Jhih-Jie Chen


2020

pdf bib
LinggleWrite: a Coaching System for Essay Writing
Chung-Ting Tsai | Jhih-Jie Chen | Ching-Yu Yang | Jason S. Chang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

This paper presents LinggleWrite, a writing coach that provides writing suggestions, assesses writing proficiency levels, detects grammatical errors, and offers corrective feedback in response to user’s essay. The method involves extracting grammar patterns, training models for automated essay scoring (AES) and grammatical error detection (GED), and finally retrieving plausible corrections from a n-gram search engine. Experiments on public test sets indicate that both AES and GED models achieve state-of-the-art performance. These results show that LinggleWrite is potentially useful in helping learners improve their writing skills.

pdf bib
Chinese Spelling Check based on Neural Machine Translation
Jhih-Jie Chen | Hai-Lun Tu | Ching-Yu Yang | Chiao-Wen Li | Jason S. Chang
International Journal of Computational Linguistics & {C}hinese Language Processing, Volume 25, Number 1, June 2020

2019

pdf bib
Learning to Respond to Mixed-code Queries using Bilingual Word Embeddings
Chia-Fang Ho | Jason Chang | Jhih-Jie Chen | Chingyu Yang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

We present a method for learning bilingual word embeddings in order to support second language (L2) learners in finding recurring phrases and example sentences that match mixed-code queries (e.g., “接 受 sentence”) composed of words in both target language and native language (L1). In our approach, mixed-code queries are transformed into target language queries aimed at maximizing the probability of retrieving relevant target language phrases and sentences. The method involves converting a given parallel corpus into mixed-code data, generating word embeddings from mixed-code data, and expanding queries in target languages based on bilingual word embeddings. We present a prototype search engine, x.Linggle, that applies the method to a linguistic search engine for a parallel corpus. Preliminary evaluation on a list of common word-translation shows that the method performs reasonablly well.

pdf bib
漢語及物化的大數據研究(A Data Scientific Study of Transitivization in Chinese)
Wei-Tien Dylan Tsai | Ching-Yu Helen Yang | Ying-Zhu Chen | Jhih-Jie Chen | Jason S. Chang
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

pdf bib
Level-Up: Learning to Improve Proficiency Level of Essays
Wen-Bin Han | Jhih-Jie Chen | Chingyu Yang | Jason Chang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We introduce a method for generating suggestions on a given sentence for improving the proficiency level. In our approach, the sentence is transformed into a sequence of grammatical elements aimed at providing suggestions of more advanced grammar elements based on originals. The method involves parsing the sentence, identifying grammatical elements, and ranking related elements to recommend a higher level of grammatical element. We present a prototype tutoring system, Level-Up, that applies the method to English learners’ essays in order to assist them in writing and reading. Evaluation on a set of essays shows that our method does assist user in writing.

pdf bib
Learning to Link Grammar and Encyclopedic Information of Assist ESL Learners
Jhih-Jie Chen | Chingyu Yang | Peichen Ho | Ming Chiao Tsai | Chia-Fang Ho | Kai-Wen Tuan | Chung-Ting Tsai | Wen-Bin Han | Jason Chang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We introduce a system aimed at improving and expanding second language learners’ English vocabulary. In addition to word definitions, we provide rich lexical information such as collocations and grammar patterns for target words. We present Linggle Booster that takes an article, identifies target vocabulary, provides lexical information, and generates a quiz on target words. Linggle Booster also links named-entity to corresponding Wikipedia pages. Evaluation on a set of target words shows that the method have reasonably good performance in terms of generating useful and information for learning vocabulary.

