‘Harnessing Abstractive Summarization for Fact-Checked Claim Detection’ gets accepted at COLING 2022. Paper released along with code and data. Models to be made available soon!

Invited Talk at Microsoft Research, Bangalore, India on 21st December. Excited!

Our study on Adversarial Evaluation of Quality Estimation accepted at WMT 2021. Slides and Video presentation are here!

Our study on Rating Humour Quotient in Standup Comedy accepted at EMNLP 2021. Poster and Dataset released!

Previous Next

Experience

 
 
 
 
 

Lecturer

Surrey Institute for People-Centred AI

Feb 2022 – Present Surrey, United Kingdom

Ongoing Projects:

  • Quality Estimation for Machine Translation
  • Post-editing for Machine Translation (Collaboration with the CFILT Lab, IIT Bombay)
  • Abbreviation and Acronym Identification
  • Multilingual Translation in Healthcare domain
  • Multilingual Translation of Sentiment in Tweets
  • Automatic Video Description
  • Computational Humour (Collaboration with the CFILT Lab, IIT Bombay)
  • Fake News Detection with Evidence Summarization
 
 
 
 
 

Visiting Faculty

Indian Institute of Information Technology Lucknow, India

Jan 2022 – Present Lucknow, India
I co-teach the Natural Language Processing course to the Master’s students at IIIT Lucknow, with Dr. Rudramurthy V
 
 
 
 
 

Postdoctoral Research Fellow

Centre for Translation Studies (CTS)

Jan 2021 – Jan 2022 Surrey, United Kingdom

Projects:

  • Quality Estimation for Machine Translation
  • Post-editing for Machine Translation (Collaboration with the CFILT Lab, IIT Bombay)
  • Abbreviation and Acronym Identification
  • Multilingual Translation in Healthcare domain
  • Multilingual Translation of Sentiment in Tweets
  • Automatic Video Description
  • Computational Humour (Collaboration with the CFILT Lab, IIT Bombay)
  • Fake News Detection with Evidence Summarization
 
 
 
 
 

Reviewer/Program Committee Member/Senior Program Committee Member

Various Conferences and Journals

Jan 2017 – Present

Reviewed papers in the following conferences/journals:

  • Computer Speech and Language
  • Transactions on Asian and Low-Resource Language Information Processing
  • Pattern Recognition Letters
  • AAAI Main Conference (2021, 2020)
  • AAAI Demonstrations Track (2021, 2020, 2019)
  • IJCAI Senior Program Committee Member (2020, 2021)
  • IJCAI Novel Program Committee [3-year invite] (2022, 2023, 2024)
  • ACL Rolling Reviews (2021)
  • ACL (2021, 2020, 2019, 2018)
  • EMNLP (2021, 2020, 2019)
  • CoNLL (2021, 2020, 2019)
  • EACL (2021)
  • COLING (2020)
  • LREC (2020)
  • GWC (2021, 2019, 2018)
  • IEEE SSCI (2021)
  • GLOBALEX Workshop with LREC 2018
  • SIGLEX-MWE Workshop (2020, 2019)
  • Eye Tracking Research and Applications (ETRA 2020)

ACL Professional Conduct Committee (2021 - 2023)

  • Member of the Professional Conduct Committee (PCC) establised by ACL; responsible for responding to complaints raised under the Anti-Harassment Policy.
 
 
 
 
 

Teaching Assistant

Computer Science and Engineering Department, IIT Bombay

Jan 2017 – Jul 2020 Mumbai

  • Assisted Prof. Pushpak Bhattacharyya in conducting the course on ‘Speech, Natural Language Processing and the Web’ (CS626). [Autumn 2020]

  • Assisted Prof. Kavi Arya in conducting theory and practical lab course on Embedded Systems (CS684). [Spring 2020]

  • Assisted Prof. Kavi Arya in conducting course on Software Lab (PG) (CS699). [Autumn 2019]

    Awarded TA of the Semester by Computer Science and Engineering Department.

  • Assisted Prof. Rushikesh Joshi in conducting theory course on Software Architecture (CS718). [Spring 2019]

  • Assisted Prof. R.K. Shyamsundar in conducting theory course Data Structures (CS213). [Autumn 2018]

  • Assisted Prof. Kavi Arya in conducting course on Software Lab (UG) (CS251). [Autumn 2017]

      Awarded TA of the Semester by Computer Science and Engineering Department.

  • Assisted Prof. Supratik Chakraborty in conducting theory course on Digital Logic Design (CS226). [Spring 2017]

 
 
 
 
 

Research Engineer

Center for Indian Language Technology (CFILT)

Jun 2013 – Dec 2015 Mumbai

Work Profile:

  • Sarcasm Detection using Cognitive Studies.
  • Sarcasm Understandability using Cogninitive Studies in NLP.
  • Multilingual Topic Modelling to improve Indian Language Machine Translation.
  • Working simultaneously on Hindi, Marathi, Sanskrit WordNets, IndoWordNet and Development of DiscrimiNET.
  • DiscrimiNET - a resource based disambiguation engine with the ability to disambiguate b/w word senses based on clue words. (on a pause)
  • TransChat - Machine Translation for Instant Messaging.
  • Parallel Corpora Management Workbench (PaCMan) - a machine translation aid allowing translation / validation / alignment for parallel corpora.
  • PanchaBhoota - Hierarchical Phrase based Statistical Machine Translation system for five language pairs.
  • Cognitive studies for Sentiment annotation.
  • Systems Administrator for Centre for Indian Language Technology handling / troubleshooting / maintaining both server systems, and desktop computers.

