• Publications
  • Influence
English to Indian Languages Machine Transliteration System at NEWS 2010
TLDR
Non-Standard Run-2 for Bengali has achieved the highest score among all the submitted runs and is ranked as the 5th and 6th among all submitted Runs.
English to Hindi Machine Transliteration System at NEWS 2009
TLDR
This paper reports about the work in the NEWS 2009 Machine Transliteration Shared Task held as part of ACL-IJCNLP 2009, where the modified joint source-channel model has been used along with a number of alternatives.
Automatic Extraction of Complex Predicates in Bengali
This paper presents the automatic extraction of Complex Predicates (CPs) in Bengali with a special focus on compound verbs (Verb + Verb) and conjunct verbs (Noun /Adjective + Verb). The lexical
Shared Task System Description: Measuring the Compositionality of Bigrams using Statistical Methodologies
TLDR
The experiments deal with various collocation based statistical approaches to compute the relative compositionality of three types of bigram phrases (Adjective-Noun, Verbsubject and Verb-object combinations) and reasonable results have been obtained in terms of average point difference and coarse precision.
Bengali, Hindi and Telugu to English Ad-hoc Bilingual Task
TLDR
This paper presents the experiments carried out at Jadavpur University as part of the participation in the CLEF 2007 ad-hoc bilingual task, which considered Bengali, Hindi and Telugu as query languages for the retrieval from English document collection.
Development and suitability of Indian languages speech database for building watson based ASR system
TLDR
It is demonstrated that these corpora for building large vocabulary speech recognition systems using WATSON Toolkit can be reduced to a varied degree for various phonemes by comparing the similarity among phonems of different languages.
Measuring the compositionality of bigrams using statistical methodologies: shared task system description
TLDR
The experiments deal with various collocation based statistical approaches to compute the relative compositionality of three types of bigram phrases (Adjective-Noun, Verb-subject and Verb-object combinations) and reasonable results have been obtained in terms of average point difference and coarse precision.
Table of Contents (linear) Maps of the Impossible: Capturing Semantic Anomalies in Distributional Space Shared Task System Description: Frustratingly Hard Compositionality Prediction Shared Task
TLDR
This has been the first attempt in the community to offer a dataset and a shared task that allows to explicitly evaluate the models of graded compositionality for phrases per se that occur in three types of grammatical relations: adjective-noun pairs, subject-verb and verb-object pairs in English and German.
Shared Task Organizing Committee -transliteration Mining: Whitepaper of News 2010 Shared Task on Transliteration Generation Transliteration Generation and Mining with Limited Training Resources
TLDR
The purpose of the NEWS workshop is to bring together researchers across the world interested in identification, analysis, extraction, mining and transformation of named entities in monolingual or multilingual natural language text, and this year two shared tasks were organized: one on Machine Transliteration Generation, and another on MachineTransliteration Mining.
JU_CSE_GREC10: Named Entity Generation at GREC 2010
TLDR
This paper presents the experiments carried out at Jadavpur University as part of the participation in the GREC Named Entity Generation Challenge 2010, and the inclusion of discourse level features has improved the performance of the system.
...
1
2
...