Search Results for author: Sumeet Agarwal

Found 23 papers, 6 papers with code

Graph Regularized Encoder Training for Extreme Classification

no code implementations28 Feb 2024 Anshul Mittal, Shikhar Mohan, Deepak Saini, Suchith C. Prabhu, Jain jiao, Sumeet Agarwal, Soumen Chakrabarti, Purushottam Kar, Manik Varma

The paper notices that in these settings, it is much more effective to use graph data to regularize encoder training than to implement a GCN.

Classification TAG

Multi-modal Extreme Classification

1 code implementation CVPR 2022 Anshul Mittal, Kunal Dahiya, Shreya Malani, Janani Ramaswamy, Seba Kuruvilla, Jitendra Ajmera, Keng-hao Chang, Sumeet Agarwal, Purushottam Kar, Manik Varma

This paper develops the MUFIN technique for extreme classification (XC) tasks with millions of labels where datapoints and labels are endowed with visual and textual descriptors.

Classification Product Recommendation

Search-time Efficient Device Constraints-Aware Neural Architecture Search

no code implementations10 Jul 2023 Oshin Dutta, Tanu Kanvar, Sumeet Agarwal

To address these concerns, we automate the construction of task-specific deep learning architectures optimized for device constraints through Neural Architecture Search (NAS).

Edge-computing Image Classification +1

Dual Mechanism Priming Effects in Hindi Word Order

no code implementations25 Oct 2022 Sidharth Ranjan, Marten Van Schijndel, Sumeet Agarwal, Rajakrishnan Rajkumar

By showing that different priming influences are separable from one another, our results support the hypothesis that multiple different cognitive mechanisms underlie priming.

Language Modelling Sentence

Discourse Context Predictability Effects in Hindi Word Order

no code implementations25 Oct 2022 Sidharth Ranjan, Marten Van Schijndel, Sumeet Agarwal, Rajakrishnan Rajkumar

While prior work has shown that a number of factors (e. g., information status, dependency length, and syntactic surprisal) influence Hindi word order preferences, the role of discourse predictability is underexplored in the literature.

Sentence

DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents

1 code implementation12 Nov 2021 Kunal Dahiya, Deepak Saini, Anshul Mittal, Ankush Shaw, Kushal Dave, Akshay Soni, Himanshu Jain, Sumeet Agarwal, Manik Varma

Scalability and accuracy are well recognized challenges in deep extreme multi-label learning where the objective is to train architectures for automatically annotating a data point with the most relevant subset of labels from an extremely large label set.

Multi-Label Learning

DECAF: Deep Extreme Classification with Label Features

1 code implementation1 Aug 2021 Anshul Mittal, Kunal Dahiya, Sheshansh Agrawal, Deepak Saini, Sumeet Agarwal, Purushottam Kar, Manik Varma

This paper develops the DECAF algorithm that addresses these challenges by learning models enriched by label metadata that jointly learn model parameters and feature representations using deep networks and offer accurate classification at the scale of millions of labels.

Classification Extreme Multi-Label Classification +5

ECLARE: Extreme Classification with Label Graph Correlations

1 code implementation31 Jul 2021 Anshul Mittal, Noveen Sachdeva, Sheshansh Agrawal, Sumeet Agarwal, Purushottam Kar, Manik Varma

This paper presents ECLARE, a scalable deep learning architecture that incorporates not only label text, but also label correlations, to offer accurate real-time predictions within a few milliseconds.

Classification Extreme Multi-Label Classification +7

Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

1 code implementation SCiL 2021 Hritik Bansal, Gantavya Bhatt, Sumeet Agarwal

However, we observe that several RNN types, including the ONLSTM which has a soft structural inductive bias, surprisingly fail to perform well on sentences without attractors when trained solely on sentences with attractors.

Inductive Bias

How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

1 code implementation ACL 2020 Gantavya Bhatt, Hritik Bansal, Rishubh Singh, Sumeet Agarwal

Long short-term memory (LSTM) networks and their variants are capable of encapsulating long-range dependencies, which is evident from their performance on a variety of linguistic tasks.

Ranked #35 on Language Modelling on WikiText-103 (Validation perplexity metric)

Language Modelling Sentence

DeepXML: Scalable & Accurate Deep Extreme Classification for Matching User Queries to Advertiser Bid Phrases

no code implementations25 Sep 2019 Kunal Dahiya, Anshul Mittal, Deepak Saini, Kushal Dave, Himanshu Jain, Sumeet Agarwal, Manik Varma

The objective in deep extreme multi-label learning is to jointly learn feature representations and classifiers to automatically tag data points with the most relevant subset of labels from an extremely large label set.

Learning Word Embeddings Multi-Label Learning +2

Surprisal and Interference Effects of Case Markers in Hindi Word Order

no code implementations WS 2019 Sidharth Ranjan, Sumeet Agarwal, Rajakrishnan Rajkumar

Based on the Production-Distribution-Comprehension (PDC) account of language processing, we formulate two distinct hypotheses about case marking, word order choices and processing in Hindi.

Sentence

Uniform Information Density Effects on Syntactic Choice in Hindi

no code implementations WS 2018 Ayush Jain, Vishal Singh, Sidharth Ranjan, Rajakrishnan Rajkumar, Sumeet Agarwal

According to the UNIFORM INFORMATION DENSITY (UID) hypothesis (Levy and Jaeger, 2007; Jaeger, 2010), speakers tend to distribute information density across the signal uniformly while producing language.

Sentence

Modeling Image Virality with Pairwise Spatial Transformer Networks

no code implementations22 Sep 2017 Abhimanyu Dubey, Sumeet Agarwal

The study of virality and information diffusion online is a topic gaining traction rapidly in the computational social sciences.

Attribute

Linguistic features for Hindi light verb construction identification

no code implementations COLING 2016 Ashwini Vaidya, Sumeet Agarwal, Martha Palmer

To build our system, we carry out a linguistic analysis of Hindi LVCs using Hindi Treebank annotations and propose two new features that are aimed at capturing the diversity of Hindi LVCs in the corpus.

Machine Translation Translation

Examining Representational Similarity in ConvNets and the Primate Visual Cortex

no code implementations12 Sep 2016 Abhimanyu Dubey, Jayadeva, Sumeet Agarwal

We compare several ConvNets with different depth and regularization techniques with multi-unit macaque IT cortex recordings and assess the impact of the same on representational similarity with the primate visual cortex.

Cannot find the paper you are looking for? You can Submit a new open access paper.