Amba Kulkarni


2024

pdf bib
Word Sense Alignment of Sanskrit Lexica
Dhaval K Patel | Amba Kulkarni
Proceedings of the 7th International Sanskrit Computational Linguistics Symposium

pdf
Inter Sentential Discourse Relations
Saee Vaze | Amba Kulkarni
Proceedings of the 7th International Sanskrit Computational Linguistics Symposium

pdf
Anuprāsa Identifier and Classifier: A computational tool to analyze Sanskrit figure of sound
Amruta Vilas Barbadikar | Amba Kulkarni
Proceedings of the 7th International Sanskrit Computational Linguistics Symposium

pdf
START: Sanskrit Teaching; Annotation; and Research Tool – Bridging Tradition and Technology in Scholarly Exploration
Anil Kumar | Amba Kulkarni | Nakka Shailaj
Proceedings of the 7th International Sanskrit Computational Linguistics Symposium

2023

pdf bib
Proceedings of the Computational Sanskrit & Digital Humanities: Selected papers presented at the 18th World Sanskrit Conference
Amba Kulkarni | Oliver Hellwig
Proceedings of the Computational Sanskrit & Digital Humanities: Selected papers presented at the 18th World Sanskrit Conference

pdf
Validation and Normalization of DCS corpus and Development of the Sanskrit Heritage Engine’s Segmenter
Krishnan Sriram | Amba Kulkarni | Gérard Huet
Proceedings of the Computational Sanskrit & Digital Humanities: Selected papers presented at the 18th World Sanskrit Conference

pdf
Disambiguation of Instrumental, Dative and Ablative Case suffixes in Sanskrit
Malay Maity | Sanjeev Panchal | Amba Kulkarni
Proceedings of the Computational Sanskrit & Digital Humanities: Selected papers presented at the 18th World Sanskrit Conference

pdf
DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit
Jivnesh Sandhan | Yaswanth Narsupalli | Sreevatsa Muppirala | Sriram Krishnan | Pavankumar Satuluri | Amba Kulkarni | Pawan Goyal
Findings of the Association for Computational Linguistics: EMNLP 2023

Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound’s components is crucial for deciphering its meaning. Earlier approaches in Sanskrit have focused on binary compounds and neglected the multi-component compound setting. This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them. To the best of our knowledge, this is the first attempt in the field of lexical semantics to propose this task. We present 2 newly annotated datasets including an out-of-domain dataset for this task. We also benchmark these datasets by exploring the efficacy of the standard problem formulations such as nested named entity recognition, constituency parsing and seq2seq, etc. We present a novel framework named DepNeCTI: Dependency-based Nested Compound Type Identifier that surpasses the performance of the best baseline with an average absolute improvement of 13.1 points F1-score in terms of Labeled Span Score (LSS) and a 5-fold enhancement in inference efficiency. In line with the previous findings in the binary Sanskrit compound identification task, context provides benefits for the NeCTI task. The codebase and datasets are publicly available at: https://github.com/yaswanth-iitkgp/DepNeCTI

2021

pdf bib
Parsing Subordinate Clauses in Telugu using Rule-based Dependency Parser
P Sangeetha | Parameswari Krishnamurthy | Amba Kulkarni
Proceedings of the First Workshop on Parsing and its Applications for Indian Languages

Parsing has been gaining popularity in recent years and attracted the interest of NLP researchers around the world. It is challenging when the language under study is a free-word order language that allows ellipsis like Telugu. In this paper, an attempt is made to parse subordinate clauses especially, non-finite verb clauses and relative clauses in Telugu which are highly productive and constitute a large chunk in parsing tasks. This study adopts a knowledge-driven approach to parse subordinate structures using linguistic cues as rules. Challenges faced in parsing ambiguous structures are elaborated alongside providing enhanced tags to handle them. Results are encouraging and this parser proves to be efficient for Telugu.

