Techniques to Improve Q&A Accuracy with Transformer-based models on Large Complex Documents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916526302429184 |
|---|---|
| author | Liao, Chejui Maniar, Tabish N, Sravanajyothi Sharma, Anantha |
| author_facet | Liao, Chejui Maniar, Tabish N, Sravanajyothi Sharma, Anantha |
| contents | This paper discusses the effectiveness of various text processing techniques, their combinations, and encodings to achieve a reduction of complexity and size in a given text corpus. The simplified text corpus is sent to BERT (or similar transformer based models) for question and answering and can produce more relevant responses to user queries. This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2009_12695 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Techniques to Improve Q&A Accuracy with Transformer-based models on Large Complex Documents Liao, Chejui Maniar, Tabish N, Sravanajyothi Sharma, Anantha Computation and Language Artificial Intelligence This paper discusses the effectiveness of various text processing techniques, their combinations, and encodings to achieve a reduction of complexity and size in a given text corpus. The simplified text corpus is sent to BERT (or similar transformer based models) for question and answering and can produce more relevant responses to user queries. This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy. |
| title | Techniques to Improve Q&A Accuracy with Transformer-based models on Large Complex Documents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2009.12695 |