中文
相关论文

相关论文: Multi-hop Inference for Sentence-level TextGraphs:…

200 篇论文

Knowledge retrieval and reasoning are two key stages in multi-hop question answering (QA) at web scale. Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning…

计算与语言 · 计算机科学 2021-05-26 Weiwen Xu , Huihui Zhang , Deng Cai , Wai Lam

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…

计算与语言 · 计算机科学 2018-06-12 Johannes Welbl , Pontus Stenetorp , Sebastian Riedel

In Textual question answering (TQA) systems, complex questions often require retrieving multiple textual fact chains with multiple reasoning steps. While existing benchmarks are limited to single-chain or single-hop retrieval scenarios. In…

计算与语言 · 计算机科学 2023-05-24 Minjun Zhu , Yixuan Weng , Shizhu He , Kang Liu , Jun Zhao

This work deals with the challenge of learning and reasoning over multi-modal multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to learn multi-source reasoning paths and…

计算与语言 · 计算机科学 2025-01-09 Navya Yarrabelly , Saloni Mittal

Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional…

计算与语言 · 计算机科学 2021-02-10 Dan Su , Yan Xu , Wenliang Dai , Ziwei Ji , Tiezheng Yu , Pascale Fung

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources…

信息检索 · 计算机科学 2020-12-22 Ruben Cartuyvels , Graham Spinks , Marie-Francine Moens

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the input to the…

计算与语言 · 计算机科学 2020-09-17 Xiyao Ma , Qile Zhu , Yanlin Zhou , Xiaolin Li , Dapeng Wu

We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification. It challenges models to extract facts from several Wikipedia articles that are relevant to a claim and classify whether the claim is…

计算与语言 · 计算机科学 2020-11-17 Yichen Jiang , Shikha Bordia , Zheng Zhong , Charles Dognin , Maneesh Singh , Mohit Bansal

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of…

计算与语言 · 计算机科学 2020-10-07 Yuwei Fang , Siqi Sun , Zhe Gan , Rohit Pillai , Shuohang Wang , Jingjing Liu

Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically requires multi-hop…

人工智能 · 计算机科学 2019-10-02 Mokanarangan Thayaparan , Marco Valentino , Viktor Schlegel , Andre Freitas

Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number…

计算与语言 · 计算机科学 2021-09-09 Peter Jansen , Kelly Smith , Dan Moreno , Huitzilin Ortiz

Developing methods of automated inference that are able to provide users with compelling human-readable justifications for why the answer to a question is correct is critical for domains such as science and medicine, where user trust and…

计算与语言 · 计算机科学 2018-02-12 Peter A. Jansen , Elizabeth Wainwright , Steven Marmorstein , Clayton T. Morrison

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition(QASC), that requires retrieving facts from a large…

计算与语言 · 计算机科学 2020-02-06 Tushar Khot , Peter Clark , Michal Guerquin , Peter Jansen , Ashish Sabharwal

Multi-hop question answering requires models to gather information from different parts of a text to answer a question. Most current approaches learn to address this task in an end-to-end way with neural networks, without maintaining an…

计算与语言 · 计算机科学 2021-06-08 Jifan Chen , Shih-ting Lin , Greg Durrett

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to…

计算与语言 · 计算机科学 2019-06-04 Lisa Bauer , Yicheng Wang , Mohit Bansal

Multi-hop reading comprehension across multiple documents attracts much attention recently. In this paper, we propose a novel approach to tackle this multi-hop reading comprehension problem. Inspired by human reasoning processing, we…

计算与语言 · 计算机科学 2020-06-15 Zeyun Tang , Yongliang Shen , Xinyin Ma , Wei Xu , Jiale Yu , Weiming Lu

Systems for language understanding have become remarkably strong at overcoming linguistic imperfections in tasks involving phrase matching or simple reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps…

计算与语言 · 计算机科学 2020-05-04 Daniel Khashabi , Erfan Sadeqi Azer , Tushar Khot , Ashish Sabharwal , Dan Roth

Language-enabled AI systems can answer complex, multi-hop questions to high accuracy, but supporting answers with evidence is a more challenging task which is important for the transparency and trustworthiness to users. Prior work in this…

计算与语言 · 计算机科学 2022-01-11 Shane Storks , Qiaozi Gao , Aishwarya Reganti , Govind Thattai

We propose a novel, path-based reasoning approach for the multi-hop reading comprehension task where a system needs to combine facts from multiple passages to answer a question. Although inspired by multi-hop reasoning over knowledge…

计算与语言 · 计算机科学 2019-07-10 Souvik Kundu , Tushar Khot , Ashish Sabharwal , Peter Clark

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of…

计算与语言 · 计算机科学 2021-06-02 Wojciech Ostrowski , Arnav Arora , Pepa Atanasova , Isabelle Augenstein
‹ 上一页 1 2 3 10 下一页 ›