GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

Abstract

Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions involving coreference or ellipsis. Moreover, when reasoning over passage text, most of them simply treat it as a word sequence without exploring rich semantic relationships among words. In this paper, we first propose a simple yet effective graph structure learning technique to dynamically construct a question and conversation history aware context graph at each conversation turn. Then we propose a novel Recurrent Graph Neural Network, and based on that, we introduce a flow mechanism to model the temporal dependencies in a sequence of context graphs. The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks. In addition, visualization experiments show that our proposed model can offer good interpretability for the reasoning process.

7 pages. Accepted by IJCAI 2020. Final Version. The SOLE copyright holder is IJCAI (https://www.ijcai.org), all rights reserved

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Gated Graph Sequence Neural Networks
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Learning Conditioned Graph Structures for Interpretable Visual Question Answering
• Learning Recurrent Span Representations for Extractive Question Answering
• SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
• Get To The Point: Summarization with Pointer-Generator Networks
• Reading Wikipedia to Answer Open-Domain Questions
• Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
• Deep Iterative and Adaptive Learning for Graph Neural Networks
• Technical report on Conversational Question Answering
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
• A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC
• SQL-to-Text Generation with Graph-to-Sequence Model

Cited by in corpus (13)

• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Open-Retrieval Conversational Question Answering
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Deep Iterative and Adaptive Learning for Graph Neural Networks
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• A Survey of Document Grounded Dialogue Systems (DGDS)
• GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search
• Weakly-Supervised Open-Retrieval Conversational Question Answering
• BERT-CoQAC: BERT-based Conversational Question Answering in Context
• Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
• A Smart and Defensive Human-Machine Approach to Code Analysis