Ellipsis and Coreference Resolution as Question Answering

08/29/2019
by   Rahul Aralikatte, et al.
0

Coreference and many forms of ellipsis are similar to reading comprehension questions, in that in order to resolve these, we need to identify an appropriate text span in the previous discourse. This paper exploits this analogy and proposes to use an architecture developed for machine comprehension for ellipsis and coreference resolution. We present both single-task and joint models and evaluate them across standard benchmarks, outperforming the current state of the art for ellipsis by up to 48.5 coreference by 37.5

READ FULL TEXT
research
09/29/2019

Tag-based Multi-Span Extraction in Reading Comprehension

With models reaching human performance on many popular reading comprehen...
research
08/16/2019

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Machine comprehension of texts longer than a single sentence often requi...
research
04/10/2020

Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure

We present the Molweni dataset, a machine reading comprehension (MRC) da...
research
03/16/2023

Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension

Although the curse of multilinguality significantly restricts the langua...
research
11/12/2017

Fast Reading Comprehension with ConvNets

State-of-the-art deep reading comprehension models are dominated by recu...
research
09/19/2023

Benchmarks for Pirá 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change

Pirá is a reading comprehension dataset focused on the ocean, the Brazil...
research
06/24/2019

EQuANt (Enhanced Question Answer Network)

Machine Reading Comprehension (MRC) is an important topic in the domain ...

Please sign up or login with your details

Forgot password? Click here to reset