Our field has seen significant improvements in the quality of machine translation systems over the past several years. The single biggest factor in this improvement has been the accumulation of ever larger stores of data. However, we now find ourselves the victims of our own success, in that it has become increasingly difficult to train on such large sets of data, due to limitations in memory, ...

In this paper, we investigate how to optimize the vocabulary for a voice search language model. The metric we optimize over is the out-of-vocabulary (OoV) rate since it is a strong indicator of user experience. In a departure from the usual way of measuring OoV rates, web search logs allow us to compute the per-session OoV rate and thus estimate the percentage of users that experience a given O...

The purpose of the present study was to identify any significant relationship between critical thinking ability, L2 vocabulary knowledge, and L2 vocabulary learning strategies of Iranian EFL learners. To this aim, the productive vocabulary levels test was administered to measure the learner’s L2 vocabulary knowledge and observe homogeneity in terms of vocabulary knowledge. At the second stage, ...

Previous research found that iconicity—the motivated correspondence between word form and meaning—contributes to expressive vocabulary acquisition. We present two new experiments with two different databases and with novel analyses to give a detailed quantification of how iconicity contributes to vocabulary acquisition across development, including both receptive understanding and production. T...

We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size for the lexicon, (2) conditioning written text for spoken language recognition, and (3) using additional training outside the text distribution. We found that increasing the lexicon 20,000 words to 40,000 words reduce...

We combine our earlier approach to context-dependent network representation with our algorithm for determinizing weighted networks to build optimized networks for large-vocabulary speech recognition combining an n-gram language model, a pronunciation dictionary and context-dependency modeling. While fullyexpanded networks have been used before in restrictive settings (medium vocabulary or no cr...

This paper presents findings of a study of recognition vocabulary knowledge as a predictor of written Academic English Proficiency (AEP) and overall Academic Achievement in an English medium higher education program in an English-as-a-Foreign-Language (EFL) context. Vocabulary knowledge was measured using a Timed YES/NO (TYN) test. AEP was assessed using an academic writing test based on IELTS....

This study examines a group of Saudi military cadets studying English as foreign language and their willingness to communicate (WTC) using English. The investigated the relationship between cadets’ WTC vocabulary size, along with perceived competence. In addition, looked at L2 anxiety. A survey was designed for administered 113 an average age 20 years old. Correlation regression analyses reveal...