Alert button
Picture for Stan Peshterliev

Stan Peshterliev

Alert button

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

Oct 13, 2021
Xilun Chen, Kushal Lakhotia, Barlas Oğuz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, Wen-tau Yih

Figure 1 for Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Figure 2 for Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Figure 3 for Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Figure 4 for Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Viaarxiv icon

Decoupled Transformer for Scalable Inference in Open-domain Question Answering

Aug 05, 2021
Haytham ElFadeel, Stan Peshterliev

Figure 1 for Decoupled Transformer for Scalable Inference in Open-domain Question Answering
Figure 2 for Decoupled Transformer for Scalable Inference in Open-domain Question Answering
Figure 3 for Decoupled Transformer for Scalable Inference in Open-domain Question Answering
Figure 4 for Decoupled Transformer for Scalable Inference in Open-domain Question Answering
Viaarxiv icon

Robustly Optimized and Distilled Training for Natural Language Understanding

Mar 16, 2021
Haytham ElFadeel, Stan Peshterliev

Figure 1 for Robustly Optimized and Distilled Training for Natural Language Understanding
Figure 2 for Robustly Optimized and Distilled Training for Natural Language Understanding
Figure 3 for Robustly Optimized and Distilled Training for Natural Language Understanding
Figure 4 for Robustly Optimized and Distilled Training for Natural Language Understanding
Viaarxiv icon

Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering

Mar 11, 2021
Stan Peshterliev, Barlas Oguz, Debojeet Chatterjee, Hakan Inan, Vikas Bhardwaj

Figure 1 for Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
Figure 2 for Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
Figure 3 for Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
Figure 4 for Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
Viaarxiv icon

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Jan 01, 2021
Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih

Figure 1 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 2 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 3 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 4 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Viaarxiv icon

Unified Open-Domain Question Answering with Structured and Unstructured Knowledge

Dec 29, 2020
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih

Figure 1 for Unified Open-Domain Question Answering with Structured and Unstructured Knowledge
Figure 2 for Unified Open-Domain Question Answering with Structured and Unstructured Knowledge
Figure 3 for Unified Open-Domain Question Answering with Structured and Unstructured Knowledge
Figure 4 for Unified Open-Domain Question Answering with Structured and Unstructured Knowledge
Viaarxiv icon