Search Results for author: Dipti Sharma

Found 33 papers, 0 papers with code

Low Resource Similar Language Neural Machine Translation for Tamil-Telugu

no code implementations WMT (EMNLP) 2021 Vandan Mujadia, Dipti Sharma

This paper describes the participation of team oneNLP (LTRC, IIIT-Hyderabad) for the WMT 2021 task, similar language translation.

Machine Translation Translation

Domain Adaptation for Hindi-Telugu Machine Translation Using Domain Specific Back Translation

no code implementations RANLP 2021 Hema Ala, Vandan Mujadia, Dipti Sharma

In this paper, we present a novel approachfor domain adaptation in Neural MachineTranslation which aims to improve thetranslation quality over a new domain. Adapting new domains is a highly challeng-ing task for Neural Machine Translation onlimited data, it becomes even more diffi-cult for technical domains such as Chem-istry and Artificial Intelligence due to spe-cific terminology, etc.

Domain Adaptation Machine Translation +1

NMT based Similar Language Translation for Hindi - Marathi

no code implementations WMT (EMNLP) 2020 Vandan Mujadia, Dipti Sharma

This paper describes the participation of team F1toF6 (LTRC, IIIT-Hyderabad) for the WMT 2020 task, similar language translation.

Machine Translation POS +1

Graph Based Automatic Domain Term Extraction

no code implementations ICON 2020 Hema Ala, Dipti Sharma

We present a Graph Based Approach to automatically extract domain specific terms from technical domains like Biochemistry, Communication, Computer Science and Law.

Term Extraction

Automatic Technical Domain Identification

no code implementations ICON 2020 Hema Ala, Dipti Sharma

In this paper we present two Machine Learning algorithms namely Stochastic Gradient Descent and Multi Layer Perceptron to Identify the technical domain of given text as such text provides information about the specific domain.

Towards Handling Verb Phrase Ellipsis in English-Hindi Machine Translation

no code implementations ICON 2019 Niyati Bafna, Dipti Sharma

English-Hindi machine translation systems have difficulty interpreting verb phrase ellipsis (VPE) in English, and commit errors in translating sentences with VPE.

Machine Translation Translation

Dataset for Aspect Detection on Mobile reviews in Hindi

no code implementations ICON 2019 Pruthwik Mishra, Ayush Joshi, Dipti Sharma

In this paper we identify all aspects related to the gadget which are present on the reviews given online on various websites.

Opinion Mining

A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives

no code implementations EMNLP (DISRPT) 2021 Sahil Bakshi, Dipti Sharma

In this paper, we present a transformer based approach towards the automated identification of discourse unit segments and connectives.

Discourse Segmentation POS +3

IIIT Hyderabad Submission To WAT 2021: Efficient Multilingual NMT systems for Indian languages

no code implementations ACL (WAT) 2021 Sourav Kumar, Salil Aggarwal, Dipti Sharma

For the scope of this task, we have built multilingual systems for 20 translation directions namely English-Indic (one-to- many) and Indic-English (many-to-one).

Translation

A Simple and Effective Dependency Parser for Telugu

no code implementations ACL 2020 Sneha Nallani, Manish Shrivastava, Dipti Sharma

We present a simple and effective dependency parser for Telugu, a morphologically rich, free word order language.

Feature Engineering

A Fully Expanded Dependency Treebank for Telugu

no code implementations LREC 2020 Sneha Nallani, Manish Shrivastava, Dipti Sharma

The available Paninian dependency treebank(s) for Telugu is annotated only with inter-chunk dependency relations and not all words of a sentence are part of the parse tree.

Towards Automated Semantic Role Labelling of Hindi-English Code-Mixed Tweets

no code implementations WS 2019 Riya Pal, Dipti Sharma

We present a system for automating Semantic Role Labelling of Hindi-English code-mixed tweets.

A Dataset for Semantic Role Labelling of Hindi-English Code-Mixed Tweets

no code implementations WS 2019 Riya Pal, Dipti Sharma

We present a data set of 1460 Hindi-English code-mixed tweets consisting of 20, 949 tokens labelled with Proposition Bank labels marking their semantic roles.

Deep Neural Network based system for solving Arithmetic Word problems

no code implementations IJCNLP 2017 Purvanshi Mehta, Pruthwik Mishra, Vinayak Athavale, Manish Shrivastava, Dipti Sharma

The worldstate and the query are processed separately in two different networks and finally, the networks are merged to predict the final operation.

Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling

no code implementations WS 2017 Riyaz A. Bhat, Irshad Bhat, Dipti Sharma

We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently.

Kathaa : NLP Systems as Edge-Labeled Directed Acyclic MultiGraphs

no code implementations WS 2016 Sharada Mohanty, Nehal J Wani, Manish Srivastava, Dipti Sharma

It models NLP systems an edge-labeled Directed Acyclic MultiGraph, and lets the user use publicly co-created modules in their own NLP applications irrespective of their technical proficiency in Natural Language Processing.

Machine Translation Translation

Using lexical and Dependency Features to Disambiguate Discourse Connectives in Hindi

no code implementations LREC 2016 Rohit Jain, Himanshu Sharma, Dipti Sharma

We report that the novel dependency features introduced have a higher impact on precision, in comparison to the syntactic features previously used for this task.

Discourse Parsing Question Answering

A Proposition Bank of Urdu

no code implementations LREC 2016 Maaz Anwar, Riyaz Ahmad Bhat, Dipti Sharma, Ashwini Vaidya, Martha Palmer, Tafseer Ahmed Khan

The present size of this Propbank is around 180, 000 tokens which is double-propbanked by the two annotators for simple predicates.

A Finite-State Morphological Analyser for Sindhi

no code implementations LREC 2016 Raveesh Motlani, Francis Tyers, Dipti Sharma

Morphological analysis is a fundamental task in natural-language processing, which is used in other NLP applications such as part-of-speech tagging, syntactic parsing, information retrieval, machine translation, etc.

Information Retrieval Machine Translation +3

Towards Building Semantic Role Labeler for Indian Languages

no code implementations LREC 2016 Maaz Anwar, Dipti Sharma

Our system achieves an accuracy of 86{\%} in identifying the arguments of a verb for Hindi and 75{\%} for Urdu.

Semantic Role Labeling

Hindi to English Machine Translation: Using Effective Selection in Multi-Model SMT

no code implementations LREC 2014 Kunal Sachdeva, Rishabh Srivastava, Sambhav Jain, Dipti Sharma

In this paper, we describe a Hindi to English statistical machine translation system and improve over the baseline using multiple translation models.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.