paper-with-me

Papers

Interactive Machine Comprehension with Dynamic Knowledge Graphs

2021-08-31 · EMNLP 2021 11 · Xingdi Yuan

Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.

📄 PDF Abstract BibTeX arXiv:2109.00077

Code (1)

xingdi-eric-yuan/imrc_graph_public 공식 구현 pytorch

Tasks

Knowledge GraphsMachine Reading ComprehensionReading Comprehension

Similar Papers 제목 키워드 기반

Machine Reading Comprehension Using Structural Knowledge Graph-aware Network

2019-11-01 · IJCNLP 2019 11 · Delai Qiu, Yuanzhe Zhang, Xinwei Feng, Xiangwen Liao 외

Leveraging external knowledge is an emerging trend in machine comprehension task. Previous work usually utilizes knowledge graphs such as ConceptNet as external knowledge, and extracts triples from them to enhance the in…

Knowledge GraphsMachine Reading ComprehensionReading Comprehension

Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

2018-10-12 · ICLR 2019 5 · Rajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan, Adam Trischler 외

We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text. It builds these graphs recurrently for each step of the described procedure, and uses them to track the evolving st…

Knowledge GraphsMachine Reading ComprehensionProcedural Text UnderstandingQuestion Answering+1

Interactive Language Learning by Question Answering

2019-08-28 · IJCNLP 2019 11 · Xingdi Yuan, Marc-Alexandre Cote, Jie Fu, Zhouhan Lin 외

Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present m…

Deep Reinforcement LearningMachine Reading ComprehensionQuestion AnsweringReading Comprehension+1

Q. Can Knowledge Graphs be used to Answer Boolean Questions? A. It’s complicated!

2020-11-01 · EMNLP (insights) 2020 11 · Daria Dzendzik, Carl Vogel, Jennifer Foster

In this paper we explore the problem of machine reading comprehension, focusing on the BoolQ dataset of Yes/No questions. We carry out an error analysis of a BERT-based machine reading comprehension model on this dataset…

Entity LinkingGraph Neural NetworkKnowledge GraphsMachine Reading Comprehension+1

Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model

2021-07-04 · Zhiqi Huang, Fenglin Liu, Xian Wu, Shen Ge 외

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs …

Knowledge DistillationMachine Reading ComprehensionReading Comprehension