N
Nikesh Garera
Researcher at Walmart
Publications - 45
Citations - 686
Nikesh Garera is an academic researcher from Walmart. The author has contributed to research in topics: Computer science & Product classification. The author has an hindex of 14, co-authored 34 publications receiving 662 citations. Previous affiliations of Nikesh Garera include Walmart Labs & Johns Hopkins University.
Papers
More filters
Journal ArticleDOI
Entity extraction, linking, classification, and tagging for social media: a wikipedia-based approach
Abhishek Gattani,Digvijay Singh Lamba,Nikesh Garera,Mitul Tiwari,Xiaoyong Chai,Sanjib Das,Sri Subramaniam,Anand Rajaraman,Venky Harinarayan,AnHai Doan +9 more
TL;DR: This paper describes in depth an end-to-end industrial system that solves these problems for social data and uses a Wikipedia-based global "real-time" knowledge base that is well suited for socialData.
Proceedings ArticleDOI
Modeling Latent Biographic Attributes in Conversational Genres
Nikesh Garera,David Yarowsky +1 more
TL;DR: A novel partner-sensitive model for extracting biographic attributes in conversations, and a rich variety of novel sociolinguistic and discourse-based features, including mean utterance length, passive/active usage, percentage domination of the conversation, speaking rate and filler word usage are presented.
Proceedings ArticleDOI
Improving Translation Lexicon Induction from Monolingual Corpora via Dependency Contexts and Part-of-Speech Equivalences
TL;DR: A dependency-based context model that incorporates long-range dependencies, variable context sizes, and reordering provides a 16% relative improvement over the baseline approach that uses a fixed context window of adjacent words.
Patent
Including hyperlinks in a document
TL;DR: In this paper, a document is received via a communications interface and an entity pair is determined by a processor, the entity pair includes a concept included in a concept taxonomy and a textual representation included in the document.
Proceedings ArticleDOI
Cross-Document Coreference Resolution: A Key Technology for Learning by Reading
James Mayfield,David Alexander,Bonnie J. Dorr,Jason Eisner,Tamer Elsayed,Tim Finin,Marjorie Freedman,Nikesh Garera,Paul McNamee,Saif M. Mohammad,Douglas W. Oard,Christine D. Piatko,Asad Sayeed,Zareen Syed,Ralph Weischedel,Tan Xu,David Yarowsky +16 more
TL;DR: Use of a wide range of features, both those that capture evidence for entity merging and those that argue against merging, can significantly improve machine learning-based cross-document coreference resolution.