KB and/or corpus) and (2) reasoning with this heterogeneous information to find the best answer. PullNet uses an {iterative} process to construct a question-specific subgraph that contains information relevant to the question. In each iteration, a graph convolutional network (graph CNN) is used to identify subgraph nodes that should be expanded using retrieval (or`pull'') operations on the corpus and/or KB. After the subgraph is complete, a similar graph CNN is used to extract the answer from the subgraph. This retrieve-and-reason process allows us to answer multi-hop questions using large KBs and corpora. PullNet is weakly supervised, requiring question-answer pairs but not gold inference paths. Experimentally PullNet improves over the prior state-of-the art, and in the setting where a corpus is used with incomplete KB these improvements are often dramatic. PullNet is also often superior to prior systems in a KB-only setting or a text-only setting.

📄 PDF Abstract BibTeX arXiv:1904.09537

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Domain Question Answering Question Answering Retrieval

Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning

2021-10-25 · Weiqiang Jin, Biao Zhao, Hang Yu, Xi Tao 외

Knowledge Graph Question Answering (KGQA) aims to answer user-questions from a knowledge graph (KG) by identifying the reasoning relations between topic entity and answer. As a complex branch task of KGQA, multi-hop KGQA…

Graph Question Answering Implicit Relations Knowledge Base Question Answering Multi-hop Question Answering+2

Answering Any-hop Open-domain Questions with Iterative Document Reranking

2020-09-16 · Ping Nie, Yuyu Zhang, Arun Ramamurthy, Le Song

Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be a…

Multi-hop Question Answering Natural Questions Open-Domain Question Answering Question Answering+2

Adaptive Information Seeking for Open-Domain Question Answering

2021-09-14 · EMNLP 2021 11 · Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen 외

Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by re…

Open-Domain Question Answering Question Answering Retrieval

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering

2024-08-08 · Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang 외

Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance by gathering additional information, cur…

Multi-hop Question Answering Question Answering RAG Retrieval+1

Multi-Hop Paragraph Retrieval for Open-Domain Question Answering

2019-06-15 · ACL 2019 7 · Yair Feldman, Ran El-Yaniv

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 Answering Question Answering Retrieval Sentence