Deep Neural Architecture for Recovering Dropped Pronouns in Korean
Pronouns are frequently dropped in Korean sentences, especially in text messages in the mobile phone environment. Restoring dropped pronouns can be a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many other applications. In this work, we ad...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2018-04-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2017-0085 |
| _version_ | 1828826148053712896 |
|---|---|
| author | Sangkeun Jung Changki Lee |
| author_facet | Sangkeun Jung Changki Lee |
| author_sort | Sangkeun Jung |
| collection | DOAJ |
| description | Pronouns are frequently dropped in Korean sentences, especially in text messages in the mobile phone environment. Restoring dropped pronouns can be a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many other applications. In this work, we address the problem of dropped pronoun recovery by resolving two simultaneous subtasks: detecting zero‐pronoun sentences and determining the type of dropped pronouns. The problems are statistically modeled by encoding the sentence and classifying types of dropped pronouns using a recurrent neural network (RNN) architecture. Various RNN‐based encoding architectures were investigated, and the stacked RNN was shown to be the best model for Korean zero‐pronoun recovery. The proposed method does not require any manual features to be implemented; nevertheless, it shows good performance. |
| first_indexed | 2024-12-12T14:32:50Z |
| format | Article |
| id | doaj.art-5887001e0fa04630be143f0b0167e350 |
| institution | Directory Open Access Journal |
| issn | 1225-6463 2233-7326 |
| language | English |
| last_indexed | 2024-12-12T14:32:50Z |
| publishDate | 2018-04-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-5887001e0fa04630be143f0b0167e3502022-12-22T00:21:27ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632233-73262018-04-0140225726510.4218/etrij.2017-008510.4218/etrij.2017-0085Deep Neural Architecture for Recovering Dropped Pronouns in KoreanSangkeun JungChangki LeePronouns are frequently dropped in Korean sentences, especially in text messages in the mobile phone environment. Restoring dropped pronouns can be a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many other applications. In this work, we address the problem of dropped pronoun recovery by resolving two simultaneous subtasks: detecting zero‐pronoun sentences and determining the type of dropped pronouns. The problems are statistically modeled by encoding the sentence and classifying types of dropped pronouns using a recurrent neural network (RNN) architecture. Various RNN‐based encoding architectures were investigated, and the stacked RNN was shown to be the best model for Korean zero‐pronoun recovery. The proposed method does not require any manual features to be implemented; nevertheless, it shows good performance.https://doi.org/10.4218/etrij.2017-0085Deep learningDropped pronoun recoveryLSTM EncodingZero pronoun |
| spellingShingle | Sangkeun Jung Changki Lee Deep Neural Architecture for Recovering Dropped Pronouns in Korean ETRI Journal Deep learning Dropped pronoun recovery LSTM Encoding Zero pronoun |
| title | Deep Neural Architecture for Recovering Dropped Pronouns in Korean |
| title_full | Deep Neural Architecture for Recovering Dropped Pronouns in Korean |
| title_fullStr | Deep Neural Architecture for Recovering Dropped Pronouns in Korean |
| title_full_unstemmed | Deep Neural Architecture for Recovering Dropped Pronouns in Korean |
| title_short | Deep Neural Architecture for Recovering Dropped Pronouns in Korean |
| title_sort | deep neural architecture for recovering dropped pronouns in korean |
| topic | Deep learning Dropped pronoun recovery LSTM Encoding Zero pronoun |
| url | https://doi.org/10.4218/etrij.2017-0085 |
| work_keys_str_mv | AT sangkeunjung deepneuralarchitectureforrecoveringdroppedpronounsinkorean AT changkilee deepneuralarchitectureforrecoveringdroppedpronounsinkorean |