Publications







Books

Graph-based Semi-Supervised Learning
Amarnag Subramanya, Partha Pratim Talukdar. Morgan & Claypool Publishers.


Tutorials

Graph-based Deep Learning in Natural Language Processing [Slides]
Shikhar Vashishth, Naganand Yadati and Partha Talukdar
Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) , Hong Kong, China


Never-Ending Learning
Tom Mitchell and Partha Talukdar
International Conference on Machine Learning (ICML 2019), Long Beach, CA, USA


Knowledge Extraction and Inference from Text: Shallow, Deep, and Everything in Between [Part-1] [Part-2]
Partha Talukdar
International Conference on Knowledge Discovery and Data Mining (KDD 2018), London, England


2022

Sequence-to-Sequence Knowledge Graph Completion and Question Answering
Apoorv Saxena, Adrian Kochsiek and Rainer Gemulla
ACL 2022


Answer-level Calibration for Free-form Multiple Choice Question Answering
Sawan Kumar
ACL 2022


Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks
Ashutosh Kumar and Aditya Joshi
Findings of ACL 2022


2021

Question Answering over Temporal Knowledge Graphs [code]
Apoorv Saxena, Soumen Chakrabarti and Partha Talukdar
ACL 2021


Reordering Examples Helps during Priming-based Few-shot Learning [code]
Sawan Kumar, Partha Talukdar
Findings of ACL 2021


OKGIT: Open Knowledge Graph Link Prediction with Implicit Types [code]
Chandrahas, Partha Talukdar
Findings of ACL 2021


Spatial Reasoning from Natural Language Instructions for Robot Manipulation
Sagar Gubbi Venkatesh, Anirban Biswas, Raviteja Upadrashta, Vikram Srinivasan, Partha Talukdar, Bharadwaj Amrutur
ICRA 2021


Graph Neural Networks for Soft Semi-Supervised Learning on Hypergraphs [code]
Naganand Yadati, Tingran Gao, Shahab Asoodeh, Partha Talukdar, Anand Louis
PAKDD 2021


2020

NHP: Neural Hypergraph Link Prediction
Naganand Yadati, Vikram Nitin, Madhav Nimishakavi, Prateek Yadav, Anand Louis, and Partha Talukdar
29th ACM International Conference on Information and Knowledge Management (CIKM2020)


Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings [code]
Apoorv Saxena, Aditay Tripathi and Partha Talukdar
58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Seattle, USA


Natural Language Inference with Faithful Natural Language Explanations [code]
Sawan Kumar and Partha Talukdar
58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Seattle, USA


A Re-evaluation of Knowledge Graph Completion Methods [code]
Zhiqing Sun*, Shikhar Vashishth*, Soumya Sanyal*, Partha Talukdar and Yiming Yang
58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Seattle, USA


Syntax-guided Controlled Generation of Paraphrases [code]
Ashutosh Kumar, Kabir Ahuja, Raghuram Vadapalli, Partha Talukdar
Transactions of ACL (TACL 2020), Seattle, USA


Composition-based Multi-Relational Graph Convolutional Networks
Shikhar Vashishth*, Soumya Sanyal*, Vikram Nitin and Partha Talukdar
Eighth International Conference on Learning Representations (ICLR 2020) , Addis Ababa, Ethiopia


ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations [code]
Ekagra Ranjan, Soumya Sanyal and Partha Talukdar
Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020) , New York, USA


InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions [code]
Shikhar Vashishth*, Soumya Sanyal*, Vikram Nitin, Nilesh Agrawal and Partha Talukdar
Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020) , New York, USA


P-SIF: Document Embeddings using Partition Averaging
Vivek Gupta, Ankit Saw, Pegah Nokhiz, Praneeth Netrapalli, Piyush Rai and Partha Talukdar
Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020) , New York, USA


2019

HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs [code]
Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis and Partha Talukdar
Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019) , Vancouver, Canada


CaRe: Open Knowledge Graph Embeddings [code]
Swapnil Gupta, Sreyash Kenkre and Partha Talukdar
Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) , Hong Kong, China


Improving Answer Selection and Answer Triggering using Hard Negatives
Sawan Kumar, Shweta Garg, Kartik Mehta and Nikhil Rasiwasia
Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) , Hong Kong, China


Zero-shot Word Sense Disambiguation using Sense Definition Embeddings [code]
Sawan Kumar, Sharmistha Jat, Karan Saxena and Partha Talukdar
The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy

Recipient of Outstanding Paper Award



Relating Simple Sentence Representations in Deep Neural Networks and Brain [code]
Sharmistha Jat, Hao Tang, Partha Talukdar and Tom Mitchell
The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy


Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks [code]
Shikhar Vashishth, Manik Bhandari*, Prateek Yadav*, Piyush Rai, Chiranjib Bhattacharyya and Partha Talukdar
The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy


Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation
Ashutosh Kumar*, Satwik Bhattamishra*, Manik Bhandari and Partha Talukdar
2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics , Minneapolis, USA
(*: Equal contributions)

Lovasz Convolutional Networks [code]
Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar and Partha Talukdar
The 22nd International Conference on Artificial Intelligence and Statistics , Okinawa, Japan


Confidence-based Graph Convolutional Networks for Semi-Supervised Learning [code]
Shikhar Vashishth, Prateek Yadav, Manik Bhandari and Partha Talukdar
The 22nd International Conference on Artificial Intelligence and Statistics , Okinawa, Japan


KVQA: Knowledge-aware Visual Question Answering [Project and Data Page]
Sanket Shah*, Anand Mishra*, Naganand Yadati and Partha Talukdar
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Hawaii, USA
(*: Equal contributions)

ReAl-LiFE: Accelerating the Discovery of Individualized Brain Connectomes on GPUs [Code]
Sawan Kumar*, Varsha Sreenivasan*, Partha Talukdar, Franco Pestilli, Devarajan Sridharan
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Hawaii, USA
(*: Equal contributions)

2018

A Riemannian approach to trace norm regularized low-rank tensor completion [Code]
Madhav Nimishakavi, Pratik Kumar Jawanpuria and Bamdev Mishra
Thirty-Second Conference on Neural Information Processing Systems (NIPS 2018), Montréal, Canada

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding [Code]
Shib Sankar Dasgupta, Swayambhu Nath Ray and Partha Talukdar
Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), Brussels, Belgium

AD3: Attentive Deep Document Dater [Code]
Swayambhu Nath Ray, Shib Sankar Dasgupta and Partha Talukdar
Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), Brussels, Belgium

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information [Code]
Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga, Chiranjib Bhattacharyya and Partha Talukdar
Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), Brussels, Belgium

Inductive Framework for Multi-Aspect Streaming Tensor Completion with Side Information [Code]
Madhav Nimishakavi, Bamdev Mishra, Manish Gupta and Partha Talukdar
27th International Conference on Information and Knowledge Management (CIKM 2018), Italy

Dating Documents using Graph Convolution Networks [Code]
Shikhar Vashishth, Shib Sankar Dasgupta, Swayambhu Nath Ray and Partha Talukdar
56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Melbourne, Australia

Towards Understanding Geometry of Knowledge Graph Embeddings [Code]
Chandrahas Dewangan, Aditya Sharma and Partha Talukdar
56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Melbourne, Australia

Higher-order Relation Schema Induction using Tensor Factorization with Back-off and Aggregation [Code]
Madhav Nimishakavi, Manish Gupta and Partha Talukdar
56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Melbourne, Australia

CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information [Code]
Shikhar Vashishth, Prince Jain and Partha Talukdar
The Web Conference 2018 (WWW 2018), Lyon, France. [acceptance rate: 14.8%]

ELDEN: Improved Entity Linking using Densified Knowledge Graphs [Code]
Priya Radhakrishnan, Partha Talukdar and Vasudeva Varma
NAACL 2018, New Orleans, USA

Never-Ending Learning
Tom M. Mitchell, W. Cohen, E. Hruschka, P. Talukdar, B. Yang, J. Betteridge, A. Carlson, B. Dalvi, M. Gardner, B. Kisiel, J. Krishnamurthy, N. Lao, K. Mazaitis, T. Mohamed, N. Nakashole, E. Platanios, A. Ritter, M. Samadi, B. Settles, R. Wang, D. Wijaya, A. Gupta, X. Chen, A. Saparov, M. Greaves, J. Welling
Communications of the ACM, 61(5), pp. 103-115, May 2018.

2017

Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods
Aditya Sharma, Zarana Parekh, Partha Talukdar
International Conference on Empirical Methods in NLP (EMNLP 2017), Cohenhagen, Denmark. [Short Paper]

KGEval: Accuracy Estimation of Automatically Constructed Knowledge Graphs
Prakhar Ojha, Partha Talukdar
International Conference on Empirical Methods in NLP (EMNLP 2017), Cohenhagen, Denmark.

Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
Srinivas Ravishankar, Chandrahas Dewangan and Partha Talukdar
6th Workshop on Automated Knowledge Base Construction (AKBC) 2017

Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention
Sharmistha Jat, Siddhesh Khandelwal and Partha Talukdar
6th Workshop on Automated Knowledge Base Construction (AKBC) 2017
BRAINZOOM: High Resolution Reconstruction from Multi-modal Brain Signals
Xiao Fu, Kejun Huang, Otilia Stretcu, Hyun Ah Song, Evangelos Papalexakis, Partha Talukdar, Tom Mitchell, Nicholas Sidiropoulos, Christos Faloutsos, Barnabas Poczos
SIAM International Conference on Data Mining (SDM 2017), Houston, USA

Facets: Adaptive Local Exploration of Large Graphs
Robert Pienta, Minsuk (Brian) Kahng, Zhiyuan Lin, Jilles Vreeken, Partha Talukdar, James Abello, Ganesh Parameswaran, Duen Horng (Polo) Chau
SIAM International Conference on Data Mining (SDM 2017), Houston, USA

2016

Quality Estimation of Workers in Collaborative Crowdsourcing Using Group Testing
Prakhar Ojha, Partha Talukdar
AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2016)

Relation Schema Induction using Tensor Factorization with Side Information [Code]
Madhav Nimishakavi, Uday Singh Saini, Partha Talukdar
International Conference on Empirical Methods in NLP (EMNLP 2016), Austin, USA

Discovering Response-Eliciting Factors in Social Question-Answering
Danish, Yogesh Dahiya and Partha Talukdar
10th International AAAI Conference on Web and Social Media (ICWSM-16), Cologne, Germany.

ClaimEval: Integrated and Flexible Framework for Claim Evaluation Using Credibility of Sources
Mehdi Samadi, Partha Talukdar, Manuela Veloso, Manuel Blum
30th AAAI Conference Conference on Artificial Intelligence (AAAI-16), Phoenix, USA

2015

An Entity-centric Approach for Overcoming Knowledge Graph Sparsity
Manjunath Hegde, Partha Talukdar
Empirical Methods in NLP (EMNLP 2015), Portugal (Short Paper)

Knowledge Base Inference using Bridging Entities
Bhushan Kotnis, Pradeep Bansal, Partha Talukdar
Empirical Methods in NLP (EMNLP 2015), Portugal (Short Paper)

Translation Invariant Word Embeddings
Matt Gardner, Kejun Huang, Evangelos Papalexakis, Xiao Fu, Partha Talukdar, Christos Faloutsos, Nicholas Sidiropoulos, Tom Mitchell
Empirical Methods in NLP (EMNLP 2015), Portugal (Short Paper)

AskWorld: Budget-Sensitive Query Evaluation for Knowledge-on-Demand
Mehdi Samadi, Partha Talukdar, Manuela Veloso, Tom Mitchell
International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires, Argentina.

Never-Ending Language Learning
Tom Mitchell, William Cohen, Estevam Hruschka, Partha Talukdar, Justin Betteridge, Andrew Carlson, Bhavana Dalvi, Matt Gardner, Bryan Kisiel, Jayant Krishnmurthy, Ni Lao, Kathryn Mazaitis, Tahir Mohammad, Ndapa Nakashole, Emmanouil Antonios Platanios, Alan Ritter, Mehdi Samadi, Burr Settles, Richard Wang, Derry Wijaya, Abhinav Gupta, Xinlei Chen, Abulhair Saparov, Malcolm Greaves and Joel Welling
Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), Austin, USA.

Automatic Gloss Finding for a Knowledge Base using Ontological Constraints
Bhavana Dalvi, Einat Minkov, Partha Talukdar and William Cohen
International Conference on Web Search and Data Mining (WSDM 2015), Shanghai, China

A Compositional and Interpretable Semantic Space
Alona Fyshe, Leila Wehbe, Partha P. Talukdar, Brian Murphy and Tom M. Mitchell
Conference of the North American Chapter of the ACL (NAACL 2015), Denver, USA

Principled Neuro-Functional Connectivity Discovery
K. Huang, N. Sidiropoulos, C. Faloutsos, E. Papalexakis, P. Talukdar, T. Mitchell
SIAM International Conference on Data Mining (SDM 2015), Vancouver, Canada

Active Learning in Keyword Search-based Data Integration
Zhepeng Yan, Nan Zheng, Zachary Ives, Partha Pratim Talukdar, Cong Yu
The VLDB Journal Special Issue on Best Papers of VLDB 2013

Combining Vector Space Embeddings with Symbolic Logical Inference over Open-Domain Text
Matt Gardner, Partha Talukdar and Tom Mitchell
AAAI Spring Symposium on Knowledge Representation and Reasoning, Stanford, USA

2014

Simultaneously Uncovering the Patterns of Brain Regions Involved in Different Story Reading Subprocesses
Leila Wehbe, Brian Murphy, Partha Talukdar, Alona Fyshe, Aaditya Ramdas, Tom Mitchell
PLoS ONE 9(11): e112575. doi:10.1371/journal.pone.0112575

Press Coverage: CMU Press Release, Scientific American (blog), AP, TIME


Theses

Optimization of Connectome Pruning Algorithm using Hybrid CPU-GPU Methods. - Gumma Venkata Kailash Madhav [2017]