Papers by Eva Vanmassenhove

5 papers
Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation (2021.eacl-main)

Copied to clipboard

Challenge: Existing studies have shown that existing models amplify biases observed in training data.
Approach: They propose to use MT and NLP to amplify biases observed in training data to investigate how bias amplification might affect language in a broader sense.
Outcome: The proposed model amplifys biases observed in training data and could lead to an artificially impoverished language, the authors show.
Getting Gender Right in Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: linguistics studies show that the language used by males and females differs in terms of style and syntax.
Approach: They integrate gender information into NMT systems to improve translation quality for multiple language pairs by incorporating gender information to a large dataset.
Outcome: The proposed system significantly improves translation quality for some language pairs.
SuperNMT: Neural Machine Translation with Semantic Supersenses and Syntactic Supertags (P18-3)

Copied to clipboard

Challenge: Neural Machine Translation models have become the state-of-the-art in the field of machine translation.
Approach: They incorporate semantic supersensetags and syntactic supertag features into EN–FR and EN–DE factored NMT systems and show that they improve model training.
Outcome: The proposed model training improves on EN–FR and EN–DE factored NMT systems.
Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs (2026.acl-long)

Copied to clipboard

Challenge: a few million years ago, we lost our tails, and with them, the narratives and identities they carry.
Approach: They argue that multilingual large language models are threatening our linguistic diversity . they argue that models collapse towards what is likely, driven by statistical biases .
Outcome: a new paper shows that models can collapse and lead to loss of linguistic diversity . the authors argue that models are a field that values and protects multilingual diversity - a key challenge for the field .
NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives (2021.emnlp-main)

Copied to clipboard

Challenge: Recent years have seen an increasing need for gender-neutral and inclusive language.
Approach: They propose a rule-based and a neural approach to gender-neutral rewriting for English . they use manually curated synthetic and natural data to train a rewriter .
Outcome: The proposed approach improves on the rule-based approach with word error rates below 0.18% on synthetic, in-domain and out-domain test sets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations