Team Z: Wiktionary as a L2 Writing Assistant

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 624–627, Dublin, Ireland, August 23-24, 2014. Team Z: Wiktionary as a L2 Writing Assistant Anubhav Gupta UFR SLHS Universit´e de Franche-Comt´e anubhav.gupta@edu.univ-fcomte.fr Abstract This paper presents a word-for-word trans- lation approach using Wiktionary for SemEval-2014 Task 5. The language pairs attempted for this task were English- Spanish and English-German. Since this approach did not take context into account, it performed poorly. 1 Introduction The objective of SemEval-2014 Task 5 is to trans- late a few words or a phrase from one language (L1) into another (L2). More specifically, a sen- tence containing primarily L2 and a few L1 words is provided, and the task is to translate the L1 words into the L2. This task is similar to the previ- ous cross-linguistic SemEval tasks involving lexi- cal substitution (Mihalcea et al., 2010) and word- sense disambiguation (Lefever and Hoste, 2013). For example, consider the following sentence, written entirely in German except for one English word: Aber auf diesem Schiff wollen wir auch Ruderer sein, wir sitzen im selben Boot und wollen mit Ihnen row. Here, the word row is polysemous and can be translated as the verb rudern or as the noun Reihe depending on context. The words to be translated can also form an idiomatic expres- sion, such as in exchange in die 1967 eroberten arabischen Gebiete in exchange gegen Frieden. These examples reveal that this is not a straightfor- ward task, as word-for-word translation may give inaccurate results. Wiktionary is a multilingual dictionary con- taining word-sense, examples, sample quotations, collocations, usage notes, proverbs and transla- tions (Torsten et al., 2008; Meyer and Gurevych, 2012). Since Wiktionary data have previously This work is licensed under a Creative Commons Attribution 4.0 International Licence. Page numbers and proceedings footer are added by the organisers. Licence details: http: //creativecommons.org/licenses/by/4.0/ been used for translations (Orlandi and Passant, 2010), it was chosen for looking up the transla- tion of source language (L1) words. However, the translation approach was word-for-word and ig- nored the target language (L2) context, i.e., the context in which the text fragment to be trans- lated is found. The Wiktionary-based solution is for English-to-Spanish and English-to-German language translation though four language pairs were provided in this shared task. 2 Wiktionary For a given word, the English version of Wik- tionary gives not only its definition but also possi- ble translations. The translations are divided based on part of speech (PoS) and word sense and at times also encode gender and number informa- tion. For example, the German and Spanish trans- lations for the English word book are stored in Wiktionary as follows: ====Noun==== {{en-noun}} =====Translations===== {{trans-top|collection of sheets of paper bound together containing printed or written material}} * German: {{t+|de|Buch|n}} * Spanish: {{t+|es|libro|m}} {{trans-top|record of betting}} * German: {{t|de|Wettliste|f}} {{trans-top|convenient collection of small paper items, such as stamps}} * German: {{t+|de|Album|n}} * Spanish: {{t+|es|´album|m}} {{trans-top|major division of a published work, larger than 624 a chapter}} {{trans-top|script of a musical}} …

Content truncated to 500 words