Related papers: Mitigating Gender Bias in Machine Translation with…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…

Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target…

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work…

A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuously generated.…

There are concerns that neural language models may preserve some of the stereotypes of the underlying societies that generate the large corpora needed to train these models. For example, gender bias is a significant problem when generating…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

This paper aims at identifying the information flow in state-of-the-art machine translation systems, taking as example the transfer of gender when translating from French into English. Using a controlled set of examples, we experiment…

Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. However, the general full-sentence translation test set is…

A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need for a prompt-style dataset to trigger specific behaviors of language models. In this paper, we address…

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this,…

Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural)…

Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation…

Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation…

One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models…

Gender biases in language generation systems are challenging to mitigate. One possible source for these biases is gender representation disparities in the training and evaluation data. Despite recent progress in documenting this problem and…

Statistical machine translation (SMT) systems perform poorly when it is applied to new target domains. Our goal is to explore domain adaptation approaches and techniques for improving the translation quality of domain-specific SMT systems.…

The field of machine translation has progressed tremendously in recent years. Even though the translation quality has improved significantly, current systems are still unable to produce uniformly acceptable machine translations for the…