S
Siva Reddy
Researcher at University of Cambridge
Publications - 82
Citations - 4168
Siva Reddy is an academic researcher from University of Cambridge. The author has contributed to research in topics: Parsing & Natural language. The author has an hindex of 25, co-authored 82 publications receiving 3321 citations. Previous affiliations of Siva Reddy include McGill University & International Institute of Information Technology, Hyderabad.
Papers
More filters
Journal ArticleDOI
Transforming Dependency Structures to Logical Forms for Semantic Parsing
Siva Reddy,Oscar Täckström,Michael Collins,Tom Kwiatkowski,Dipanjan Das,Mark Steedman,Mirella Lapata +6 more
TL;DR: This work introduces a robust system based on the lambda calculus for deriving neo-Davidsonian logical forms from dependency trees and obtains the strongest result to date on Free917 and competitive results on WebQuestions.
Posted Content
Question Answering on Freebase via Relation Extraction and Textual Evidence
TL;DR: This article used a neural network based relation extractor to retrieve candidate answers from Freebase, and then infer over Wikipedia to validate these answers, achieving an F_1 of 53.3% on the WebQuestions question answering dataset.
Proceedings Article
An Empirical Study on Compositionality in Compound Nouns
TL;DR: This paper collects and analyse the compositionality judgments for a range of compound nouns using Mechanical Turk, and evaluates two different types of distributional models for compositionality detection – constituent based models and composition function based models.
Proceedings ArticleDOI
Learning to Paraphrase for Question Answering
TL;DR: The authors use paraphrases as a means of capturing knowledge and present a general framework which learns felicitous paraphrasing for various QA tasks using question-answer pairs as a supervision signal.
Proceedings ArticleDOI
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks
TL;DR: Evaluation results on \spades fill-in-the-blank question answering dataset show that exploiting universal schema for question answering is better than using either a KB or text alone.