Work

Machine Translation of Labeled Discourse Connectives

Year: 2012

Type: article

Abstract: This paper shows how the disambiguation of discourse connectives can improve their automatic translation, while preserving the overall performance of statistical MT as measured by BLEU.State-of-the-art automatic classifiers for rhetorical relations are used prior to MT to label discourse connectives that signal those relations.These labels are used for MT in two ways: (1) by augmenting factored translation models; and (2) by using the probability distributions of labels in order to train and tune SMT.The improvement of translation quality is demonstrated using a new semi-automated metric for discourse connectives, on the English/French WMT10 data, while BLEU scores remain comparable to non-discourse-aware systems, due to the low frequency of discourse connectives.

Source: Infoscience (Ecole Polytechnique Fédérale de Lausanne)

Authors: Thomas Meyer, Andréi Popescu-Belis, Najeh Hajlaoui, Andréa Gesmundo

Institutions: Idiap Research Institute, University of Geneva

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Award: Improving the coherence of machine translation output by modeling intersentential relations

OpenAlex ID: W120531462