| 坂口慶祐 | 1151052: M, 2回目発表 | 松本裕治, 関浩之, 新保仁，小町守 |
|
title: Joint English Spelling Error Correction and POS Tagging for Language Learners Writing
abstract: We propose an approach to correcting spelling errors and assigning part-of-speech (POS) tags simultaneously for sentences written by learners of English as a second language (ESL). In ESL writing, there are several types of errors such as preposition, determiner, verb, noun, and spelling errors. Spelling errors often interfere with POS tagging and syntactic parsing, which makes other error detection and correction tasks very difficult. In studies of grammatical error detection and correction in ESL writing, spelling correction has been regarded as a preprocessing step in a pipeline. However, several types of spelling errors in ESL are difficult to correct in the preprocessing, for example, homophones (e.g. *hear/here), confusion (*quiet/quite), split (*now a day/nowadays), merge (*swimingpool/swimming pool), inflection (*please/pleased) and derivation (*badly/bad), where the incorrect word is actually in the vocabulary and grammatical information is needed to disambiguate. In order to correct these spelling errors, and also typical typographical errors (*begginning/beginning), we propose a joint analysis of POS tagging and spelling error correction with a CRF (Conditional Random Field)-based model. We present an approach that achieves significantly better accuracies for both POS tagging and spelling correction, compared to existing approaches using either individual or pipeline analysis. We also show that the joint model can deal with novel types of misspelling in ESL writing. language of the presentation: Japanese | ||
| 西川仁 | 1261010: D, 中間発表 | 松本裕治, 関浩之, 新保仁，小町守 |
|
title: Domain Adaptation with Augmented Space Method for Multi-Domain Contact Center Dialogue Summarization
abstract: We propose a method to improve the quality of extractive summarization for contact center dialogues in various domains by making use of training samples whose domains are different from that of the test samples. Since preparing sufficient numbers of training samples for each domain is too expensive, we leverage references from many different domains and employ the Augmented Space Method to implement domain adaptation. As the target of summarization, we take up contact center dialogues in six domains and summarize their transcripts. Our experiment shows that the proposed method achieves better results than the usual supervised learning approach. language of the presentation: Japanese | ||
| 林部祐太 | 1161009: D, 中間発表 | 松本裕治, 関浩之, 新保仁，小町守 |
|
title: Writing Assistant For ESL learners
It is difficult for learners of English as a second language (ESL) to use prepositions properly. Automatic preposition error correction has been paid attention in recent years. Tough the usage of preposition depends of semantic context, they have not utilized semantic information for it. I will report how effective the large predicate argument structure database for it with the results of experiments on several learners' corpus. | ||