Cross-Lingual Conversational Speech Summarization with Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916355378249728 |
|---|---|
| author | Nelson, Max Wotherspoon, Shannon Keith, Francis Hartmann, William Snover, Matthew |
| author_facet | Nelson, Max Wotherspoon, Shannon Keith, Francis Hartmann, William Snover, Matthew |
| contents | Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing summaries are non-existent. We build upon the existing Fisher and Callhome Spanish-English Speech Translation corpus by supplementing the translations with summaries. The summaries are generated using GPT-4 from the reference translations and are treated as ground truth. The task is to generate similar summaries in the presence of transcription and translation errors. We build a baseline cascade-based system using open-source speech recognition and machine translation models. We test a range of LLMs for summarization and analyze the impact of transcription and translation errors. Adapting the Mistral-7B model for this task performs significantly better than off-the-shelf models and matches the performance of GPT-4. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06484 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Lingual Conversational Speech Summarization with Large Language Models Nelson, Max Wotherspoon, Shannon Keith, Francis Hartmann, William Snover, Matthew Computation and Language Artificial Intelligence Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing summaries are non-existent. We build upon the existing Fisher and Callhome Spanish-English Speech Translation corpus by supplementing the translations with summaries. The summaries are generated using GPT-4 from the reference translations and are treated as ground truth. The task is to generate similar summaries in the presence of transcription and translation errors. We build a baseline cascade-based system using open-source speech recognition and machine translation models. We test a range of LLMs for summarization and analyze the impact of transcription and translation errors. Adapting the Mistral-7B model for this task performs significantly better than off-the-shelf models and matches the performance of GPT-4. |
| title | Cross-Lingual Conversational Speech Summarization with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.06484 |