Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution

06/06/2016
by   Ting Liu, et al.
0

Most existing approaches for zero pronoun resolution are heavily relying on annotated data, which is often released by shared task organizers. Therefore, the lack of annotated data becomes a major obstacle in the progress of zero pronoun resolution task. Also, it is expensive to spend manpower on labeling the data for better performance. To alleviate the problem above, in this paper, we propose a simple but novel approach to automatically generate large-scale pseudo training data for zero pronoun resolution. Furthermore, we successfully transfer the cloze-style reading comprehension neural network model into zero pronoun resolution task and propose a two-step training mechanism to overcome the gap between the pseudo training data and the real one. Experimental results show that the proposed approach significantly outperforms the state-of-the-art systems with an absolute improvements of 3.1

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/15/2016

Attention-over-Attention Neural Networks for Reading Comprehension

Cloze-style queries are representative problems in reading comprehension...
research
04/13/2020

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

Dialogue state tracking (DST) is at the heart of task-oriented dialogue ...
research
09/01/2019

Cross-Lingual Machine Reading Comprehension

Though the community has made great progress on Machine Reading Comprehe...
research
04/15/2021

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

The use of pretrained masked language models (MLMs) has drastically impr...
research
08/15/2019

Multi-Task Self-Supervised Learning for Disfluency Detection

Most existing approaches to disfluency detection heavily rely on human-a...
research
10/24/2020

Improved Synthetic Training for Reading Comprehension

Automatically generated synthetic training examples have been shown to i...
research
12/20/2019

SberQuAD – Russian Reading Comprehension Dataset: Description and Analysis

SberQuAD—a large scale analog of Stanford SQuAD in the Russian language—...

Please sign up or login with your details

Forgot password? Click here to reset