2020

pdf
Dependency Relations for Sanskrit Parsing and Treebank
Amba Kulkarni | Pavankumar Satuluri | Sanjeev Panchal | Malay Maity | Amruta Malvade
Proceedings of the 19th International Workshop on Treebanks and Linguistic Theories

pdf
Free Word Order in Sanskrit and Well-nestedness
Sanal Vikram | Amba Kulkarni
Proceedings of the 17th International Conference on Natural Language Processing (ICON)

The common wisdom about Sanskrit is that it is free word order language. This word order poses challenges such as handling non-projectivity in parsing. The earlier works on the word order of Sanskrit have shown that there are syntactic structures in Sanskrit which cannot be covered under even the non-planarity. In this paper, we study these structures further to investigate if they can fall under well-nestedness or not. A small manually tagged corpus of the verses of Śrīmad-Bhagavad-Gītā was considered for this study. It was noticed that there are as many well-nested trees as there are ill-nested ones. From the linguistic point of view, we could get a list of relations that are involved in the planarity violations. All these relations had one thing in common - that they have unilateral expectancy. It was this loose binding, as against the mutual expectancy with certain other relations, that allowed them to cross the phrasal boundaries.

2019

pdf
Sanskrit Segmentation revisited
Sriram Krishnan | Amba Kulkarni
Proceedings of the 16th International Conference on Natural Language Processing

Computationally analyzing Sanskrit texts requires proper segmentation in the initial stages. There have been various tools developed for Sanskrit text segmentation. Of these, Gérard Huet’s Reader in the Sanskrit Heritage Engine analyzes the input text and segments it based on the word parameters - phases like iic, ifc, Pr, Subst, etc., and sandhi (or transition) that takes place at the end of a word with the initial part of the next word. And it enlists all the possible solutions differentiating them with the help of the phases. The phases and their analyses have their use in the domain of sentential parsers. In segmentation, though, they are not used beyond deciding whether the words formed with the phases are morphologically valid. This paper tries to modify the above segmenter by ignoring the phase details (except for a few cases), and also proposes a probability function to prioritize the list of solutions to bring up the most valid solutions at the top.

pdf bib
Sanskrit Sentence Generator
Amba Kulkarni | Madhusoodana Pai
Proceedings of the 6th International Sanskrit Computational Linguistics Symposium

pdf bib
Dependency Parser for Sanskrit Verses
Amba Kulkarni | Sanal Vikram | Sriram K
Proceedings of the 6th International Sanskrit Computational Linguistics Symposium

pdf
Pāṇinian Syntactico-Semantic Relation Labels
Amba Kulkarni | Dipti Sharma
Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)

2014

pdf
Segmentation of Navya-Nyāya Expressions
Arjuna S. R | Amba Kulkarni
Proceedings of the 11th International Conference on Natural Language Processing

pdf
Converting Phrase Structures to Dependency Structures in Sanskrit
Pawan Goyal | Amba Kulkarni
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf
Sanskrit Linguistics Web Services
Gérard Huet | Amba Kulkarni
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations

2013

pdf
A Deterministic Dependency Parser with Dynamic Programming for Sanskrit
Amba Kulkarni
Proceedings of the Second International Conference on Dependency Linguistics (DepLing 2013)

2012

pdf bib
Discourse Analysis of Sanskrit texts
Amba Kulkarni | Monali Das
Proceedings of the Workshop on Advances in Discourse Analysis and its Computational Aspects

pdf
A Distributed Platform for Sanskrit Processing
Pawan Goyal | Gérard Huet | Amba Kulkarni | Peter Scharf | Ralph Bunker
Proceedings of COLING 2012

pdf
Semantic Processing of Compounds in Indian Languages
Amba Kulkarni | Soma Paul | Malhar Kulkarni | Anil Kumar | Nitesh Surtani
Proceedings of COLING 2012

2009

pdf bib
Anusaaraka: An accessor cum machine translator
Amba Kulkarni
Proceedings of the First International Workshop on Free/Open-Source Rule-Based Machine Translation

2002

pdf bib
AnnCorra: Building Tree-banks in Indian Languages
Akshar Bharati | Rajeev Sangal | Vineet Chaitanya | Amba Kulkarni | Dipti Misra Sharma | K.V. Ramakrishnamacharyulu
COLING-02: The 3rd Workshop on Asian Language Resources and International Standardization