Debolena's work on hallucinations in LVLM-based captioning for drone-captured data is accepted in WACV 2025. Congratulations, Debolena.
Suvodip's work on titled "BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation" is accepted in SIGDIAL 2024. This is the 25th edition of the conference focused on the theme of dialog systems.
Suvodip Dey defends his PhD Thesis, in the area of Conversational AI/Dialog Systems. The title of his thesis is "Towards Scalable and Interpretable Dialogue Systems and their Evaluation".
We have our work on non-toxic autosuggest generation accepted at SIGIR 2024. It is one of the topmost conference in the Information Retrieval field. This is another publication from our MAPG work in collaboration with Microsoft.
Two papers accepted at PAKDD 2024. One is on non-toxic autosuggest generation - A joint work with Manish Gipta (Microsoft). This is the first publication from Aishwarya's PhD work. The other paper is from Debolena's PhD work on Image captioning. Again, first publication. Congratulations, Aishwarya and Debolena.
We are working on improving zero-short MT for extremely low resource languages, using noise injection techniques. Two papers on this theme are acceptted, in EMNLP (Findings) and EACL. congratulations Kaushal. Also, congratulations to Maharaj on his first publication from PhD.
Suvodip's work on dialog system evaluation is nominated for best short paper award in SIGDIAL 2023. Although it became the runner-up, it is an amazing feat and recognition from the dialog system community.
Our MAPG (Microsoft Academic Partnership Grant) work on Autosuggest generation is accepted in ECML-PKDD journal track.
Suvodip's work on masking for explainable dialog response evaluation is accepted in SIGDIAL 2023.
Sharan's work on unsupervised style transfer using masked language models is accepted in INLG 2023
Arkadipta's work on VisioTextual Attention for Grounded Cross-Lingual NLI is accepted in Elsevier Natural Language journal.
"Time-to-Event Modeling with Hypernetwork based Hawkes Process"- work from Manisha's PhD work is accepted in SIGKDD.
We have a publication in ACL 2023, on the interesting task of Diverse Headline Generation. Congratultions to all the contributors, from different batches and programs.
Manisha Dubey defends her PhD thesis. Congratulations, Dr. Manisha.
2022
Samujjwal defends his PhD thesis. Congratulations Samujjwal!
Appointed as the Head of the Department of AI department at IIT Hyderabad.
Sharan has a publication in NAACL now. "Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Transfer" by Sharan and Suvodip is accepted in NAACL main conference.
"Hostility Detection in Online Hindi-English code-mixed Conversations" by Kamal, Aditi and Kaushal is accepted in WebSci 2022.
"GNoM: Graph Neural Network Enhanced Language Models for Disaster Related Multilingual Text Classification" - Samujjwal's last piece of PhD work is accepted in WebSci 2022.
Suvodip's paper is accepted in ACL 2022 main. Kaushal's work is accepted in Findings of ACL. Congratulations to both.
Samujjwal's work on unsupervised domain adaptation for disaster related post classification is used in IEEE Transactions on Computational Social Systems. The work uses limited labeled data along with abundantly available unlabeled data generated during a source disaster to propose a novel two-part graph neural network. Congratulations Samujjwal.
Sreekanth's work on retrieving social media posts related to planned events is published in Springer WWW Journal. The journal is ranked A in CORE. The work identifies additional querying/matching components based on limited event metadata. Proper identification and use of these cues help in determining the final ranking. The work took more than 1.5 years to mature and one more year to get accepted. Congratulations Sreekanth.
2021
Manisha gets her work on Semantic Annotation in LBSNs accepted in ASONAM 2021. The proposed method uses multi-view Hypergraph GCNs on spatio-temporal data. Congratulations Manisha!
Suvodip's work on Dialog State Tracking gets accepted in SIGDIAL 2021. Paper title: "Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking". Congratulations to Suvodip.
Kaushal's work on Zero-shot Cross lingual transfer for Natural Language Generation will appear in Findings of ACL 2021. Congratulations to Kaushal.
Work by Arkadipta, Venkatesh and Kaushal on hostility detection in regional language posts has been selected as Shared task best paper honorable mention award in CONSTRAINT (Combating Online Hostile Posts in Regional Languages during Emergency Situation) Workshop in AAAI 2021. Congratulations to the students!
Sreekanth's work on future popularity estimation of planned events is accepted in ECIR 2021. Title of the paper: "Social Media Popularity Prediction of Planned Events using Deep Learning". ECIR has rank A in CORE ranking.
2020
Sreekanth Madisetty defends his thesis. Thesis title: "Towards Event Recommendation using Social Media: Content Identification, Characterization, and Future Popularity Estimation". Congratulations Dr. Sreekanth.
Manisha's work on semantic annotations for LBSNs is accepted in ACM SIGSPATIAL. Manisha is a PhD student jointly supervised by Dr. Srijithand myself. Congratulations to Manisha!!!
Glad to received Teaching Excellence Award (Category: Large Class) form IIT Hyderabad.
Kaushal's work on distractor generation for Reading comprehension MCQ is accepted in CIKM 2020. Congratulations Kaushal.
Work titled "A Neural Approach for Detecting Inline Mathematical Expressions from Scientific Documents" by Sreekanth and Kaushal is accepted in Wiley Expert Systems journal. Congratulations to Sreekanth and Kaushal.
Work done by Samujjwal Ghosh as part of his PhD work is accepted in The 12th ACM Web Science Conference (ACM WebSci 2020). Title of the paper is: "Semi-Supervised Granular Classification Framework for Resource Constrained Short-texts: Towards Retrieving Situational Information During Disaster Events". Congratulations Samujjwal.
2019
Work done by Swapnil in his MTech is accepted in The 19th ACM Symposium on Document Engineering (ACM DocEng 2019). Title of the paper is: "Multi-Context Information for Word Representation Learning". Congratulations Swapnil.
Sreekanth's work is published in the Springer series book Knowledge Discovery, Knowledge Engineering and Knowledge Management. The book includes extended and revised versions of a set of selected papers from KDIR 2017 and other colocated IC3K events. Extended versions of only 12% of the papers that were originally submitted to KDIR 2017 found place in the book. Title of this paper is "Identification of Relevant Hashtags for Planned Events Using Learning to Rank". Congratulations Sreekanth.
Sreekanth Madisetty has an accepted manuscript at the ICDE 2019 Doctoral Symposium. This is the 35th editition of the premier coference in the field of data engineering. The manuscript is about the work that Sreekanth has done as part of his Doctoral Thesis so far, and the research plans ahead.
2018
And now it is "IEEE Transactions on Computational Social Systems". Title of the paper: "A Neural Network Based Ensemble Approach for Spam Detection in Twitter". Many congratulations to Sreekanth.
Long paper accepted at RecSys 2018. This is a work with Rohan Tondulkar and Manisha Dubey. Title of the paper is: "Get Me The Best: Predicting Best Answerers in Community Question Answering Sites"
Work with MTech student Shamik Kundu titled "Classification of Short-Texts Generated During Disasters: A Deep Neural Network Based Approach" accepted in International Symposium on Foundations of Open Source Intelligence and Security Informatics (FOSINT-SI), to be held in conjunction with ASONAM 2018.
Work with MTech student Priyanka Choudhury accepted in 2018 SIGIR Workshop On eCommerce. Title of the paper is "PReFacTO: Preference Relations Based Factor Model with Topic Awareness and Offset".
Paper titled "Personalized Tourist Package Recommendation using Graph Based Approach" accepted in User Modelling Adaptation and Personalization (UMAP) 2018 under Late Breaking Results category. This paper is a work with Rashmi HTI, our MTech student.
Paper titled "Class Specific TF-IDF Boosting for Short-text Classification: Application to Short-texts Generated During Disasters" accepted in Exploitation of Social Media for Emergency Relief and Preparedness (SMERP) Workshop is WebConf 2018 (earlier known as WWW). Samujjwal gets travel grant from Microsoft Research India to present the work.
2017
Paper on Using Social Media for Classifying Actionable Insights in Disaster Scenario accepted in International Journal of Advances in Engineering Sciences and Applied Mathematics (Springer).
Paper on Identifying Relevant Hashtags for Planned Events accepted at 9th International Conference on Knowledge Discovery and Information Retrieval (KDIR 2017).
Work on Prediction of emotion intensity in tweets accepted in 8th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (in conjunction with EMNLP 2017)
Work on Prediction of emotion intensity in tweets accepted in 8th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (in conjunction with EMNLP 2017). An extended version is accepted in MIKE 2017.
Work on "Finding Relevant Tweets for Cultural Events" accepted as CLEF 2017 Working Notes.
2016 and earlier
Paper on Decision Tree Learning accepted at 16th International Conference on BioInformatics and BioEngineering (IEEE BIBE 2016).
GIAN course on "Enabling Large Scale Data Analytics: From Theoretical Foundations to Practice" was held during 13th-17th June 2016. Guest faculty: Dr. Barna Saha from University of Massachusetts Amherst. Course website is here.
CSE@IITH is expected to hold next round of faculty interviews in July 2016. Last date of sending applications for this round is 31st May, 2016.
I am not taking any more interns this summer.
Paper on Metasearch accepted at Expert Systems with Applications Journal.
Presented a talk titled "PREFER: Exploring Preference RElations as FEedback in Recommender Systems" at Indo-UK Workshop on Conformal Prediction for Reliable Machine Learning at IIT Hyderabad.
Paper on application of supervised learning on medical rehabilitation accepted at IEEE Transactions on Biomedical Engineering.