Stochastic Answer Networks for SQuAD 2.0
arXiv:1809.09194
Abstract
This paper presents an extension of the Stochastic Answer Network (SAN), one of the state-of-the-art machine reading comprehension models, to be able to judge whether a question is unanswerable or not. The extended SAN contains two components: a span detector and a binary classifier for judging whether the question is unanswerable, and both components are jointly optimized. Experiments show that SAN achieves the results competitive to the state-of-the-art on Stanford Question Answering Dataset (SQuAD) 2.0. To facilitate the research on this field, we release our code: https://github.com/kevinduh/san_mrc.
6 pages, 2 figures and 2 tables
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Bidirectional Attention Flow for Machine Comprehension
- A Structured Self-attentive Sentence Embedding
- Machine Comprehension Using Match-LSTM and Answer Pointer
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Stochastic Answer Networks for Natural Language Inference
- Read + Verify: Machine Reading Comprehension with Unanswerable Questions
- Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
Cited by in corpus (6)
- SG-Net: Syntax-Guided Machine Reading Comprehension
- Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
- Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring
- Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension
- Relation Module for Non-answerable Prediction on Question Answering
- Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking