SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.05514 · 2019

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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\footnote{\url{https://github.com/huminghao16/MTMSN}} is released to facilitate future work.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.05514")
get_code_for_paper("1908.05514")
have("1908.05514")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.05514.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.05514.svg)](https://syntology.ai/paper/1908.05514)

Connect an agent — have() is free.