Portrait de Siva Reddy

Siva Reddy

Membre académique principal
siva.reddy@mila.quebec
Chaire en IA Canada-CIFAR
Professeur adjoint, McGill University, École d'informatique et Département de linguistique
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Raisonnement
Traitement du langage naturel
Site web
X

Biographie

Siva Reddy est professeur adjoint en informatique et linguistique à l’Université McGill. Ses travaux portent sur les algorithmes qui permettent aux ordinateurs de comprendre et de traiter les langues humaines. Il a fait ses études postdoctorales avec le Stanford NLP Group. Son expertise inclut la construction de symboliques linguistiques et induites et de modèles d’apprentissage profond pour le langage.

Étudiants actuels

Vaibhav Adlakha
Doctorat - McGill
Parishad BehnamGhader
Maîtrise recherche - McGill
Site web
Github
Google Scholar
Mehar Bhatia
Doctorat - McGill
Site web
Github
Google Scholar
Spandana Gella
Collaborateur·rice de recherche
Google Scholar
Gaurav Kamath
Doctorat - McGill
Amirhossein Kazemnejad
Maîtrise recherche - McGill
Github
Aditi Khandelwal
Doctorat - McGill
Superviseur⋅e principal⋅e :
Golnoosh Farnadi
Github
Google Scholar
Austin Kraft
Doctorat - McGill
Aravind Krishnan
Stagiaire de recherche - UNIVERSITÄT DES SAARLANDES
Benno Krojer
Doctorat - McGill
Site web
Google Scholar
Zichao Li
Doctorat - McGill
Co-superviseur⋅e :
Jackie Cheung
Xing Han Lu
Doctorat - McGill
mila@xinghanlu.com
Site web
Github
Google Scholar
Andreas Madsen
Doctorat - Polytechnique
Superviseur⋅e principal⋅e :
Sarath Chandar
andreas.madsen@mila.quebec
Site web
Github
Google Scholar
Nicholas Meade
Doctorat - McGill
Site web
Github
Google Scholar
Marius Mosbach
Postdoctorat - McGill
Site web
Google Scholar
Arkil Patel
Doctorat - McGill
Superviseur⋅e principal⋅e :
Dzmitry Bahdanau
Site web
Github
Google Scholar
Nooshin Soheililangroodi
Stagiaire de recherche - McGill
Karolina Ewa Stańczak
Postdoctorat - McGill
Site web
Github
Google Scholar
Ada Tur Tur
Stagiaire de recherche - McGill
Site web
Github
Google Scholar
Ivan Vulić
Collaborateur·rice de recherche - Cambridge University
Alejandra Zambrano
Stagiaire de recherche - McGill

Publications

Building a Neural Semantic Parser from a Domain Ontology
Jianpeng Cheng
Siva Reddy
Mirella Lapata
Semantic parsing is the task of converting natural language utterances into machine interpretable meaning representations which can be execu… (voir plus)ted against a real-world environment such as a database. Scaling semantic parsing to arbitrary domains faces two interrelated challenges: obtaining broad coverage training data effectively and cheaply; and developing a model that generalizes to compositional utterances and complex intentions. We address these challenges with a framework which allows to elicit training data from a domain ontology and bootstrap a neural parser which recursively builds derivations of logical forms. In our framework meaning representations are described by sequences of natural language templates, where each template corresponds to a decomposed fragment of the underlying meaning representation. Although artificial, templates can be understood and paraphrased by humans to create natural utterances, resulting in parallel triples of utterances, meaning representations, and their decompositions. These allow us to train a neural semantic parser which learns to compose rules in deriving meaning representations. We crowdsource training data on six domains, covering both single-turn utterances which exhibit rich compositionality, and sequential utterances where a complex task is procedurally performed in steps. We then develop neural semantic parsers which perform such compositional tasks. In general, our approach allows to deploy neural semantic parsers quickly and cheaply from a given domain ontology.
2018-12-25
ArXiv (prépublication)
arxiv.org
arxiv.org
Learning Typed Entailment Graphs with Global Soft Constraints
Mohammad Javad Hosseini
Nathanael Chambers
Siva Reddy
Xavier R. Holt
Shay B. Cohen
Mark Johnson
Mark Steedman
This paper presents a new method for learning typed entailment graphs from text. We extract predicate-argument structures from multiple-sour… (voir plus)ce news corpora, and compute local distributional similarity scores to learn entailments between predicates with typed arguments (e.g., person contracted disease). Previous work has used transitivity constraints to improve local decisions, but these constraints are intractable on large graphs. We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph. Learning takes only a few hours to run over 100K predicates and our results show large improvements over local similarity scores on two entailment data sets. We further show improvements over paraphrases and entailments from the Paraphrase Database, and prior state-of-the-art entailment graphs. We show that the entailment graphs improve performance in a downstream task.
2018-12-01
Transactions of the Association for Computational Linguistics (publié)
doi.org