Publication

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Related publications (34)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Word Sense Consistency in Statistical and Neural Machine Translation

Xiao Pu

Different senses of source words must often be rendered by different words in the target language when performing machine translation (MT). Selecting the correct translation of polysemous words can be done based on the contexts of use. However, state-of-th ...

EPFL2018

Translating Data into Images: The Design Process for the Creation of Visualizations

Dario Rodighiero

The design process is a series of endeavors aimed to solve a problem, which is extensively defined as a need, a task, a situation, etc. Visualizations are objects that result from a design process that solves a problem of unreadable data. They are technica ...

2018

Collaborative Filtering Under a Sybil Attack: Similarity Metrics do Matter!

Rachid Guerraoui, Anne-Marie Kermarrec, Davide Frey, Antoine Rault, Florestan Laurentin Marie De Moor

Recommendation systems help users identify interesting content, but they also open new privacy threats. In this paper, we deeply analyze the effect of a Sybil attack that tries to infer information on users from a user-based collaborative-filtering recomme ...

IEEE2018

Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms

Maud Ehrmann

This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual c ...

European Language Resources Association (ELRA)2016

Discourse-level features for statistical machine translation

Thomas Meyer

Machine Translation (MT) has progressed tremendously in the past two decades. The rule-based and interlingua approaches have been superseded by statistical models, which learn the most likely translations from large parallel corpora. System design does not ...

EPFL2015

, ,

Noise in genetic networks has been the subject of extensive experimental and computational studies. However, very few of these studies have considered noise properties using mechanistic models that account for the discrete movement of ribosomes and RNA pol ...

Amer Inst Physics2015

Disambiguating Discourse Connectives for Statistical Machine Translation

Andrei Popescu-Belis, Thomas Meyer

This paper shows that the automatic labeling of discourse connectives with the relations they signal, prior to machine translation (MT), can be used by phrase-based statistical MT systems to improve their translations. This improvement is demonstrated here ...

2015

Discourse-level Features for Statistical Machine Translation

Thomas Meyer

École Polytechnique Fédérale de Lausanne (EPFL)2014

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

Andrei Popescu-Belis, Thomas Meyer

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. The method starts from automatic word alignment performed with GIZA++, and reli ...

2014

Automatic Speech Recognition and Translation of a Swiss German Dialect: Walliserdeutsch

Philip Neil Garner, David Imseng, Thomas Meyer

Walliserdeutsch is a Swiss German dialect spoken in the south west of Switzerland. To investigate the potential of automatic speech processing of Walliserdeutsch, a small database was collected based mainly on broadcast news from a local radio station. Exp ...

2014