Lune

EMNLP Findings2022

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

Mingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang, Yanfang Ye

摘要

A common thread of open-domain question answering (QA) models employs a retrieverreader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even state-of-the-art readers fail to capture the complex relationships between entities appearing in questions and retrieved passages, leading to answers that contradict the facts. In light of this, we propose a novel knowledge Graph enhanced passage reader, namely GRAPE , to improve the reader performance for open-domain QA. Specifically, for each pair of question and retrieved passage, we first construct a localized bipartite graph, attributed to entity embeddings extracted from the intermediate layer of the reader model. Then, a graph neural network learns relational knowledge while fusing graph and contextual representations into the hidden states of the reader model. Experiments on three open-domain QA benchmarks show GRAPE can improve the state-of-the-art performance by up to 2.2 exact match score with a negligible overhead increase, with the same retriever and retrieved passages. Our code is publicly available at https://github.com/jumxglhf/GRAPE.

Question: What is the primary language of China? Retrieved Wikipedia passage (ID: 253645): Language of the People's Republic of China and of the Republic of China (Taiwan), and one of the official languages of Singapore. Standard Mandarin Chinese now dominates public life in mainland China. Outside China and Taiwan, the only varieties of Chinese commonly taught in university courses are Mandarin and Cantonese. Answer (SoTA reader): Cantonese Answer (ours): Standard Mandarin Factual Triplet from Wikidata: Question: What does the Missouri river bisect? Retrieved Wikipedia passage (ID: 19591): The Missouri River is the longest river in North America. Rising in the Rocky Mountains of western Montana the Missouri flows east and south for before entering the Mississippi River north of St. Louis, Missouri. The river drains a sparsely populated, … 500,000 square miles, which includes parts of ten U.S. States and two Canadian provinces. Answer (SoTA reader): Missouri Answer (ours): Mississippi River Factual Triplet from Wikidata:

问 Lune

尽管问,回答会引用原文。

Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 引用它的 14 篇顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

引用它的顶会 Paper14

  1. Knowledge Graph Prompting for Multi-Document Question AnsweringYu Wang, Nedim Lipka, Ryan A. Rossi, Alexa F. Siu 等AAAI 2024 · 290 次引用
  2. GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time AugmentationMingxuan Ju, Tong Zhao, Wenhao Yu, Neil Shah 等NeurIPS 2023 · 52 次引用
  3. How Does Message Passing Improve Collaborative Filtering?Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye 等NeurIPS 2024 · 21 次引用
  4. RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM GenerationPengcheng Jiang, Lang Cao, Ruike Zhu, Minhao Jiang 等ICLR 2026 · 20 次引用
  5. Graph is a Substrate Across Data ModalitiesZiming Li, Xiao-Ming Wu, Zehong Wang, Jiazheng Li 等ICML 2026 · 16 次引用

它引用的 Paper11

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 64,255 次引用
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni 等NeurIPS 2020 · 19,162 次引用
  3. Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat 等ICML 2020 · 2,937 次引用
  4. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question AnsweringAkari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher 等ICLR 2020 · 322 次引用
  5. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis 等EMNLP 2020 · 142 次引用

相关 Paper

  1. Open-domain Question Answering via Chain of Reasoning over Heterogeneous KnowledgeKaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg 等EMNLP Findings 2022 · 16 次引用
  2. KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question AnsweringDonghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu 等ACL 2022 · 108 次引用
  3. REANO: Optimising Retrieval-Augmented Reader Models through Knowledge Graph GenerationJinyuan Fang, Zaiqiao Meng, Craig MacDonaldACL 2024 · 7 次引用
  4. R2-D2: A Modular Baseline for Open-Domain Question AnsweringMartin Fajcik, Martin Docekal, Karel Ondrej, Pavel SmrzEMNLP Findings 2021 · 34 次引用
  5. Graph Reasoning for Question Answering with Triplet RetrievalShiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin 等ACL Findings 2023 · 42 次引用
黄昏的海面,两侧是细线勾勒的悬崖