Vassilina Nikoulina


2022

pdf bib
Zero-Shot Aspect-Based Scientific Document Summarization using Self-Supervised Pre-training
Amir Soleimani | Vassilina Nikoulina | Benoit Favre | Salah Ait Mokhtar
Proceedings of the 21st Workshop on Biomedical Language Processing

We study the zero-shot setting for the aspect-based scientific document summarization task. Summarizing scientific documents with respect to an aspect can remarkably improve document assistance systems and readers experience. However, existing large-scale datasets contain a limited variety of aspects, causing summarization models to over-fit to a small set of aspects and a specific domain. We establish baseline results in zero-shot performance (over unseen aspects and the presence of domain shift), paraphrasing, leave-one-out, and limited supervised samples experimental setups. We propose a self-supervised pre-training approach to enhance the zero-shot performance. We leverage the PubMed structured abstracts to create a biomedical aspect-based summarization dataset. Experimental results on the PubMed and FacetSum aspect-based datasets show promising performance when the model is pre-trained using unlabelled in-domain data.

pdf bib
DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation
Cheonbok Park | Hantae Kim | Ioan Calapodescu | Hyun Chang Cho | Vassilina Nikoulina
Findings of the Association for Computational Linguistics: ACL 2022

Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel samples it would require. It is however a desirable functionality that could help MT practitioners to make an informed decision before investing resources in dataset creation. We propose a Domain adaptation Learning Curve prediction (DaLC) model that predicts prospective DA performance based on in-domain monolingual samples in the source language. Our model relies on the NMT encoder representations combined with various instance and corpus-level features. We demonstrate that instance-level is better able to distinguish between different domains compared to corpus-level frameworks proposed in previous studies Finally, we perform in-depth analyses of the results highlighting the limitations of our approach, and provide directions for future research.

pdf bib
Speeding Up Entmax
Maxat Tezekbayev | Vassilina Nikoulina | Matthias Gallé | Zhenisbek Assylbekov
Findings of the Association for Computational Linguistics: NAACL 2022

Softmax is the de facto standard for normalizing logits in modern neural networks for language processing. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being selected at each generation step, leading to a variety of reported problems in text generation. đ›Œ-entmax of Peters et al. (2019) solves this problem, but is unfortunately slower than softmax. In this paper, we propose an alternative to đ›Œ-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task.

2021

pdf bib
Visualizing Cross‐Lingual Discourse Relations in Multilingual TED Corpora
Zae Myung Kim | Vassilina Nikoulina | Dongyeop Kang | Didier Schwab | Laurent Besacier
Proceedings of the 2nd Workshop on Computational Approaches to Discourse

This paper presents an interactive data dashboard that provides users with an overview of the preservation of discourse relations among 28 language pairs. We display a graph network depicting the cross-lingual discourse relations between a pair of languages for multilingual TED talks and provide a search function to look for sentences with specific keywords or relation types, facilitating ease of analysis on the cross-lingual discourse relations.

pdf bib
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
Asa Cooper Stickland | Alexandre Berard | Vassilina Nikoulina
Proceedings of the Sixth Conference on Machine Translation

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a small set of parameters for each new setting (language pair or domain). In this work we study the compositionality of language and domain adapters in the context of Machine Translation. We aim to study, 1) parameter-efficient adaptation to multiple domains and languages simultaneously (full-resource scenario) and 2) cross-lingual transfer in domains where parallel data is unavailable for certain language pairs (partial-resource scenario). We find that in the partial resource scenario a naive combination of domain-specific and language-specific adapters often results in ‘catastrophic forgetting’ of the missing languages. We study other ways to combine the adapters to alleviate this issue and maximize cross-lingual transfer. With our best adapter combinations, we obtain improvements of 3-4 BLEU on average for source languages that do not have in-domain data. For target languages without in-domain data, we achieve a similar improvement by combining adapters with back-translation. Supplementary material is available at https://tinyurl.com/r66stbxj.

pdf bib
Findings of the WMT Shared Task on Machine Translation Using Terminologies
Md Mahfuz Ibn Alam | Ivana Kvapilíkovå | Antonios Anastasopoulos | Laurent Besacier | Georgiana Dinu | Marcello Federico | Matthias Gallé | Kweonwoo Jung | Philipp Koehn | Vassilina Nikoulina
Proceedings of the Sixth Conference on Machine Translation

Language domains that require very careful use of terminology are abundant and reflect a significant part of the translation industry. In this work we introduce a benchmark for evaluating the quality and consistency of terminology translation, focusing on the medical (and COVID-19 specifically) domain for five language pairs: English to French, Chinese, Russian, and Korean, as well as Czech to German. We report the descriptions and results of the participating systems, commenting on the need for further research efforts towards both more adequate handling of terminologies as well as towards a proper formulation and evaluation of the task.

pdf bib
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
Zae Myung Kim | Laurent Besacier | Vassilina Nikoulina | Didier Schwab
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Efficient Inference for Multilingual Neural Machine Translation
Alexandre Berard | Dain Lee | Stephane Clinchant | Kweonwoo Jung | Vassilina Nikoulina
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at inference without degrading its quality. We experiment with several “light decoder” architectures in two 20-language multi-parallel settings: small-scale on TED Talks and large-scale on ParaCrawl. Our experiments demonstrate that combining a shallow decoder with vocabulary filtering leads to almost 2 times faster inference with no loss in translation quality. We validate our findings with BLEU and chrF (on 380 language pairs), robustness evaluation and human evaluation.

