I am a PhD student at the ILCC, University of Edinburgh jointly supervised by Prof. Frank Keller and Prof. Mirella Lapata. I am working on action recognition in images and visual sense disambiguation by integrating language and vision techniques.

Prior to this I graduated from Dept. of Computing and Information systems, University of Melbourne and worked under the supervision of Dr. Tim Baldwin and Dr. Paul Cook. I worked on Word Senses and Word Usage patterns in Social Media for my masters thesis. I was funded by the Erasmus Mundus LCT for my masters.

Prior to my masters I have 18 months of industry experience as a Sr. Technical Associate in Global Rates and Currencies Technology (GRCT) division at Bank of America Merrill Lynch, India and a Bachelors with honors in Data Mining from IIIT Hyderabad.

From July 2016 - Sep 2016 I interned at Microsoft Research Redmond with Margaret Mitchell.

Quick Links: CV, Google Scholar Profile, Twitter

Academic Activities
Organizer: ACL 2017, Student Research Workshop
PC Member: Social NLP 2017, Ethics in NLP 2017, Social NLP 2016
Reviewer: *SEM 2013, ESSLLI 2015, EMNLP 2015, ESSLLI 2016, *SEM 2016, EMNLP 2016, WiML 2016 , EMNLP 2017, EACL 2017, *SEM 2017
Sub Reviewer: NODALIDA 2015, IJCAI 2016



Spandana Gella, Rico Sennrich, Frank Keller and Mirella Lapata. Image Pivoting for Learning Multilingual Multimodal Representations. (To appear) In the Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP, 2017). Copenhagen, Denmark. [Slides]

Spandana Gella, Frank Keller, Mirella Lapata. Disambiguating Visual Verbs. IEEE Transactions on Pattern Analysis and Machine Intelligence. (Submitted)

Spandana Gella. Visual Verb Sense Disambiguation. In first Women in NLP Workshop, in conjunction with ACL,2017. Vancouver, Canada.[Poster]

Spandana Gella, Frank Keller. Analysis of Action Recognition Tasks and Datasets for Still Images. In Proceedings of the 55th annual meeting of the Association for Computational Linguistics (ACL, 2017). Vancouver, Canada [Slides]


Spandana Gella, Margaret Mitchell. Residual Multiple Instance Learning for Visually Impaired Image Descriptions. In 11th Women in Machine Learning Workshop, in conjunction with NIPS, 2016

Spandana Gella, Mirella Lapata, and Frank Keller. 2016. Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (NAACL, 2016). San Diego, California. [Project Page, Slides]

Agha Ali Raza, Rajat Kulshreshtha, Spandana Gella, Sean Blagsvedt, Maya Chandrasekaran, Bhiksha Raj, Roni Rosenfeld. 2016. Viral Spread via Entertainment and Voice-Messaging Among Telephone Users in India. In Proceedings of the International Conference on Information & Communication Technologies and Development (ICTD, 2016). Ann Arbor, Michigan.


Spandana Gella, Marc Dymetman, Jean-Michel Renders, Sriram Venkatapathy. Method and System for Assisting Contact Center Agents in Composing Electronic Mail Replies USPTO Publication Number: US9722957 B2


Spandana Gella, Kalika Bali and Monojit Choudhury. "ye word kis lang ka hai bhai?" Testing the Limits of Word level Language Identification . In Proceedings of the Eleventh International Conference on Natural Language Processing (ICON 2014). Goa, India.

Yogarshi Vyas, Spandana Gella, Jatin Sharma, Kalika Bali and Monojit Choudhury, Challenges in POS Tagging of English-Hindi Code-Mixed Social Media Content. In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP 2014). Doha, Qatar.

Parth Gupta, Kalika Bali, Rafael Banchs, Monojit Choudhury and Paolo Rosso (Additional Author: Spandana Gella) Query Expansion for Mixed-script Information Retrieval. In Proceedings of SIGIR 2014 (Gold Coast, Australia).
Contributions: Bing Query Log Analysis (Identification and Categorization of code-switched queries in Bing query logs)

Jey Han Lau, Paul Cook, Diana McCarthy, Spandana Gella and Timothy Baldwin. Learning Word Sense Distributions, Detecting Unattested Senses and Identifying Novel Senses Using Topic Models. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014). Baltimore, Maryland [Slides]

Spandana Gella, Paul Cook and Timothy Baldwin. One Sense per Tweeter ... and Other Lexical Semantic Tales of Twitter, In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), Gothenburg, Sweden. [Slides, Dataset]

Spandana Gella, Carlo Strapparava and Vivi Nastase. Mapping WordNet Domains, WordNet Topics and Wikipedia Categories to Generate Multilingual Domain Specific Resources In the Nineth International Conference on Language Resources and Evaluation (LREC) 2014, Reykjavik (Iceland) . [Project Page, Poster]


Spandana Gella, Jatin Sharma and Kalika Bali. Query word labeling and Back Transliteration for Indian Languages: Shared task system description In Proceedings of the Fifth Workshop on Forum for Information Retrieval (FIRE 2013). New Delhi, India. Best performing system, subtask1 [Slides, bib]

Spandana Gella, Paul Cook and Bo Han. Unsupervised Word Usage Similarity in Social Media Texts In Proceedings of the Second Joint Conference on Lexical and Computational Semantics (*SEM2013). Atlanta, Georgia. Best Short paper award [Slides, Dataset]

Spandana Gella, Bahar Salehi, Marco Lui, Karl Grieser, Paul Cook, Tim Baldwin. UniMelb NLP-CORE: Integrating predictions from multiple domains and feature sets for estimating semantic textual similarity. In Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval 2013), in conjunction with (*SEM 2013). Atlanta, Georgia.

Ranked 4th/17th out of 89 participating Systems.


Spandana Gella, Duong Thanh Long. 2012. Automatic sentence classifier using sentence ordering features
for Event Based Medicine: Shared task system description
In Proceedings of Australasian Language Technology Association Workshop, pages 130−133. bib.
Our system was among top 5 best performing systems

Diana McCarthy, Spandana Gella, Siva Reddy. DSS: Text Similarity Using Lexical
Alignments of Form, Distributional Semantics and Grammatical Relations
of the 6th International Workshop on Semantic Evaluation (SemEval 2012), in conjunction with (*SEM 2012), 2012
. [bib]


Siva Reddy, Diana McCarthy, Suresh Manandhar, Spandana Gella. Exemplar-based Word-Space Model for Compositionality Detection: Shared task system description In Proceedings of DISCo-2011 in conjunction with ACL 2011. Best performing system [bib]


Spandana Gella Word Usages and Patterns over Social Media University of Melbourne, Australia. [Slides, bib]

Site Counter