Question Directed Graph Attention Network for Numerical Reasoning over Text

By Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu. 2020

69 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Tat-seng Chua
3. Fuli Feng
4. Xiang Wang
5. Jonathan Berant
6. Hanwang Zhang
7. Jian-Guang Lou
8. Alon Talmor

In Natural Language Processing

1. Jonathan Berant
2. Alon Talmor
3. Weizhu Chen
4. Jian-Guang Lou
5. Ori Yoran
6. Zeqi Lin
7. Qiang Fu
8. Qian Liu

Citations in the corpus

• Reasoning Like Program Executors (2022, methodology): “With a hybrid architecture, i.e., symbolic reasoners attached to LMs, neural-symbolic reasoning shines in a variety of reasoning tasks (Chen et al., 2020c; Tu et al., 2020; Wolfson et al., 2020).”
• Teaching Autoregressive Language Models Complex Tasks By Demonstration (2021, background): “…or reasoning tasks expressed in natural language by including components explicitly designed to execute numerical or logical operations [27]–[32]; this is not the approach we take here, but presumably could be combined with more dataset-focused approaches to achieve improved performance on…”
• PaLM 2 Technical Report (2023, neutral): “, 2023), dQDGAT (Chen et al., 2020), eDeBERTaV3-large+KEAR (Xu et al.”
• Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills (2021, methodology): “models has taken two flavors: (a) adding specialized components for specific skills, like numerical and temporal reasoning (Ran et al., 2019; Gupta et al., 2020a; Khot et al., 2021; Chen et al., 2020a), or (b) generating synthetic examples at scale, for example, by using grammars or templates (Rozen”
• Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning (2022, methodology): “As to extending the context, several studies try to enable the NDR model to operate on context with semi-structured tabular data and hybrid data (Chen et al., 2020c; Herzig et al., 2020; Chen et al., 2021).”
• TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance (2021, methodology): “The HyBrider is the worst among all baseline models, because it is designed for Hy-bridQA (Chen et al., 2020b) which does not focus on the comprehensive interdependence of table and paragraphs, nor numerical reasoning.”
• Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021, background): “Despite the great success in extractive MRC (Wang et al., 2018; Chen et al., 2020), in real-world applications, correct answers may span different Question does gameplay programmer need math skill”