Attention-Based End-to-End Named Entity Recognition from Speech
| Autor: | Dejan Porjazovski, Mikko Kurimo, Juho Leinonen |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry 020206 networking & telecommunications 02 engineering and technology computer.software_genre Pipeline (software) Field (computer science) Named entity 030507 speech-language pathology & audiology 03 medical and health sciences End-to-end principle Named-entity recognition 0202 electrical engineering electronic engineering information engineering Encoder decoder Artificial intelligence 0305 other medical science business computer Natural language processing Spoken language |
| Zdroj: | Text, Speech, and Dialogue ISBN: 9783030835262 TDS |
| DOI: | 10.1007/978-3-030-83527-9_40 |
| Popis: | Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|