Abstract
Despite significant advancements in Question-Answering (QA) systems based on Large Languge Models (LLMs), the issue of generating imprecise answers leading to less informative responses persists. To develop effective QA systems for open-domain datasets, particularly content-specific datasets, dense passage retrieval and the two-stage retriever-reader model remain a rational choice. However, when being applied in real-world systems, these approaches encounter challenges posed by the limitation of computational resources and training data. To address the scarcity of training data, we propose fine-tuning the pretrained BERT-based encoder using masked language modeling before employing a dual-encoder architecture—an established and efficient technique. Additionally, we introduce a modified loss function for dual-encoder training that reduces memory usage during training without compromising system performance. The new loss function is employed in a multi-stage training strategy, yielding enhanced retriever performance at each training stage. To further augment the system's capabilities, we train a cross-encoder to construct a robust retriever for domain-specific datasets. The effectiveness of these proposed techniques is validated by experiments with significant increases in performance compared to the baseline models, underscoring their potential to advance the state-of-the-art in open-domain question-answering systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chang, W.C., Yu, F.X., Chang, Y.W., Yang, Y., Kumar, S.: Pre-training tasks for embedding-based large-scale retrieval (2020)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)
Fajcik, M., Docekal, M., Ondrej, K., Smrz, P.: R2-d2: a modular baseline for open-domain question answering (2021)
Gao, L., Callan, J.: Condenser: a pre-training architecture for dense retrieval (2021)
Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.W.: Realm: retrieval-augmented language model pre-training (2020)
Johnson, J., Douze, M., Jégou, H.: Billion-scale similarity search with gpus (2017)
Karpukhin, V., OÄŸuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., Yih, W.: Dense passage retrieval for open-domain question answering (2020)
Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering (2019)
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: a robustly optimized bert pretraining approach (2019)
Luan, Y., Eisenstein, J., Toutanova, K., Collins, M.: Sparse, dense, and attentional representations for text retrieval (2021)
Nguyen, D.Q., Nguyen, A.T.: Phobert: pre-trained language models for Vietnamese (2020)
Nogueira, R., Cho, K.: Passage re-ranking with BERT (2020)
Qu, Y., Ding, Y., Liu, J., Liu, K., Ren, R., Zhao, W.X., Dong, D., Wu, H., Wang, H.: RocketQA: an optimized training approach to dense passage retrieval for open-domain question answering (2021)
Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using Siamese bert-networks (2019)
Robertson, S., Walker, S.: Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval, pp. 232–241 (Jan. 1994). https://doi.org/10.1007/978-1-4471-2099-524
Robertson, S.E., Zaragoza, H.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr.Retr. 3, 333–389 (2009)
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag.Manag. 24, 513–523 (1988)
**ong, L., **ong, C., Li, Y., Tang, K.F., Liu, J., Bennett, P., Ahmed, J., Over-Wijk, A.: Approximate nearest neighbor negative contrastive learning for dense text retrieval (2020)
Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, Q.N., Le, H.T. (2023). Building an Efficient Retriever System with Limited Resources. In: Nghia, P.T., Thai, V.D., Thuy, N.T., Son, L.H., Huynh, VN. (eds) Advances in Information and Communication Technology. ICTA 2023. Lecture Notes in Networks and Systems, vol 847. Springer, Cham. https://doi.org/10.1007/978-3-031-49529-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-49529-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49528-1
Online ISBN: 978-3-031-49529-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)