DeepAI AI Chat
Log In Sign Up

A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

by   Minghao Hu, et al.
National University of Defense Technology

Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings. However, the performance of these models degrades significantly when they are applied to more realistic scenarios, such as answers involve various types, multiple text strings are correct answers, or discrete reasoning abilities are required. In this paper, we introduce the Multi-Type Multi-Span Network (MTMSN), a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types (e.g., span, count, negation, and arithmetic expression) with a multi-span extraction method for dynamically producing one or multiple text spans. In addition, an arithmetic expression reranking mechanism is proposed to rank expression candidates for further confirming the prediction. Experiments show that our model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. Source code[<>] will be released to facilitate future work.


page 1

page 2

page 3

page 4


Tag-based Multi-Span Extraction in Reading Comprehension

With models reaching human performance on many popular reading comprehen...

Stochastic Answer Networks for SQuAD 2.0

This paper presents an extension of the Stochastic Answer Network (SAN),...

Multi-span Style Extraction for Generative Reading Comprehension

Generative machine reading comprehension (MRC) requires a model to gener...

Composing Answer from Multi-spans for Reading Comprehension

This paper presents a novel method to generate answers for non-extractio...

Learning Recurrent Span Representations for Extractive Question Answering

The reading comprehension task, that asks questions about a given eviden...

Procedural Reading Comprehension with Attribute-Aware Context Flow

Procedural texts often describe processes (e.g., photosynthesis and cook...

Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension

In this paper, we study machine reading comprehension (MRC) on long text...