Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.03736 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916537373294592 |
|---|---|
| author | Sultania, Dewang Lu, Zhaoyu Naik, Twisha Dernoncourt, Franck Yoon, David Seunghyun Sharma, Sanat Bui, Trung Gupta, Ashok Vatsa, Tushar Suresha, Suhas Verma, Ishita Belavadi, Vibha Chen, Cheng Friedrich, Michael |
| author_facet | Sultania, Dewang Lu, Zhaoyu Naik, Twisha Dernoncourt, Franck Yoon, David Seunghyun Sharma, Sanat Bui, Trung Gupta, Ashok Vatsa, Tushar Suresha, Suhas Verma, Ishita Belavadi, Vibha Chen, Cheng Friedrich, Michael |
| contents | Domain specific question answering is an evolving field that requires specialized solutions to address unique challenges. In this paper, we show that a hybrid approach combining a fine-tuned dense retriever with keyword based sparse search methods significantly enhances performance. Our system leverages a linear combination of relevance signals, including cosine similarity from dense retrieval, BM25 scores, and URL host matching, each with tunable boost parameters. Experimental results indicate that this hybrid method outperforms our single-retriever system, achieving improved accuracy while maintaining robust contextual grounding. These findings suggest that integrating multiple retrieval methodologies with weighted scoring effectively addresses the complexities of domain specific question answering in enterprise settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03736 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain-specific Question Answering with Hybrid Search Sultania, Dewang Lu, Zhaoyu Naik, Twisha Dernoncourt, Franck Yoon, David Seunghyun Sharma, Sanat Bui, Trung Gupta, Ashok Vatsa, Tushar Suresha, Suhas Verma, Ishita Belavadi, Vibha Chen, Cheng Friedrich, Michael Computation and Language Domain specific question answering is an evolving field that requires specialized solutions to address unique challenges. In this paper, we show that a hybrid approach combining a fine-tuned dense retriever with keyword based sparse search methods significantly enhances performance. Our system leverages a linear combination of relevance signals, including cosine similarity from dense retrieval, BM25 scores, and URL host matching, each with tunable boost parameters. Experimental results indicate that this hybrid method outperforms our single-retriever system, achieving improved accuracy while maintaining robust contextual grounding. These findings suggest that integrating multiple retrieval methodologies with weighted scoring effectively addresses the complexities of domain specific question answering in enterprise settings. |
| title | Domain-specific Question Answering with Hybrid Search |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.03736 |