Noun Group and Verb Group Identification for Hindi

Proceedings of COLING 2012: Technical Papers, pages 2491–2506, COLING 2012, Mumbai, December 2012. Noun Group and Verb Group Identification for Hindi Smriti Singh1, Om P. Damani2, Vaijayanthi M. Sarma2 (1) Insideview Technologies (India) Pvt. Ltd., Hyderabad (2) Indian Institute of Technology Bombay, Mumbai, India smriti.singh@insideview.com, damani@cse.iitb.ac.in, vsarma@iitb.ac.in ABSTRACT We present algorithms for identifying Hindi Noun Groups and Verb Groups in a given text by using morphotactical constraints and sequencing that apply to the constituents of these groups. We provide a detailed repertoire of the grammatical categories and their markers and an account of their arrangement. The main motivation behind this work on word group identification is to improve the Hindi POS Tagger’s performance by including strictly contextual rules. Our experiments show that the introduction of group identification rules results in improved accuracy of the tagger and in the resolution of several POS ambiguities. The analysis and implementation methods discussed here can be applied straightforwardly to other Indian languages. The linguistic features exploited here are drawn from a range of well-understood grammatical features and are not peculiar to Hindi alone. KEYWORDS : POS tagging, chunking, noun group, verb group. 2491 1 Introduction Chunking (local word grouping) is often employed to reduce the computational effort at the level of parsing by assigning partial structure to a sentence. A typical chunk, as defined by Abney (1994:257) consists of a single content word surrounded by a constellation of function words, matching a fixed template. Chunks, in computational terms are considered the truncated versions of typical phrase-structure grammar phrases that do not include arguments or adjuncts (Grover and Tobin 2006). For Abney, chunks are connected subgraphs of a sentence’s parse tree. They are defined in terms of major heads and have their own syntactic structure that can be represented in the form of a tree. However a chunk does not include all the descendants of the root node that may be present in the parse-tree of the complete sentence. It only represents the root node (the head of the chunk) and its modifiers (auxiliaries in the case of verbs). Two heads of the same lexical category are not allowed inside a chunk. Consequently, ‘Ram’s son’ in English and ‘rām kā betā’ in Hindi will have two chunks each [Ram’s] [son] and [raam kā] [betā]. Similarly, verb complements are not grouped inside the verb chunk; they form separate chunks. The English sentence ‘The bald man was sitting on his suitcase,’ can be grouped into three chunks – [The bald man], [was sitting] and [on his suitcase]. The parallel sentence in Hindi ‘ganjā ādmī apne sandūk pe baithā thā’ will have the chunks [ganjā ādmī] [apne sandūk pe] [baithā thā] in that order. The task of the chunker is to divide a sentence into chunks leaving out some words that are not grouped into any of the identified chunks. The output of the chunker is a shallow syntactic analysis employing simple, context sensitive grammars to detect the boundaries of syntactic groups such as a Noun Group (NG) …

Content truncated to 500 words