Dependency Parsing in Bangla

2013 ◽  
pp. 155-168 ◽  
Author(s):  
Utpal Garain ◽  
Sankar De
Keyword(s):  
Test Data ◽  
Word Order ◽  
Dependency Parsing ◽  
Order Problem ◽  
Simple Sentences ◽  
Free Word

A grammar-driven dependency parsing has been attempted for Bangla (Bengali). The free-word order nature of the language makes the development of an accurate parser very difficult. The Paninian grammatical model has been used to tackle the free-word order problem. The approach is to simplify complex and compound sentences and then to parse simple sentences by satisfying the Karaka demands of the Demand Groups (Verb Groups). Finally, parsed structures are rejoined with appropriate links and Karaka labels. The parser has been trained with a Treebank of 1000 annotated sentences and then evaluated with un-annotated test data of 150 sentences. The evaluation shows that the proposed approach achieves 90.32% and 79.81% accuracies for unlabeled and labeled attachments, respectively.

scholarly journals Dependency Parsing in Bangla

2014 ◽  
pp. 1536-1549
Author(s):  
Utpal Garain ◽  
Sankar De
Keyword(s):  
Test Data ◽  
Word Order ◽  
Dependency Parsing ◽  
Order Problem ◽  
Simple Sentences ◽  
Free Word

A grammar-driven dependency parsing has been attempted for Bangla (Bengali). The free-word order nature of the language makes the development of an accurate parser very difficult. The Paninian grammatical model has been used to tackle the free-word order problem. The approach is to simplify complex and compound sentences and then to parse simple sentences by satisfying the Karaka demands of the Demand Groups (Verb Groups). Finally, parsed structures are rejoined with appropriate links and Karaka labels. The parser has been trained with a Treebank of 1000 annotated sentences and then evaluated with un-annotated test data of 150 sentences. The evaluation shows that the proposed approach achieves 90.32% and 79.81% accuracies for unlabeled and labeled attachments, respectively.

Analyzing and Integrating Dependency Parsers

2011 ◽  
Vol 37 (1) ◽  
pp. 197-230 ◽  
Author(s):  
Ryan McDonald ◽  
Joakim Nivre
Keyword(s):  
Word Order ◽  
Integrated System ◽  
Data Driven ◽  
Dependency Parsing ◽  
Learning Framework ◽  
The Past ◽  
Complex Phenomena ◽  
Free Word

There has been a rapid increase in the volume of research on data-driven dependency parsers in the past five years. This increase has been driven by the availability of treebanks in a wide variety of languages—due in large part to the CoNLL shared tasks—as well as the straightforward mechanisms by which dependency theories of syntax can encode complex phenomena in free word order languages. In this article, our aim is to take a step back and analyze the progress that has been made through an analysis of the two predominant paradigms for data-driven dependency parsing, which are often called graph-based and transition-based dependency parsing. Our analysis covers both theoretical and empirical aspects and sheds light on the kinds of errors each type of parser makes and how they relate to theoretical expectations. Using these observations, we present an integrated system based on a stacking learning framework and show that such a system can learn to overcome the shortcomings of each non-integrated system.

Pragmatics for Latin

2019 ◽  
Author(s):  
A. M. Devine ◽  
Laurence D. Stephens
Keyword(s):  
Noun Phrase ◽  
Word Order ◽  
Information Structure ◽  
Descriptive Analysis ◽  
Informational Content ◽  
Compositional Process ◽  
Association With Focus ◽  
Narrow Scope ◽  
Order Language ◽  
Free Word

Latin is often described as a free word order language, but in general each word order encodes a particular information structure: in that sense, each word order has a different meaning. This book provides a descriptive analysis of Latin information structure based on detailed philological evidence and elaborates a syntax-pragmatics interface that formalizes the informational content of the various different word orders. The book covers a wide ranges of issues including broad scope focus, narrow scope focus, double focus, topicalization, tails, focus alternates, association with focus, scrambling, informational structure inside the noun phrase and hyperbaton (discontinuous constituency). Using a slightly adjusted version of the structured meanings theory, the book shows how the pragmatic meanings matching the different word orders arise naturally and spontaneously out of the compositional process as an integral part of a single semantic derivation covering denotational and informational meaning at one and the same time.

scholarly journals Word order in Latin locative constructions: a corpus study in Caesar’s De bello gallico

2011 ◽  
Vol 64 (2) ◽  
Author(s):  
Stavros Skopeteas
Keyword(s):  
Word Order ◽  
Information Structure ◽  
Motion Verbs ◽  
Structural Domains ◽  
Corpus Study ◽  
First Order ◽  
Order Language ◽  
Free Word

AbstractClassical Latin is a free word order language, i.e., the order of the constituents is determined by information structure rather than by syntactic rules. This article presents a corpus study on the word order of locative constructions and shows that the choice between a Theme-first and a Locative-first order is influenced by the discourse status of the referents. Furthermore, the corpus findings reveal a striking impact of the syntactic construction: complements of motion verbs do not have the same ordering preferences with complements of static verbs and adjuncts. This finding supports the view that the influence of discourse status on word order is indirect, i.e., it is mediated by information structural domains.

Sign in / Sign up

Export Citation Format

Share Document