2018

pdf bib
Cool English: a Grammatical Error Correction System Based on Large Learner Corpora
Yu-Chun Lo | Jhih-Jie Chen | Chingyu Yang | Jason Chang
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

This paper presents a grammatical error correction (GEC) system that provides corrective feedback for essays. We apply the sequence-to-sequence model, which is frequently used in machine translation and text summarization, to this GEC task. The model is trained by EF-Cambridge Open Language Database (EFCAMDAT), a large learner corpus annotated with grammatical errors and corrections. Evaluation shows that our system achieves competitive performance on a number of publicly available testsets.

pdf bib
LanguageNet: Learning to Find Sense Relevant Example Sentences
Shang-Chien Cheng | Jhih-Jie Chen | Chingyu Yang | Jason Chang
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

In this paper, we present a system, LanguageNet, which can help second language learners to search for different meanings and usages of a word. We disambiguate word senses based on the pairs of an English word and its corresponding Chinese translations in a parallel corpus, UM-Corpus. The process involved performing word alignment, learning vector space representations of words and training a classifier to distinguish words into groups of senses. LanguageNet directly shows the definition of a sense, bilingual synonyms and sense relevant examples.

pdf bib
Chinese Spelling Check based on Neural Machine Translation
Chiao-Wen Li | Jhih-Jie Chen | Jason Chang
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

pdf bib
SmartWrite: Extracting Chinese Lexical Grammar Patterns Using Dependency Parsing
Cheng-Cyuan Peng | Ching-Yu Yang | Jhih-Jie Chen | Jason Chang
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

pdf bib
節能知識問答機器人 (Energy Saving Knowledge Chatbot) [In Chinese]
Jhih-Jie Chen | Shih-Ying Chang | Tsu-Jin Chiu | Ming-Chiao Tsai | Jason S. Chang
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)

2017

pdf bib
Verb Replacer: An English Verb Error Correction System
Yu-Hsuan Wu | Jhih-Jie Chen | Jason Chang
Proceedings of the IJCNLP 2017, System Demonstrations

According to the analysis of Cambridge Learner Corpus, using a wrong verb is the most common type of grammatical errors. This paper describes Verb Replacer, a system for detecting and correcting potential verb errors in a given sentence. In our approach, alternative verbs are considered to replace the verb based on an error-annotated corpus and verb-object collocations. The method involves applying regression on channel models, parsing the sentence, identifying the verbs, retrieving a small set of alternative verbs, and evaluating each alternative. Our method combines and improves channel and language models, resulting in high recall of detecting and correcting verb misuse.

pdf bib
Learning Synchronous Grammar Patterns for Assisted Writing for Second Language Learners
Chi-En Wu | Jhih-Jie Chen | Jim Chang | Jason Chang
Proceedings of the IJCNLP 2017, System Demonstrations

In this paper, we present a method for extracting Synchronous Grammar Patterns (SGPs) from a given parallel corpus in order to assisted second language learners in writing. A grammar pattern consists of a head word (verb, noun, or adjective) and its syntactic environment. A synchronous grammar pattern describes a grammar pattern in the target language (e.g., English) and its counterpart in an other language (e.g., Mandarin), serving the purpose of native language support. Our method involves identifying the grammar patterns in the target language, aligning these patterns with the target language patterns, and finally filtering valid SGPs. The extracted SGPs with examples are then used to develop a prototype writing assistant system, called WriteAhead/bilingual. Evaluation on a set of randomly selected SGPs shows that our system provides satisfactory writing suggestions for English as a Second Language (ESL) learners.

2016

pdf bib
Linggle Knows: A Search Engine Tells How People Write
Jhih-Jie Chen | Hao-Chun Peng | Mei-Cih Yeh | Peng-Yu Chen | Jason Chang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

This paper shows the great potential of incorporating different approaches to help writing. Not only did they solve different kinds of writing problems, but also they complement and reinforce each other to be a complete and effective solution. Despite the extensive and multifaceted feedback and suggestion, writing is not all about syntactically or lexically well-written. It involves contents, structure, the certain understanding of the background, and many other factors to compose a rich, organized and sophisticated text. (e.g., conventional structure and idioms in academic writing). There is still a long way to go to accomplish the ultimate goal. We envision the future of writing to be a joyful experience with the help of instantaneous suggestion and constructive feedback.