Yoko Futagi

A Computational Approach to Detecting Collocation Errors in the Writing of Non-Native Speakers of English.

This paper describes the first prototype of an automated tool for detecting collocation errors in texts written by non-native speakers of English. Candidate strings are extracted by pattern matching over POS-tagged text. Since learner texts often contain spelling and morphological errors, the tool attempts to automatically correct them in order to reduce noise. For a measure of collocation strength, we use the rank-ratio statistic calculated over one billion words of native-speaker texts. Two human annotators evaluated the systems performance. We report the overall results, as well as detailed error analyses, and discuss possible improvements for the future.

Method and system for assessing pronunciation difficulties of non-native speakers by entropy calculation

The present disclosure presents a useful metric for assessing the relative difficulty which non-native speakers face in pronouncing a given utterance and a method and systems for using such a metric in the evaluation and assessment of the utterances of non-native speakers. In an embodiment, the metric may be based on both known sources of difficulty for language learners and a corpus-based measure of cross-language sound differences. The method may be applied to speakers who primarily speak a first language speaking utterances in any non-native second language.

Preliminary Experiments on Crowdsourced Evaluation of Feedback Granularity

Providing writing feedback to English language learners (ELLs) helps them learn to write better, but it is not clear what type or how much information should be provided. There have been few experiments directly comparing the effects of different types of automatically generated feedback on ELL writing. Such studies are difficult to conduct because they require participation and commitment from actual students and their teachers, over extended periods of time, and in real classroom settings. In order to avoid such difficulties, we instead conduct a crowdsourced study on Amazon Mechanical Turk to answer questions concerning the effects of type and amount of writing feedback. We find that our experiment has several serious limitations but still yields some interesting results.