Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2309.14823 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914814093164544 |
|---|---|
| author | Iranzo-Sánchez, Javier Iranzo-Sánchez, Jorge Giménez, Adrià Civera, Jorge Juan, Alfons |
| author_facet | Iranzo-Sánchez, Javier Iranzo-Sánchez, Jorge Giménez, Adrià Civera, Jorge Juan, Alfons |
| contents | Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_14823 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Segmentation-Free Streaming Machine Translation Iranzo-Sánchez, Javier Iranzo-Sánchez, Jorge Giménez, Adrià Civera, Jorge Juan, Alfons Computation and Language Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance. |
| title | Segmentation-Free Streaming Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2309.14823 |