We address the problem of informal word recognition in Chinese microblogs. A key problem is the lack of word delimiters in Chinese. We exploit this reliance as an opportunity: recognizing the relation between informal word recognition and Chinese word segmentation, we propose to model the two tasks jointly. Our joint inference method significantly outperforms baseline systems that conduct the t...

This study investigated the amount of incidental vocabulary learning through comprehension-focused reading of short stories and explicit instruction to this goal.  Forty male high school students were selected randomly, and divided into two groups of twenty.  One group of these students was given five 400-word-level short stories to read with the purpose of comprehension, and the students in th...

We show that semantic relationships can be used to improve word alignment, in addition to the lexical and syntactic features that are typically used. In this paper, we present a method based on a neural network to automatically derive word similarity from monolingual data. We present an extension to word alignment models that exploits word similarity. Our experiments, in both large-scale and re...

The importance of vocabulary is undeniable. EFL learners need sufficient lexicon in order to bea competitive speaker. Lots of strategies have been proposed. The concept of involvement loadwas first introduced by Hulstijn and Laufer (2001). They believed that deeper explanation oflexical information will result in better retention of them. The present study aimed at finding the...

Current evaluation metrics for image description may be too coarse. We therefore propose a series of binary forced-choice tasks that each focus on a different aspect of the captions. We evaluate a number of different off-the-shelf image description systems. Our results indicate strengths and shortcomings of both generation and ranking based approaches.