Nitesh Surtani

IIIT Hyderabad, Language Technologies Research Centre (LTRC), Graduate Student

Followers

Following

Public Views

Supervisors: Dr. Soma Paul

less

Aydin Han

Koç University

Elisabetta Jezek

Università degli studi di Pavia

Philippe Kruchten

University of British Columbia

Tony Veale

University College Dublin

Keith Hall

Brown University

Piek Vossen

Vrije Universiteit Amsterdam

Mariona Taulé

Universitat de Barcelona

Preslav Nakov

Qatar Computing Research Institute

Shu-Kai Hsieh

National Taiwan University

Rada Mihalcea

InterestsView All (7)

Uploads

Papers by Nitesh Surtani

A Corpus-Driven Co-occurrence Based Probabilistic Model for Noun Compound Paraphrasing

SemEval-2013, International Workshop on Semantic Evaluation, Atlanta, Georgia, Jun 14, 2013

This paper presents a system for automatically generating a set of plausible paraphrases for a gi... more This paper presents a system for automatically generating a set of plausible paraphrases for a given noun compound and rank them in de-creasing order of their usage represented by the confidence value provided by the human annotators. Our system implements a corpus-driven probabilistic co-occurrence based model for predicting the paraphrases, that uses a seed list of paraphrases extracted from corpus to predict other paraphrases based on their co-occurrences. The corpus study reveals that the prepositional paraphrases for the noun compounds are quite frequent and well covered but the verb paraphrases, on the other hand, are scarce, revealing the unsuitability of the model for standalone corpus-driven approach. Therefore, to predict other paraphrases, we adopt a two-fold approach: (i) Prediction based on Verb-Verb co-occurrences, in case the seed paraphrases are greater than threshold; and (ii) Prediction
based on Semantic Relation of NC, otherwise. The system achieves a considerable score of
0.23 for the isomorphic system while maintaining a score of 0.26 for the non-isomorphic system.

Download

Issues with the Unergative/Unaccusative Classification of the Intransitive Verbs

The paper abandons a strict two-way sub-classification of intransitive verbs into unaccuasative a... more The paper abandons a strict two-way sub-classification of intransitive verbs into unaccuasative and unergative for Hindi and proposes a distribution plotting of the same in a diffusion chart. The diagnostics tests that Bhatt (2003) applied on Hindi data are ranked for their efficiency of attributing correct sub-class to verbs. The diffusion chart shows that a tripartite classification handles the issue of classification of intransitive verbs in a better manner than the classical binary approach. The tripartite classification is as follows: (1) Verbs that take animate subject and are compatible with adverb of volitionality; (2) Verbs that take animate subject but are not compatible with adverb of volitionality; and (3) Verbs that take inanimate subject. The classification is of immense advantage for various NLP tasks such as machine translation, natural language generation.

Download

Automatic Annotation of Genitives in Hindi Treebank

24th International Conference on Computational Linguistics (COLING 2012)

Noun with genitive marker in Indo-Aryan language can variously be a child of a noun, a verb or a ... more Noun with genitive marker in Indo-Aryan language can variously be a child of a noun, a verb or a complex predicate, thus making it an important parsing issue. In this paper, we examine genitive data of Hindi and aim to automatically determine the attachment and relational label of the same in a dependency framework. We implement two approaches: a rule based approach and a statistical approach. The rule based approach produces promising results but fails to handle certain constructions because of its greedy selection. The statistical approach overcomes this by using a single candidate approach that considers all the possible candidates for the head and chooses the most probable candidate among them. Both approaches are applied on controlled and open environment data. A Controlled environment refers to the situation when the relational labels are attested to the input data except for the genitive data; while open environment refers to cases in which the input is only POS tagged and chunked. The rule based and statistical systems produce a high accuracy of 95% and 97% respectively for attachment and perform considerably well for labeling in controlled environment but poorly in open environment.

Genitives in Hindi Treebank: An Attempt for Automatic Annotation

The 11th International Workshop on Treebanks and Linguistic Theories (TLT11 2012)

Building syntactic Treebank manually is a time consuming and human labor intensive task. The corr... more Building syntactic Treebank manually is a time consuming and human labor intensive task. The correctness of annotated data is very important because this resource can be used for developing important NLP tools such as syntactic parsers. In this paper, we examine genitive construction in Hindi Treebank with a view of developing a set of rules for automatic annotation of genitive data in Hindi Treebank. The rules perform quite well producing an overall 89% accuracy for right attachment of genitive noun with its head and correct labeling for the attachment.

Automatic Tripartite Classification of Intransitive Verbs

Proceedings of 26 th Pacific Asia Conference on Language Information and Computation, Bali, Indonesia

In this paper, we develop a multi-class SVM classifier based model that confirms a tripartite cla... more In this paper, we develop a multi-class SVM classifier based model that confirms a tripartite classification of intransitive verbs of Hindi to be a more suitable model of classification than the classical binary unaccusative/unergative classification. We rank the unaccusative diagnostic tests for Hindi based on their authenticity in attesting an intransitive verb under unaccussative class. We show that the use of the ranking score in the feature of the classifier improves the efficiency of the classification model even with a small amount of data. The empirical result illustrates the fact that judicious use of linguistic knowledge builds a better classification model than the one that is purely statistical.

Issues with the Unergative/Unaccusative Classification of the Intransitive Verbs

Proceedings of 4 th International Conference on Asian Language Processing (IALP), Penang, Malaysia

A Corpus-Driven Co-occurrence Based Probabilistic Model for Noun Compound Paraphrasing

SemEval-2013, International Workshop on Semantic Evaluation, Atlanta, Georgia, Jun 14, 2013

Download

Issues with the Unergative/Unaccusative Classification of the Intransitive Verbs

Download

Automatic Annotation of Genitives in Hindi Treebank

24th International Conference on Computational Linguistics (COLING 2012)

Genitives in Hindi Treebank: An Attempt for Automatic Annotation

The 11th International Workshop on Treebanks and Linguistic Theories (TLT11 2012)

Automatic Tripartite Classification of Intransitive Verbs

Proceedings of 26 th Pacific Asia Conference on Language Information and Computation, Bali, Indonesia

Issues with the Unergative/Unaccusative Classification of the Intransitive Verbs

Proceedings of 4 th International Conference on Asian Language Processing (IALP), Penang, Malaysia

Nitesh Surtani

Uploads

Papers by Nitesh Surtani

Log In