Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2403.00586 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910349618315264 |
|---|---|
| author | Fischer, Sophie Rossetto, Federico Gemmell, Carlos Ramsay, Andrew Mackie, Iain Zubel, Philip Tecklenburg, Niklas Dalton, Jeffrey |
| author_facet | Fischer, Sophie Rossetto, Federico Gemmell, Carlos Ramsay, Andrew Mackie, Iain Zubel, Philip Tecklenburg, Niklas Dalton, Jeffrey |
| contents | We present the second version of the Open Assistant Toolkit (OAT-v2), an open-source task-oriented conversational system for composing generative neural models. OAT-v2 is a scalable and flexible assistant platform supporting multiple domains and modalities of user interaction. It splits processing a user utterance into modular system components, including submodules such as action code generation, multimodal content retrieval, and knowledge-augmented response generation. Developed over multiple years of the Alexa TaskBot challenge, OAT-v2 is a proven system that enables scalable and robust experimentation in experimental and real-world deployment. OAT-v2 provides open models and software for research and commercial applications to enable the future of multimodal virtual assistants across diverse applications and types of rich interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00586 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open Assistant Toolkit -- version 2 Fischer, Sophie Rossetto, Federico Gemmell, Carlos Ramsay, Andrew Mackie, Iain Zubel, Philip Tecklenburg, Niklas Dalton, Jeffrey Information Retrieval We present the second version of the Open Assistant Toolkit (OAT-v2), an open-source task-oriented conversational system for composing generative neural models. OAT-v2 is a scalable and flexible assistant platform supporting multiple domains and modalities of user interaction. It splits processing a user utterance into modular system components, including submodules such as action code generation, multimodal content retrieval, and knowledge-augmented response generation. Developed over multiple years of the Alexa TaskBot challenge, OAT-v2 is a proven system that enables scalable and robust experimentation in experimental and real-world deployment. OAT-v2 provides open models and software for research and commercial applications to enable the future of multimodal virtual assistants across diverse applications and types of rich interaction. |
| title | Open Assistant Toolkit -- version 2 |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2403.00586 |