Papers by Loic Barrault

9 papers
Evaluation of Lifelong Learning Systems (2020.lrec-1)

Copied to clipboard

Challenge: Current intelligent systems need the expensive support of machine learning experts to sustain their performance level when used on a daily basis.
Approach: They propose a generic evaluation methodology for lifelong learning systems . they use "initialisation data" to refer to the set of training, development and test data together .
Outcome: The proposed evaluation method is based on the evaluation of human-assisted learning outside the context of lifelong learning.
Aligning Speech Segments Beyond Pure Semantics (2024.findings-acl)

Copied to clipboard

Challenge: Existing speech-to-speech parallel data is scarce and expensive to create from scratch.
Approach: They propose an algorithm which automatically aligns pairs of speech segments aligned in meaning and expressivity.
Outcome: The proposed algorithm outperforms semantic-focused approaches on content translation quality.
Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better (2023.acl-long)

Copied to clipboard

Challenge: a recent study shows that without artificially encouraging models to hallucinate, existing methods fall short . hallucinations are cases when the model generates output that is partially or fully unrelated to the source sentence.
Approach: They propose a method that evaluates the percentage of the source contribution to a generated translation.
Outcome: The proposed method improves detection accuracy for the most severe hallucinations by a factor of 2.
MEXMA: Token-level objectives improve sentence representations (2025.acl-long)

Copied to clipboard

Challenge: Current approaches to cross-lingual sentence encoders use sentence-level objectives only.
Approach: They propose a novel approach that integrates both sentence-level and token-level objectives.
Outcome: The proposed approach outperforms existing CLSEs on bitext mining tasks and downstream tasks.
On the Importance of Effectively Adapting Pretrained Language Models for Active Learning (2022.acl-short)

Copied to clipboard

Challenge: Recent active learning approaches in NLP use off-the-shelf pretrained language models (LMs) . a poor training strategy can be catastrophic for AL, authors argue .
Approach: They propose to first adapt the pretrained LM to the target task and then use it for AL.
Outcome: The proposed approach provides substantial data efficiency improvements compared to the standard fine-tuning approach.
Mixture of Languages: Improved Multilingual Encoders Through Language Grouping (2025.emnlp-main)

Copied to clipboard

Challenge: Recent work in this field relies on training transformer encoders on a large amount of multilingual data, with all parameters shared across all languages.
Approach: They propose a mixture of languages strategy to pretrain largely multilingual encoders using masked language modeling.
Outcome: The proposed architecture outperforms a dense counterpart, MoE models and public multilingual encoders on downstream tasks while minimizing interference.
Metaphor Detection with Effective Context Denoising (2023.eacl-main)

Copied to clipboard

Challenge: Existing models focus on semantically relevant information and provide a target-oriented parse tree structure for metaphor detection.
Approach: They propose a new model which introduces a target-oriented parse tree structure for metaphor detection.
Outcome: The proposed model achieves state-of-the-art on several main metaphor datasets and compares with other methods.
FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning (2023.eacl-main)

Copied to clipboard

Challenge: Existing models for concept-level metaphor detection lack explicit knowledge of FrameNet . Metaphor detection is a pervasive linguistic device that is used in cognitive and communicative functions of language.
Approach: They propose a BERT-based model that explicitly learns FrameNet Embeddings for metaphor detection.
Outcome: The proposed model is more explainable and interpretable than existing models.
HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Previously available quality assessments do not distinguish between hallucinations and omissions.
Approach: They propose to annotate hallucinations and omissions in machine translation using a single language pair.
Outcome: The proposed dataset covers 18 translation directions with varying resource levels and scripts.

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