Search Results for author: Andrei Popescu-Belis

Found 37 papers, 11 papers with code

Constrained Language Models for Interactive Poem Generation

no code implementations LREC 2022 Andrei Popescu-Belis, Àlex Atrio, Valentin Minder, Aris Xanthos, Gabriel Luthier, Simon Mattei, Antonio Rodriguez

This paper describes a system for interactive poem generation, which combines neural language models (LMs) for poem generation with explicit constraints that can be set by users on form, topic, emotion, and rhyming scheme.

The IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task

no code implementations WMT (EMNLP) 2021 Àlex R. Atrio, Gabriel Luthier, Axel Fahy, Giorgos Vernikos, Andrei Popescu-Belis, Ljiljana Dolamic

We then present the application of this system to the 2021 task for low-resource supervised Upper Sorbian (HSB) to German translation, in both directions.

Translation

On the Interaction of Regularization Factors in Low-resource Neural Machine Translation

1 code implementation EAMT 2022 None Àlex R. Atrio, Andrei Popescu-Belis

We explore the roles and interactions of the hyper-parameters governing regularization, and propose a range of values applicable to low-resource neural machine translation.

Low Resource Neural Machine Translation Low-Resource Neural Machine Translation +1

Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation

no code implementations12 Jan 2024 Giorgos Vernikos, Andrei Popescu-Belis

Our method consistently improves translation quality in terms of COMET and BLEURT scores when applied to large language models (LLMs) used for translation (PolyLM, XGLM, Llama2, Mistral, ALMA, and Tower) and to multilingual translation models (NLLB), over five language pairs.

Machine Translation Translation

Small Batch Sizes Improve Training of Low-Resource Neural MT

no code implementations ICON 2021 Àlex R. Atrio, Andrei Popescu-Belis

We study the role of an essential hyper-parameter that governs the training of Transformers for neural machine translation in a low-resource setting: the batch size.

Machine Translation Translation

A Consolidated Dataset for Knowledge-based Question Generation using Predicate Mapping of Linked Data

no code implementations LREC 2020 Johanna Melly, Gabriel Luthier, Andrei Popescu-Belis

The new data set can be used to generate novel questions given an unseen Wikidata triple, by replacing the subjects of existing questions with the new one and then selecting the best candidate questions using semantic and syntactic criteria.

Question Generation Question-Generation

Chat or Learn: a Data-Driven Robust Question-Answering System

no code implementations LREC 2020 Gabriel Luthier, Andrei Popescu-Belis

We present our choices of data sets for training and testing the components, and present the experimental results that helped us optimize the parameters of the chatbot.

Chatbot coreference-resolution +2

Context in Neural Machine Translation: A Review of Models and Evaluations

no code implementations25 Jan 2019 Andrei Popescu-Belis

This review paper discusses how context has been used in neural machine translation (NMT) in the past two years (2017-2018).

Machine Translation NMT +1

Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation

1 code implementation TACL 2018 Xiao Pu, Nikolaos Pappas, James Henderson, Andrei Popescu-Belis

We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones.

Clustering Machine Translation +3

Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German

1 code implementation LREC 2018 Pierre-Edouard Honnet, Andrei Popescu-Belis, Claudiu Musat, Michael Baeriswyl

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written.

Diversity Machine Translation +1

Multilingual Hierarchical Attention Networks for Document Classification

2 code implementations IJCNLP 2017 Nikolaos Pappas, Andrei Popescu-Belis

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language.

Classification Computational Efficiency +3

Using Coreference Links to Improve Spanish-to-English Machine Translation

1 code implementation WS 2017 Lesly Miculicich Werlen, Andrei Popescu-Belis

In this paper, we present a proof-of-concept implementation of a coreference-aware decoder for document-level machine translation.

Coreference Resolution Decoder +5

Consistent Translation of Repeated Nouns using Syntactic and Semantic Cues

no code implementations EACL 2017 Xiao Pu, Laura Mascarell, Andrei Popescu-Belis

We compare the automatic post-editing of noun translations with the re-ranking of the translation hypotheses based on the classifiers{'} output, and also use these methods in combination.

Automatic Post-Editing Re-Ranking +1

Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities

1 code implementation EACL 2017 Ngoc Quang Luong, Andrei Popescu-Belis, Annette Rios Gonzales, Don Tuggener

We implement a fully probabilistic model to combine the hypotheses of a Spanish anaphora resolution system with those of a Spanish-English machine translation system.

Coreference Resolution Machine Translation +1

English-French Verb Phrase Alignment in Europarl for Tense Translation Modeling

no code implementations LREC 2014 Sharid Lo{\'a}iciga, Thomas Meyer, Andrei Popescu-Belis

This paper presents a method for verb phrase (VP) alignment in an English-French parallel corpus and its use for improving statistical machine translation (SMT) of verb tenses.

Machine Translation POS +2

Discourse-level Annotation over Europarl for Machine Translation: Connectives and Pronouns

no code implementations LREC 2012 Andrei Popescu-Belis, Thomas Meyer, Jeevanthi Liyanapathirana, Bruno Cartoni, S Zufferey, rine

This paper describes methods and results for the annotation of two discourse-level phenomena, connectives and pronouns, over a multilingual parallel corpus.

Machine Translation Translation

ISO 24617-2: A semantically-based standard for dialogue annotation

no code implementations LREC 2012 Harry Bunt, Alex, Jan ersson, Jae-Woong Choe, Alex Chengyu Fang, Koiti Hasida, Volha Petukhova, Andrei Popescu-Belis, David Traum

This paper summarizes the latest, final version of ISO standard 24617-2 ``Semantic annotation framework, Part 2: Dialogue acts''''''''.

Cannot find the paper you are looking for? You can Submit a new open access paper.