DeepAI AI Chat
Log In Sign Up

Entity Tracking Improves Cloze-style Reading Comprehension

by   Luong Hoang, et al.
Harvard University

Reading comprehension tasks test the ability of models to process long-term context and remember salient information. Recent work has shown that relatively simple neural methods such as the Attention Sum-Reader can perform well on these tasks; however, these systems still significantly trail human performance. Analysis suggests that many of the remaining hard instances are related to the inability to track entity-references throughout documents. This work focuses on these hard entity tracking cases with two extensions: (1) additional entity features, and (2) training with a multi-task tracking objective. We show that these simple modifications improve performance both independently and in combination, and we outperform the previous state of the art on the LAMBADA dataset, particularly on difficult entity examples.


page 1

page 2

page 3

page 4


Relation/Entity-Centric Reading Comprehension

Constructing a machine that understands human language is one of the mos...

ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension

Reading comprehension is one of the crucial tasks for furthering researc...

Reading Comprehension Ability Test-A Turing Test for Reading Comprehension

Reading comprehension is an important ability of human intelligence. Lit...

Neural Models for Reasoning over Multiple Mentions using Coreference

Many problems in NLP require aggregating information from multiple menti...

Emergent Predication Structure in Hidden State Vectors of Neural Readers

A significant number of neural architectures for reading comprehension h...

Frustratingly Simple Entity Tracking with Effective Use of Multi-Task Learning Models

We present SET, a frustratingly Simple-yet-effective approach for Entity...

Design and Challenges of Cloze-Style Reading Comprehension Tasks on Multiparty Dialogue

This paper analyzes challenges in cloze-style reading comprehension on m...