From Dataset Recycling to Multi-Property Extraction and Beyond

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.

PDF Abstract CONLL 2020 PDF CONLL 2020 Abstract

Datasets


Introduced in the Paper:

WikiReading Recycled

Used in the Paper:

GLUE SQuAD SNLI WikiReading

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods