Peyman Heidari
Research Subjects
Research Interests
Peyman Heidari has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Arash Einolghozati
Meta Reality Lab 1
3 shared publications - Shashank Jain
Meta Reality Lab 1
3 shared publications - Anchit Gupta
Meta Reality Lab 1
2 shared publications - Ankit Arun2 shared publications
- Anuj Kumar
Facebook Conversational AI 1 Hacker Way 94025 Menlo Park CA USA
2 shared publications Barlas Oguz
Meta Reality Lab 1
2 shared publications
Latest Publications
- Open Access
A Study on the Efficiency and Generalization of Light Hybrid Retrievers
Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance"? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves 13X memory while maintaining 98.0% performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.
Open AccessA Study on the Efficiency and Generalization of Light Hybrid Retrievers
Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance"? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves 13X memory while maintaining 98.0% performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1617-1626
A Study on the Efficiency and Generalization of Light Hybrid Retrievers
Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati, Barlas Oguz, Debojeet Chatterjee, Xilun Chen, Chitta Baral, Peyman Heidari. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1617-1626
Open AccessA Study on the Efficiency and Generalization of Light Hybrid Retrievers
Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati, Barlas Oguz, Debojeet Chatterjee, Xilun Chen, Chitta Baral, Peyman Heidari. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 66-76
Getting to Production with Few-shot Natural Language Generation Models
Peyman Heidari, Arash Einolghozati, Shashank Jain, Soumya Batra, Lee Callender, Ankit Arun, Shawn Mei, Sonal Gupta, Pinar Donmez, Vikas Bhardwaj, Anuj Kumar, Michael White. Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2021.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 66-76
Open AccessGetting to Production with Few-shot Natural Language Generation Models
Peyman Heidari, Arash Einolghozati, Shashank Jain, Soumya Batra, Lee Callender, Ankit Arun, Shawn Mei, Sonal Gupta, Pinar Donmez, Vikas Bhardwaj, Anuj Kumar, Michael White. Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2021.
- Open Access
Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data
Natural language generation (NLG) is a critical component in conversational systems, owing to its role of formulating a correct and natural text response. Traditionally, NLG components have been deployed using template-based solutions. Although neural network solutions recently developed in the research community have been shown to provide several benefits, deployment of such model-based solutions has been challenging due to high latency, correctness issues, and high data needs. In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production. We describe a family of sampling and modeling techniques to attain production quality with light-weight neural network models using only a fraction of the data that would be necessary otherwise, and show a thorough comparison between each. Our results show that domain complexity dictates the appropriate approach to achieve high data efficiency. Finally, we distill the lessons from our experimental findings into a list of best practices for production-level NLG model development, and present them in a brief runbook. Importantly, the end products of all of the techniques are small sequence-to-sequence models (2Mb) that we can reliably deploy in production.
Open AccessBest Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data
Natural language generation (NLG) is a critical component in conversational systems, owing to its role of formulating a correct and natural text response. Traditionally, NLG components have been deployed using template-based solutions. Although neural network solutions recently developed in the research community have been shown to provide several benefits, deployment of such model-based solutions has been challenging due to high latency, correctness issues, and high data needs. In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production. We describe a family of sampling and modeling techniques to attain production quality with light-weight neural network models using only a fraction of the data that would be necessary otherwise, and show a thorough comparison between each. Our results show that domain complexity dictates the appropriate approach to achieve high data efficiency. Finally, we distill the lessons from our experimental findings into a list of best practices for production-level NLG model development, and present them in a brief runbook. Importantly, the end products of all of the techniques are small sequence-to-sequence models (2Mb) that we can reliably deploy in production.