WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation

11/13/2022
by   Binbin Xie, et al.
0

Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm (Ye et al., 2021) generates keyphrases as a set and has achieved competitive performance. Nevertheless, we observe serious calibration errors outputted by ONE2SET, especially in the over-estimation of ∅ token (means "no corresponding keyphrase"). In this paper, we deeply analyze this limitation and identify two main reasons behind: 1) the parallel generation has to introduce excessive ∅ as padding tokens into training instances; and 2) the training mechanism assigning target to each slot is unstable and further aggravates the ∅ token over-estimation. To make the model well-calibrated, we propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism. The former dynamically penalizes the over-estimated slots for different instances thus smoothing the uneven training distribution. The latter refines the original inappropriate assignment and reduces the supervisory signals of over-estimated slots. Experimental results on commonly-used datasets demonstrate the effectiveness and generality of our proposed paradigm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/28/2022

Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention

Vision transformer has emerged as a new paradigm in computer vision, sho...
research
05/26/2021

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

Recently, token-level adaptive training has achieved promising improveme...
research
07/21/2020

Neural Machine Translation with Error Correction

Neural machine translation (NMT) generates the next target token given a...
research
05/24/2021

One2Set: Generating Diverse Keyphrases as a Set

Recently, the sequence-to-sequence models have made remarkable progress ...
research
04/10/2023

ViT-Calibrator: Decision Stream Calibration for Vision Transformer

A surge of interest has emerged in utilizing Transformers in diverse vis...
research
03/06/2022

Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

Token-level adaptive training approaches can alleviate the token imbalan...

Please sign up or login with your details

Forgot password? Click here to reset