2020

pdf bib
Naver Labs Europe’s Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020
Alexandre Berard | Ioan Calapodescu | Vassilina Nikoulina | Jerin Philip
Proceedings of the Fifth Conference on Machine Translation

This paper describes Naver Labs Europe’s participation in the Robustness, Chat, and Biomedical Translation tasks at WMT 2020. We propose a bidirectional German-English model that is multi-domain, robust to noise, and which can translate entire documents (or bilingual dialogues) at once. We use the same ensemble of such models as our primary submission to all three tasks and achieve competitive results. We also experiment with language model pre-training techniques and evaluate their impact on robustness to noise and out-of-domain translation. For German, Spanish, Italian, and French to English translation in the Biomedical Task, we also submit our recently released multilingual Covid19NMT model.

pdf bib
A Multilingual Neural Machine Translation Model for Biomedical Data
Alexandre Bérard | Zae Myung Kim | Vassilina Nikoulina | Eunjeong Lucy Park | Matthias Gallé
Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020

We release a multilingual neural machine translation model, which can be used to translate text in the biomedical domain. The model can translate from 5 languages (French, German, Italian, Korean and Spanish) into English. It is trained with large amounts of generic and biomedical data, using domain tags. Our benchmarks show that it performs near state-of-the-art both on news (generic domain) and biomedical test sets, and that it outperforms the existing publicly released models. We believe that this release will help the large-scale multilingual analysis of the digital content of the COVID-19 crisis and of its effects on society, economy, and healthcare policies. We also release a test set of biomedical text for Korean-English. It consists of 758 sentences from official guidelines and recent papers, all about COVID-19.

2019

pdf bib
On the use of BERT for Neural Machine Translation
Stephane Clinchant | Kweon Woo Jung | Vassilina Nikoulina
Proceedings of the 3rd Workshop on Neural Generation and Translation

Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality. We use WMT-14 English-German, IWSLT15 English-German and IWSLT14 English-Russian datasets for these experiments. In addition to standard task test set evaluation, we perform evaluation on out-of-domain test sets and noise injected test sets, in order to assess how BERT pretrained representations affect model robustness.

pdf bib
Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness
Alexandre Berard | Ioan Calapodescu | Marc Dymetman | Claude Roux | Jean-Luc Meunier | Vassilina Nikoulina
Proceedings of the 3rd Workshop on Neural Generation and Translation

We share a French-English parallel corpus of Foursquare restaurant reviews, and define a new task to encourage research on Neural Machine Translation robustness and domain adaptation, in a real-world scenario where better-quality MT would be greatly beneficial. We discuss the challenges of such user-generated content, and train good baseline models that build upon the latest techniques for MT robustness. We also perform an extensive evaluation (automatic and human) that shows significant improvements over existing online systems. Finally, we propose task-specific metrics based on sentiment analysis or translation accuracy of domain-specific polysemous words.

pdf bib
“Sentiment Aware Map” : exploration cartographique de points d’intĂ©rĂȘt via l’analyse de sentiments au niveau des aspects ()
Ioan Calapodescu | Caroline Brun | Vassilina Nikoulina | Salah AĂŻt-Mokhtar
Actes de la Conférence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Volume IV : Démonstrations

2018

pdf bib
Aspect Based Sentiment Analysis into the Wild
Caroline Brun | Vassilina Nikoulina
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

In this paper, we test state-of-the-art Aspect Based Sentiment Analysis (ABSA) systems trained on a widely used dataset on actual data. We created a new manually annotated dataset of user generated data from the same domain as the training dataset, but from other sources and analyse the differences between the new and the standard ABSA dataset. We then analyse the results in performance of different versions of the same system on both datasets. We also propose light adaptation methods to increase system robustness.

2014

pdf bib
A Lightweight Terminology Verification Service for External Machine Translation Engines
Alessio Bosca | Vassilina Nikoulina | Marc Dymetman
Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics

2012

pdf bib
Linguistically-Adapted Structural Query Annotation for Digital Libraries in the Social Sciences
Caroline Brun | Vassilina Nikoulina | Nikolaos Lagos
Proceedings of the 6th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities

pdf bib
Hybrid Adaptation of Named Entity Recognition for Statistical Machine Translation
Vassilina Nikoulina | Agnes Sandor | Marc Dymetman
Proceedings of the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT

pdf bib
Adaptation of Statistical Machine Translation Model for Cross-Lingual Information Retrieval in a Service Context
Vassilina Nikoulina | Bogomil Kovachev | Nikolaos Lagos | Christof Monz
Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

2008

pdf bib
Using Syntactic Coupling Features for Discriminating Phrase-Based Translations (WMT-08 Shared Translation Task)
Vassilina Nikoulina | Marc Dymetman
Proceedings of the Third Workshop on Statistical Machine Translation

pdf bib
Experiments in Discriminating Phrase-Based Translations on the Basis of Syntactic Coupling Features
Vassilina Nikoulina | Marc Dymetman
Proceedings of the ACL-08: HLT Second Workshop on Syntax and Structure in Statistical Translation (SSST-2)