Reference-less Analysis of Context Specificity in Translation with Personalised Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vincent, Sebastian, Dowek, Alice, Sumner, Rowanne, Blundell, Charlotte, Preston, Emily, Bayliss, Chris, Oakley, Chris, Scarton, Carolina
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910353674207232
author Vincent, Sebastian
Dowek, Alice
Sumner, Rowanne
Blundell, Charlotte
Preston, Emily
Bayliss, Chris
Oakley, Chris
Scarton, Carolina
author_facet Vincent, Sebastian
Dowek, Alice
Sumner, Rowanne
Blundell, Charlotte
Preston, Emily
Bayliss, Chris
Oakley, Chris
Scarton, Carolina
contents Sensitising language models (LMs) to external context helps them to more effectively capture the speaking patterns of individuals with specific characteristics or in particular environments. This work investigates to what extent rich character and film annotations can be leveraged to personalise LMs in a scalable manner. We then explore the use of such models in evaluating context specificity in machine translation. We build LMs which leverage rich contextual information to reduce perplexity by up to 6.5% compared to a non-contextual model, and generalise well to a scenario with no speaker-specific data, relying on combinations of demographic characteristics expressed via metadata. Our findings are consistent across two corpora, one of which (Cornell-rich) is also a contribution of this paper. We then use our personalised LMs to measure the co-occurrence of extra-textual context and translation hypotheses in a machine translation setting. Our results suggest that the degree to which professional translations in our domain are context-specific can be preserved to a better extent by a contextual machine translation model than a non-contextual model, which is also reflected in the contextual model's superior reference-based scores.
format Preprint
id arxiv_https___arxiv_org_abs_2303_16618
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Reference-less Analysis of Context Specificity in Translation with Personalised Language Models
Vincent, Sebastian
Dowek, Alice
Sumner, Rowanne
Blundell, Charlotte
Preston, Emily
Bayliss, Chris
Oakley, Chris
Scarton, Carolina
Computation and Language
Artificial Intelligence
Machine Learning
Sensitising language models (LMs) to external context helps them to more effectively capture the speaking patterns of individuals with specific characteristics or in particular environments. This work investigates to what extent rich character and film annotations can be leveraged to personalise LMs in a scalable manner. We then explore the use of such models in evaluating context specificity in machine translation. We build LMs which leverage rich contextual information to reduce perplexity by up to 6.5% compared to a non-contextual model, and generalise well to a scenario with no speaker-specific data, relying on combinations of demographic characteristics expressed via metadata. Our findings are consistent across two corpora, one of which (Cornell-rich) is also a contribution of this paper. We then use our personalised LMs to measure the co-occurrence of extra-textual context and translation hypotheses in a machine translation setting. Our results suggest that the degree to which professional translations in our domain are context-specific can be preserved to a better extent by a contextual machine translation model than a non-contextual model, which is also reflected in the contextual model's superior reference-based scores.
title Reference-less Analysis of Context Specificity in Translation with Personalised Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2303.16618