Gourab Kundu


2022

pdf bib
Normalized Contrastive Learning for Text-Video Retrieval
Yookoon Park | Mahmoud Azab | Seungwhan Moon | Bo Xiong | Florian Metze | Gourab Kundu | Kirmani Ahmed
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness. In this work, however, we reveal that cross-modal contrastive learning suffers from incorrect normalization of the sum retrieval probabilities of each text or video instance. Specifically, we show that many test instances are either over- or under-represented during retrieval, significantly hurting the retrieval performance. To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise biases that properly normalize the sum retrieval probabilities of each instance so that every text and video instance is fairly represented during cross-modal retrieval. Empirical study shows that NCL brings consistent and significant gains in text-video retrieval on different model architectures, with new state-of-the-art multimodal retrieval metrics on the ActivityNet, MSVD, and MSR-VTT datasets without any architecture engineering.

2018

pdf bib
Neural Cross-Lingual Coreference Resolution And Its Application To Entity Linking
Gourab Kundu | Avi Sil | Radu Florian | Wael Hamza
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We propose an entity-centric neural crosslingual coreference model that builds on multi-lingual embeddings and language independent features. We perform both intrinsic and extrinsic evaluations of our model. In the intrinsic evaluation, we show that our model, when trained on English and tested on Chinese and Spanish, achieves competitive results to the models trained directly on Chinese and Spanish respectively. In the extrinsic evaluation, we show that our English model helps achieve superior entity linking accuracy on Chinese and Spanish test sets than the top 2015 TAC system without using any annotated data from Chinese or Spanish.

2013

pdf bib
Margin-based Decomposed Amortized Inference
Gourab Kundu | Vivek Srikumar | Dan Roth
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2012

pdf bib
On Amortizing Inference Cost for Structured Prediction
Vivek Srikumar | Gourab Kundu | Dan Roth
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2011

pdf bib
Adapting Text instead of the Model: An Open Domain Approach
Gourab Kundu | Dan Roth
Proceedings of the Fifteenth Conference on Computational Natural Language Learning