Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mąka, Paweł, Semerci, Yusuf Can, Scholtes, Jan, Spanakis, Gerasimos
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929632484261888
author Mąka, Paweł
Semerci, Yusuf Can
Scholtes, Jan
Spanakis, Gerasimos
author_facet Mąka, Paweł
Semerci, Yusuf Can
Scholtes, Jan
Spanakis, Gerasimos
contents In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions. We analyze their influence by both observing and modifying the attention scores corresponding to the plausible relations that could impact a pronoun prediction. Our findings reveal that while some heads do attend the relations of interest, not all of them influence the models' ability to disambiguate pronouns. We show that certain heads are underutilized by the models, suggesting that model performance could be improved if only the heads would attend one of the relations more strongly. Furthermore, we fine-tune the most promising heads and observe the increase in pronoun disambiguation accuracy of up to 5 percentage points which demonstrates that the improvements in performance can be solidified into the models' parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models
Mąka, Paweł
Semerci, Yusuf Can
Scholtes, Jan
Spanakis, Gerasimos
Computation and Language
Artificial Intelligence
Machine Learning
In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions. We analyze their influence by both observing and modifying the attention scores corresponding to the plausible relations that could impact a pronoun prediction. Our findings reveal that while some heads do attend the relations of interest, not all of them influence the models' ability to disambiguate pronouns. We show that certain heads are underutilized by the models, suggesting that model performance could be improved if only the heads would attend one of the relations more strongly. Furthermore, we fine-tune the most promising heads and observe the increase in pronoun disambiguation accuracy of up to 5 percentage points which demonstrates that the improvements in performance can be solidified into the models' parameters.
title Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.11187