Výsledky vyhledávání - "Vladimir Karpukhin"

Joint Verification and Reranking for Open Fact Checking Over Tables

Autor: Vladimir Karpukhin, Barlas Oguz, Wen-tau Yih, Sebastian Riedel, Michael Sejr Schlichtkrull, Michael Lewis

Publikováno v: ACL/IJCNLP (1)

Structured information is an important knowledge source for automatic verification of factual claims. Nevertheless, the majority of existing research into this task has focused on textual data, and the few recent inquiries into structured data have b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d07e1db46ca0ea66fab7860f122e26f0
https://doi.org/10.18653/v1/2021.acl-long.529

Zobrazit plný text záznamu

Dense Passage Retrieval for Open-Domain Question Answering

Autor: Sergey Edunov, Wen-tau Yih, Danqi Chen, Vladimir Karpukhin, Sewon Min, Barlas Oguz, Patrick S. H. Lewis, Ledell Wu

Publikováno v: EMNLP (1)

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4586e4a9f0e9488de8d1bb2d039be7a3

Zobrazit plný text záznamu

KILT: a Benchmark for Knowledge Intensive Language Tasks

Autor: Patrick S. H. Lewis, Nicola De Cao, Aleksandra Piktus, Yacine Jernite, Jean Maillard, Angela Fan, James Thorne, Vassilis Plachouras, Vladimir Karpukhin, Tim Rocktäschel, Sebastian Riedel, Majid Yazdani, Fabio Petroni

Publikováno v: NAACL-HLT

Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::858c48f1c93a18c525f01a73ceda1250

Zobrazit plný text záznamu

Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation

Autor: Marjan Ghazvininejad, Vladimir Karpukhin, Jacob Eisenstein, Omer Levy

Publikováno v: W-NUT@EMNLP

We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by applying subword models such as byte-pair encoding (BPE) and character-leve

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d02ba71a620a9e2a185a0ce86cb1d16
https://doi.org/10.18653/v1/d19-5506

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání