Word Sense Consistency in Statistical and Neural Machine Translation
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.
The various meanings of discourse connectives like while and however are difficult to identify and annotate, even for trained human annotators. This problem is all the more important that connectives are salient textual markers of cohesion and need to be c ...
Europarl is a large multilingual corpus containing the minutes of the debates at the European Parliament. This article presents a method to extract different corpora from Europarl: monolingual and multilingual comparable corpora, as well as parallel corpor ...
The correct translation of verb tenses ensures that the temporal ordering of events in the source text is maintained in the target text. This paper assesses the utility of automatically labeling English Simple Past verbs with a binary discursive feature, n ...
Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically sim- plify the word embed ...
Languages like F#, C#, and recently also Scala, provide “async” extensions which aim to make asynchronous programming easier by avoiding an inversion of control that is inherent in traditional callback-based programming models (for the purpose of this pape ...
The paper presents machine translation experiments from English to Czech with a large amount of manually annotated discourse connectives. The gold-standard discourse relation annotation leads to better translation performance in ranges of 4–60% for some am ...
There has been much discussion in the literature regarding the determinants of ribosomal decoding speed during the mRNA translation process. Computational results based on mechanistic models for ribosomal kinetics have predicted a major role for near-cogna ...
This paper gives a detailed description of the ACT (Accuracy of Connective Translation) metric, a reference-based metric that assesses only connective translations. ACT relies on automatic word-level alignment (using GIZA++) between a source sentence and r ...
Automatic metrics for the evaluation of machine translation (MT) compute scores that characterize globally certain aspects of MT quality such as adequacy and fluency. This paper introduces a reference-based metric that is focused on a particular class of f ...
Business rules are everywhere. Some of these rules are implicit and thus poorly enforced, others are written but not enforced, and still others are perhaps poorly written and obscurely enforced. In this work, we propose an interactive, simulation-driven ap ...
