paper-with-me

홈 › Papers

Question Directed Graph Attention Network for Numerical Reasoning over Text

2020-09-16 · EMNLP 2020 11 · Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu

Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. The code link is at: https://github.com/emnlp2020qdgat/QDGAT

📄 PDF Abstract BibTeX arXiv:2009.07448

Code (0)

등록된 구현이 없습니다.

Tasks

Graph AttentionMachine Reading ComprehensionNatural Language UnderstandingQuestion AnsweringReading Comprehension

Similar Papers 제목 키워드 기반

GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering

2024-09-04 · Lingling Zhang, Muye Huang, Qianying Wang, Yaxian Wang 외

Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data report generation. CQA is a challenging …

Chart Question AnsweringQuestion Answering

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

2022-09-16 · COLING 2022 10 · Fangyu Lei, Shizhu He, Xiang Li, Jun Zhao 외

In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challe…

DecoderModels AlignmentQuestion Answering

Message Intercommunication for Inductive Relation Reasoning

2023-05-23 · Ke Liang, Lingyuan Meng, Sihang Zhou, Siwei Wang 외

Inductive relation reasoning for knowledge graphs, aiming to infer missing links between brand-new entities, has drawn increasing attention. The models developed based on Graph Inductive Learning, called GraIL-based mode…

Inductive LearningKnowledge GraphsRelation

Measuring Compositional Consistency for Video Question Answering

2022-04-14 · CVPR 2022 1 · Mona Gandhi, Mustafa Omer Gul, Eva Prakash, Madeleine Grunde-McLaughlin 외

Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositional reasoning cause models to mispredict. …

Question AnsweringVideo Question Answering

GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering

2024-12-02 · Qianlong Li, Chen Huang, Shuai Li, Yuanxin Xiang 외

Complex Table Question Answering involves providing accurate answers to specific questions based on intricate tables that exhibit complex layouts and flexible header locations. Despite considerable progress having been m…

Question Answering