A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing
نویسندگان
چکیده
This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models. We extensively compare various word-level vocabularies to show that the performance of smoothing is not significantly affected by the choice of vocabulary. This result provides empirical evidence that the standard phrase translation model is extremely sparse. Our experiments also reveal that vocabulary reduction is more effective for smoothing large-scale phrase tables.
منابع مشابه
Nanjing University’s System Report for NIST MT09 Workshop
This paper describes our participation (NJU-NLP) in the Chinese-to-English Progress Test of the NIST Open MT09 evaluation. We built a phrase-based machine translation system with the help of MOSES and tried several methods to improve the result. Our efforts include pre-segmenting long train sentence pairs into shorter ones, phrase table smoothing, phrase table filtering. Details of these techni...
متن کاملThe Comparative Study of the Iranian EFL Learners Vocabulary Learning through Two Different Formats: Paper & Pencil vs. Software
This study aimed to investigate the effect of using vocabulary software on the vocabulary learning of Iranian EFL learners. Participants of the study were 54 intermediate-level students (23 males and 31 females) learning English as a foreign language in Mehr Institute in Izeh who were selected after taking the Nelson English Language Test as a proficiency test. They were randomly divided into t...
متن کاملVector Space Models for Phrase-based Machine Translation
This paper investigates the application of vector space models (VSMs) to the standard phrase-based machine translation pipeline. VSMs are models based on continuous word representations embedded in a vector space. We exploit word vectors to augment the phrase table with new inferred phrase pairs. This helps reduce out-of-vocabulary (OOV) words. In addition, we present a simple way to learn bili...
متن کاملThe comparative effects of song, picture and the keyword method on L2 vocabulary recognition and production
The present study investigated the effects of three methods of vocabulary presentation, i.e., picture, song, and the keyword method on Iranian EFL learners' vocabulary recognition and production. The participants were 102 Iranian lower-intermediate EFL learners in Zaban Sara English language institute in Kermanshah. To make sure that they had no previous knowl...
متن کاملComparative Study of the Academic Vocabulary Content of Electronic Engi-neering Corpora, GE Materials and M.S. Entrance Examinations
The importance of vocabulary learning has been underlined in the field of English for Academic Purposes (EAP) because non-English majors who require reading English texts in their fields of study have to expand their English vocabulary knowledge much more efficiently than ordinary ESL/EFL learners. Since academic vocabulary instruction in Iranian universities is realized through the use of Gene...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016