English-to-Chinese transliteration with phonetic auxiliary task
Approaching named entities transliteration as a Neural Machine Translation (NMT) problem is common practice. While many have applied various NMT techniques to enhance machine transliteration models, few focus on the linguistic features particular to the relevant languages. In this paper, we investig...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Association for Computational Linguistics
2020
|
| _version_ | 1826309413471780864 |
|---|---|
| author | He, Y Cohen, SB |
| author_facet | He, Y Cohen, SB |
| author_sort | He, Y |
| collection | OXFORD |
| description | Approaching named entities transliteration as a Neural Machine Translation (NMT) problem is common practice. While many have applied various NMT techniques to enhance machine transliteration models, few focus on the linguistic features particular to the relevant languages. In this paper, we investigate the effect of incorporating phonetic features for English-to-Chinese transliteration under the multi-task learning (MTL) setting—where we define a phonetic auxiliary task aimed to improve the generalization performance of the main transliteration task. In addition to our system, we also release a new English-to-Chinese dataset and propose a novel evaluation metric which considers multiple possible transliterations given a source name. Our results show that the multi-task model achieves similar performance as the previous state of the art with a model of a much smaller size. |
| first_indexed | 2024-03-07T07:33:50Z |
| format | Conference item |
| id | oxford-uuid:bbefdf16-c939-4665-8e3f-9bc9312e6152 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:33:50Z |
| publishDate | 2020 |
| publisher | Association for Computational Linguistics |
| record_format | dspace |
| spelling | oxford-uuid:bbefdf16-c939-4665-8e3f-9bc9312e61522023-02-20T10:36:18ZEnglish-to-Chinese transliteration with phonetic auxiliary taskConference itemhttp://purl.org/coar/resource_type/c_5794uuid:bbefdf16-c939-4665-8e3f-9bc9312e6152EnglishSymplectic ElementsAssociation for Computational Linguistics2020He, YCohen, SBApproaching named entities transliteration as a Neural Machine Translation (NMT) problem is common practice. While many have applied various NMT techniques to enhance machine transliteration models, few focus on the linguistic features particular to the relevant languages. In this paper, we investigate the effect of incorporating phonetic features for English-to-Chinese transliteration under the multi-task learning (MTL) setting—where we define a phonetic auxiliary task aimed to improve the generalization performance of the main transliteration task. In addition to our system, we also release a new English-to-Chinese dataset and propose a novel evaluation metric which considers multiple possible transliterations given a source name. Our results show that the multi-task model achieves similar performance as the previous state of the art with a model of a much smaller size. |
| spellingShingle | He, Y Cohen, SB English-to-Chinese transliteration with phonetic auxiliary task |
| title | English-to-Chinese transliteration with phonetic auxiliary task |
| title_full | English-to-Chinese transliteration with phonetic auxiliary task |
| title_fullStr | English-to-Chinese transliteration with phonetic auxiliary task |
| title_full_unstemmed | English-to-Chinese transliteration with phonetic auxiliary task |
| title_short | English-to-Chinese transliteration with phonetic auxiliary task |
| title_sort | english to chinese transliteration with phonetic auxiliary task |
| work_keys_str_mv | AT hey englishtochinesetransliterationwithphoneticauxiliarytask AT cohensb englishtochinesetransliterationwithphoneticauxiliarytask |