A
Archna Bhatia
Researcher at Florida Institute for Human and Machine Cognition
Publications - 41
Citations - 684
Archna Bhatia is an academic researcher from Florida Institute for Human and Machine Cognition. The author has contributed to research in topics: Hindi & Semantics. The author has an hindex of 11, co-authored 41 publications receiving 590 citations. Previous affiliations of Archna Bhatia include Northwestern University & Carnegie Mellon University.
Papers
More filters
Proceedings ArticleDOI
A Dependency Parser for Tweets
TL;DR: A new dependency parser for English tweets, TWEEBOPARSER, which builds on several contributions: new syntactic annotations for a corpus of tweets, with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data.
Journal ArticleDOI
Closest Conjunct Agreement in Head-Final Languages
TL;DR: Data is presented from two head-final languages, Hindi and Tsez, which allow agreement with the rightmost conjunct when the verb follows the conjoined phrase, which contrasts with head-initial languages, such as Arabic, where close conjunct agreement is with the left most conjunct in clauses with VS order.
Journal ArticleDOI
Erosion of case and agreement in Hindi heritage speakers
TL;DR: The authors report on the morphosyntactic competence of Hindi heritage speakers living in the U.S and show that these speakers have representational problems with ergative, accusative and dative case morphology, albeit to different degrees.
Proceedings Article
PropBank Annotation of Multilingual Light Verb Constructions
Jena D. Hwang,Archna Bhatia,Claire Bonial,Aous Mansouri,Ashwini Vaidya,Nianwen Xue,Martha Palmer +6 more
TL;DR: This paper has addressed the task of PropBank annotation of light verb constructions, which like multi-word expressions pose special problems and has evaluated 3 different possible methods of annotation.
Proceedings Article
Augmenting English Adjective Senses with Supersenses
TL;DR: A supersense taxonomy for adjectives is developed, based on that of GermaNet, and applied to English adjectives in WordNet using human annotation and supervised classification, showing that accuracy for automatic adjective type classification is high, but synsets are considerably more difficult to classify.