A Bi-Encoder LSTM Model For Learning Unstructured Dialogs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910002268078080 |
|---|---|
| author | Brahman, Danny Negi, Pooran S. Mahoor, Mohammad |
| author_facet | Brahman, Danny Negi, Pooran S. Mahoor, Mohammad |
| contents | Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing Retrieval-based Chatbot systems. This paper presents a Long Short Term Memory (LSTM) based architecture that learns unstructured multi-turn dialogs and provides results on the task of selecting the best response from a collection of given responses. Ubuntu Dialog Corpus Version 2 was used as the corpus for training. We show that our model achieves 0.8%, 1.0% and 0.3% higher accuracy for Recall@1, Recall@2 and Recall@5 respectively than the benchmark model. We also show results on experiments performed by using several similarity functions, model hyper-parameters and word embeddings on the proposed architecture |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2104_12269 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | A Bi-Encoder LSTM Model For Learning Unstructured Dialogs Brahman, Danny Negi, Pooran S. Mahoor, Mohammad Computation and Language Artificial Intelligence Information Retrieval Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing Retrieval-based Chatbot systems. This paper presents a Long Short Term Memory (LSTM) based architecture that learns unstructured multi-turn dialogs and provides results on the task of selecting the best response from a collection of given responses. Ubuntu Dialog Corpus Version 2 was used as the corpus for training. We show that our model achieves 0.8%, 1.0% and 0.3% higher accuracy for Recall@1, Recall@2 and Recall@5 respectively than the benchmark model. We also show results on experiments performed by using several similarity functions, model hyper-parameters and word embeddings on the proposed architecture |
| title | A Bi-Encoder LSTM Model For Learning Unstructured Dialogs |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2104.12269 |