Home
I am a PhD candidate in the Department of CSE,
IIT Bombay, since Autumn 2011. I am working under
the guidance of Prof. Preeti Rao and Prof. Pushpak Bhattacharyya
Research Interests
I am interested in Natural Language Processing (NLP); especially coreference resolution, Music Information Retrieval (MIR), NLP applied for MIR, Deep learning for NLP and MIR.
Details of research given here.
In the past
Course
|
Year |
Institute
|
CPI/Percent
|
PhD (ongoing)
|
2011- till date |
IIT Bombay
|
8.13
|
M-Tech CSE
|
2006-2008 |
NIT Calicut
|
8.63
|
B-Tech CSE
|
2002-2006 |
Amal Jyothi College of Engg: (MG University)
|
80.7%
|
Resume can be found
here.
Research
Music Information Retrieval for Hindustani Music
The research on music information retrieval (MIR) for Hindustani
music targets retrieval from music content and text (meta-content)
Music content: This research focusses on Motif identification and
identification of similarity between ragas.
- motif is a small music segment or a phrase which can be seen
repeating in a composition. We investigated methods for identifying
pakad (characteristic phrase) and mukhda (main title phrase)
instances from a Hindustani raga performance.
- The task of raga similarity identification aims at identifying similarities
between ragas to assist problems like music recommendation
in Hindustani music. Out of the two proposed methods,
the first one identifies raga similarities from textual discussions
on Hindustani ragas and the other one extracts similarities with
the help of composition notations. In both the approaches we
try to learn representation for a raga in the form of a neural
embedding.
Text content: This part of the research aims at improving information
extraction from online forums related to Indian classical music to
enrich the knowledge base with music metadata along with content
based information. Coreference resulution being a crucial problem in
identifying entities in the text, here we focus on coreference resulution
in online forums related to Indian classical music. This invulves
design of features considering the nature of the text. We have also
proposed a few methods to improve coreference resulution on forum
posts.
Google Scholar profile
Publications
2017
- Joe Cheri Ross, Abhijit Mishra, Kaustuv Kanti Ganguli and Pushpak
Bhattacharyya, Identifying Raga Similarity Through embeddings learned
from Compositions’ notation, The 18th International Society for Music
Information Retrieval Conference (ISMIR 2017), Suzhou, China, October 23,
2017.
- Joe Cheri Ross, Rudra Murthy, Kaustuv Kanti Ganguli and Pushpak
Bhattacharyya, Identifying Raga Similarity in Hindustani Classical Music through Distributed Representation of Raga Names, The 13th International
Symposium on Computer Music Multidisciplinary Research (CMMR 2017), Porto, Portugal, September 25, 2017.
- Samarth Agarwal, Aditya Joshi, Joe Cheri Ross, Pushpak Bhattacharyya and
Harsha Wabgaonkar, Are Word Embedding and Dialogue Act Class-based
Features Useful for Coreference Resolution in Dialogue?, The 15th
International Conference of the Pacific Association for Computational
Linguistics (PACLING 2017), Yangon, Myanmar, August 16, 2017.
- Joe Cheri Ross and Pushpak Bhattacharyya, Towards Harnessing Memory
Networks for Coreference Resolution, 2nd Workshop on Representation
Learning for NLP (Repl4NLP) at ACL 2017, Vancouver, Canada, August 3, 2017.
- Joe Cheri Ross and Pushpak Bhattacharyya, Improved Best-First Clustering
for Coreference Resolution in Indian Classical Music Forums, 18th
International Conference on Computational Linguistics and Intelligent Text
Processing (CICLING 2017), Budapest, Hungary, April 17, 2017.
2016
- Joe Cheri Ross, Abhijit Mishra and Pushpak Bhattacharyya, Leveraging
Annotators’ Gaze Behaviour for Coreference Resolution, ACL 2016
Workshop on Cognitive Aspects of Computational Language Learning
(CogACLL 2016) at ACL 2016, Berlin, Germany, August 11, 2016.
- Joe Cheri Ross, Aditya Joshi, Pushpak Bhattacharyya, A Framework th at Uses
the Web for Named Entity Class Identification: Case Study for Indian
Classical Music Forums. Computacin y Sistemas 20(3): 505-513, 2016. (journal)
- Joe Cheri Ross, Aditya Joshi, Pushpak Bhattacharyya A Framework That Uses
the Web for Named Entity Class Identification: Case Study for Indian
Classical Music Forums, 17th International Conference on Computational
Linguistics and Intelligent Text Processing (CICLING 2016), Konya, Turkey,
April 3-9, 2016.
2015
- Joe Cheri Ross, Pushpak Bhattacharyya Coreference Resolution to Support IE
from Indian Classical Music Forums, Recent Advances in Natural Language
Processing (RANLP 2015), Hissar, Bulgaria, September 5, 2015.
2014
- Joe Cheri Ross, Sachin Pawar, Pushpak Bhattacharyya Coreference Resolution
for Better Information Retrieval from Indian Classical Music Forums, 11th
International Conference on Natural Language Processing (ICON 2014), Goa,
India, December 18, 2014.
- Preeti Rao, Joe Cheri Ross, Kaustuv Kanti Ganguli, Vignesh Ishwar, Sankalp
Gulati and Hema Murthy, Classification of Melodic Motifs in Raga Music
with Time series Matching, Journal of New Music Research, 2014 (journal)
2012
- Joe Cheri Ross, TP Vinutha and Preeti Rao, Detecting Melodic Motifs from
Audio for Hindustani Classical Music, 13th International Society for Music
Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.
- Joe Cheri Ross and Preeti Rao, Detection of Raga-Characteristic Phrases from
Hindustani Classical Music Audio, Proceedings of the 2nd CompMusic
Workshop; 2012 Jul 12-13; Istanbul, Turkey, July, 2012
- Joe Cheri Ross and John Samuel, Hierarchical Clustering of Music Database
Based on HMM and Markov Chain for Search Efficiency, Speech, Sound and
Music Processing: Embracing Research in India, Lecture Notes in Computer
Science, Vulume 7172, 2012
2008
- Joe Cheri Ross and Priya Chandran, Object Serialization Support for Object
Oriented Java Processors, ITSim 2008, Kuala Lumpur, Malaysia, Aug, 2008.
News
[Write about your latest awards, fellowships, internships here! :-)]
News
- News Item 1
- News Item 2