A tool for detecting French-English cognates and false friends
1551Authors
nan
Abstract
AbstractCognates are pairs of words in different languages similar in spelling and meaning. They can help a second-language learner on the tasks of vocabulary expansion and reading comprehension. False friends are pairs of words that have similar spelling but different meanings. Partial cognates are pairs of words in two languages that have the same meaning in some, but not all contexts. In this article we present a method to automatically classify a pair of words as cognates or false friends, by using several measures of orthographic similarity as features for classification. We use this method to create complete lists of cognates and false friends between two languages. We also disambiguate partial cognates in context. We applied all our methods to French and English, but they can be applied to other pairs of languages as well. We built a tool that takes the produced lists and annotates a French text with equivalent English cognates or false friends, in order to help second-language learners improve their reading comprehension skills and retention rate.
Keywords
Full Content
TALN 2007, Toulouse, 5–8 juin 2007 A tool for detecting French-English cognates and false friends Oana FRUNZA, Diana INKPEN School of Information Technology and Engineering University of Ottawa, Ottawa, ON, K1N 6N5, Canada {ofrunza,diana}@site.uottawa.ca Résumé. Les congénères sont des mots qui ont au moins un sens en commun entre deux langues en plus d‘avoir une orthographie semblable. La reconnaissance de ce type de mots permet aux apprenants de langue seconde ou étrangère d‘enrichir plus rapidement leur vocabu- laire et d‘améliorer leur compréhension écrite. Toutefois, les faux amis sont des paires de mots qui à l‘écrit ont des similarités, mais ils ont des significations différentes. Pour leur part, les congénères partiels sont des mots qui ont la même signification dans certains contextes dans chacune des deux langues. Cet article présente une méthode pour la classification automatique des paires des mots classées en congénères ou faux amis, en utilisant des mesures de simi- larité orthographiques et des méthodes d‘apprentissage automatique. Ainsi, nous construisons des listes complètes des congénères et des faux amis entre les deux langues. Nous désambigui- sons les congénères partiels dans des contextes spécifiques. Nos méthodes sont évaluées pour le français et l‘anglais, mais elles seraient applicables à d‘autres paires des langues. Nous avons construit un outil qui prend ces listes et marque dans un texte français les mots qui ont des congénères ou des faux amis en anglais, dans le but d‘aider les apprenants en français langue seconde ou étrangère à améliorer leur compréhension écrite et à développer une meilleure ré- tention. Abstract. Cognates are pairs of words in different languages similar in spelling and mea- ning. They can help a second-language learner on the tasks of vocabulary expansion and rea- ding comprehension. False friends are pairs of words that have similar spelling but different meanings. Partial cognates are pairs of words in two languages that have the same meaning in some, but not all contexts. In this article we present a method to automatically classify a pair of words as cognates or false friends, by using several measures of orthographic similarity as features for classification. We use this method to create complete lists of cognates and false friends between two languages. We also disambiguate partial cognates in context. We applied all our methods to French and English, but they can be applied to other pairs of languages as well. We built a tool that takes the produced lists and annotates a French text with equivalent En- glish cognates or false friends, in order to help second-language learners improve their reading comprehension skills and retention rate. Mots-clés : congénères, faux amis, congénères partiels, mesures de similarité orthogra- phiques, apprentissage automatique, apprentissage des langues assisté par ordinateur. Keywords: cognates, false friends, partial cognates, orthographic similarity measures, machine learning (ML), computer-assisted language learning (CALL). 91 Oana FRUNZA, Diana INKPEN 1 Introduction When learning a second language, a student can benefit from knowledge in his/her first language (Gass, 1987), (LeBlanc et al., 1989). Cognate words can accelerate vocabulary acquisition and facilitate the …
Content truncated to 500 words
Labeled Text
AbstractCognates are pairs of words in different languages similar in spelling and meaning. They can help a second-language learner on the tasks of vocabulary expansion and reading comprehension. False friends are pairs of words that have similar spelling but different meanings. Partial cognates are pairs of words in two languages that have the same meaning in some, but not all contexts. In this article we present a method to automatically classify a pair of words as cognates or false friends, by using several measures of orthographic similarity as features for classification. We use this method to create complete lists of cognates and false friends between two languages. We also disambiguate partial cognates in context. We applied all our methods to French and English, but they can be applied to other pairs of languages as well. We built a tool that takes the produced lists and annotates a French text with equivalent English cognates or false friends, in order to help second-language learners improve their reading comprehension skills and retention rate.
Publication Details
- Paper ID:
- 1551
- Year:
- 2007
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan