Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base
arXiv:1910.05069
Abstract
We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.
Accepted to appear at EMNLP-IJCNLP 2019
References in corpus (11)
- Distributed Representations of Words and Phrases and their Compositionality
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Gaussian Error Linear Units (GELUs)
- Bidirectional Attention Flow for Machine Comprehension
- End-To-End Memory Networks
- A Syntactic Neural Model for General-Purpose Code Generation
- Latent Predictor Networks for Code Generation
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- Abstract Syntax Networks for Code Generation and Semantic Parsing
- Simpler Context-Dependent Logical Forms via Model Projections
- Learning Structured Natural Language Representations for Semantic Parsing