Strong and Efficient Baselines for Open Domain Conversational Question Answering

Andrei Coman, Gianni Barlacchi, Adrià de Gispert


Abstract
Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the State-of-the-Art (SotA) Dense Passage Retrieval (DPR) retriever and Fusion-in-Decoder (FiD) reader pipeline, and show that it significantly underperforms when applied to ODConvQA tasks due to various limitations. We then propose and evaluate strong yet simple and efficient baselines, by introducing a fast reranking component between the retriever and the reader, and by performing targeted finetuning steps. Experiments on two ODConvQA tasks, namely TopiOCQA and OR-QuAC, show that our method improves the SotA results, while reducing reader’s latency by 60%. Finally, we provide new and valuable insights into the development of challenging baselines that serve as a reference for future, more intricate approaches, including those that leverage Large Language Models (LLMs).
Anthology ID:
2023.findings-emnlp.417
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6305–6314
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.417
DOI:
10.18653/v1/2023.findings-emnlp.417
Bibkey:
Cite (ACL):
Andrei Coman, Gianni Barlacchi, and Adrià de Gispert. 2023. Strong and Efficient Baselines for Open Domain Conversational Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6305–6314, Singapore. Association for Computational Linguistics.
Cite (Informal):
Strong and Efficient Baselines for Open Domain Conversational Question Answering (Coman et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.findings-emnlp.417.pdf