DeepAI AI Chat
Log In Sign Up

From Dataset Recycling to Multi-Property Extraction and Beyond

by   Tomasz Dwojak, et al.

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled-a newly developed public dataset and the task of multiple property extraction. It uses the same data as WikiReading but does not inherit its predecessor's identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance.


page 2

page 4

page 6

page 7

page 8

page 9

page 10

page 11


On the Multi-Property Extraction and Beyond

In this paper, we investigate the Dual-source Transformer architecture o...

Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension

Multiple-choice Machine Reading Comprehension (MRC) is an important and ...

From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap

Dialogue state tracking (DST) is at the heart of task-oriented dialogue ...

A New Entity Extraction Method Based on Machine Reading Comprehension

Entity extraction is a key technology for obtaining information from mas...

Detecting Hateful Memes Using a Multimodal Deep Ensemble

While significant progress has been made using machine learning algorith...

MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding

Reading comprehension of legal text can be a particularly challenging ta...