Awards

Best Paper Honourable Mention (Long Papers)

EACL 2021 Conference Apr 2021
Our work ‘Cognition-aware Cognate Detection’ was awarded the best paper honourable mention (long papers) at The 16th Conference of the European Chapter of the Association for Computational Linguistics.
See certificate

TA of the Semester

Teaching Assistant (Semester) Nov 2017 – Aug 2019

  • Awarded TA of the Semester by CSE Department, IIT Bombay for assisting Prof. Kavi Arya with Software lab (PG) (CS699)
  • Awarded TA of the Semester by CSE Department, IIT Bombay for assisting Prof. Kavi Arya with Software Foundations lab (CS251)

Best Poster Presentation (Early Researcher Category)

IITB - Monash Research Academy Aug 2016
Awarded the best poster paper presentation in the PhD Early Researchers category from amongst all students of the IITB-Monash Research Academy

CISCO Fellowship Awardee

CISCO - CSE, IIT Bombay Jul 2016 – Jul 2020
Awarded the CISCO fellowship from among all the applicants of Computer Science and Engineering Department, IIT Bombay
See certificate

Statistical Machine Translation (SMT) Competition

ICON 2014 Dec 2014
Winner of the SMT competition held at ICON 2014, Goa. We built a Heirarchical SMT system which outperformed all other systems by a significant margin.

Featured Publications

Proceedings of the Sixth Conference on Machine Translation (WMT 2021)

Current Machine Translation (MT) systems achieve very good results on a growing variety of language pairs and datasets. However, they are known to produce fluent translation outputs that can contain important meaning errors, thus undermining their reliability in practice. Quality Estimation (QE) is the task of automatically assessing the performance of MT systems at test time. Thus, in order to be useful, QE systems should be able to detect such errors. However, this ability is yet to be tested in the current evaluation practices, where QE systems are assessed only in terms of their correlation with human judgements. In this work, we bridge this gap by proposing a general methodology for adversarial testing of QE for MT. First, we show that despite a high correlation with human judgements achieved by the recent SOTA, certain types of meaning errors are still problematic for QE to detect. Second, we show that on average, the ability of a given model to discriminate between meaning-preserving and meaning-altering perturbations is predictive of its overall performance, thus potentially allowing for comparing QE systems without relying on manual quality annotation. This paper is also available on ACL Anthology.
Preprint PDF Code Dataset Slides Video
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Automatic detection of cognates helps downstream NLP tasks of Machine Translation, Cross-lingual Information Retrieval, Computational Phylogenetics and Cross-lingual Named Entity Recognition. Previous approaches for the task of cognate detection use orthographic, phonetic and semantic similarity based features sets. In this paper, we propose a novel method for enriching the feature sets, with cognitive features extracted from human readers’ gaze behaviour. We collect gaze behaviour data for a small sample of cognates and show that extracted cognitive features help the task of cognate detection. However, gaze data collection and annotation is a costly task. We use the collected gaze behaviour data to predict cognitive features for a larger sample and show that predicted cognitive features, also, significantly improve the task performance. We report improvements of 10% with the collected gaze features, and 12% using the predicted gaze features, over the previously proposed approaches. Furthermore, we release the collected gaze behaviour data along with our code and cross-lingual models. </> This paper was awarded an honourable mention during the best papers award in the long papers category at EACL 2021. </>
Preprint PDF Code Poster Slides Video

Recent Publications

(2022). Findings of the WMT 2022 Shared Task on Automatic Post-Editing. Proceedings of the 7th Conference on Machine Translation (WMT 2022) at EMNLP.

PDF Code Dataset Slides

(2022). Findings of the WMT 2022 Shared Task on Quality Estimation. Proceedings of the 7th Conference on Machine Translation (WMT 2022) at EMNLP.

PDF Dataset Slides Source Document

(2022). Utilizing Weak Supervision to Create S3D: A Sarcasm Annotated Dataset. Proceedings of the 5th workshop on NLP+CSS at EMNLP 2022 in Abu Dhabi.

PDF Code Dataset Slides

(2022). Harnessing Abstractive Summarization for Fact-Checked Claim Detection. Proceedings of The 29th International Conference on Computational Linguistics (COLING 2022).

Preprint PDF Code Dataset Slides Video

(2022). HiNER: A Large Hindi Named Entity Recognition Dataset. Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022).

Preprint PDF Code Dataset Poster Video

See all publications

Recent & Upcoming Talks

This was a poster I presented at Convergence 2023. I discuss the work done, the collaborations, our NLP Cafe and publicly available …
Feb 4, 2023 12:00 PM Surrey, United Kingdom (Online)
Poster

The workshop explored questions on the lines of how should knowledge about neural machine translation be disseminated in the …
Feb 4, 2023 12:00 PM Surrey, United Kingdom (Online)
Slides

Presented as a co-chair on the panel, ‘Natural Language Processing Augmenting Translation and Interpreting’ at Convergence …
Feb 4, 2023 12:00 AM University of Surrey, United Kingdom
Slides

In this talk, I discuss the interdisciplinary area cognitive NLP. I discuss the various intersections which give it a unique blend and …
Nov 25, 2022 12:00 AM University of Surrey, United Kingdom
Slides

In this talk, I discuss the Quality Estimation (QE) for Machine Translation (MT). I discuss the basics of the QE task, and the QE …
Nov 15, 2022 12:00 AM University of Surrey, United Kingdom (Online)
Slides
See all talks

Recent Posts

There are many ways using which developers get updates from Python. Some use the ‘knockknock’ library, some use the …
6 min read python, notifications, telegram, hacks

Contact