Search Results for author: Sumit Bhatia

Found 27 papers, 7 papers with code

SMART: Submodular Data Mixture Strategy for Instruction Tuning

1 code implementation13 Mar 2024 H S V N S Kowndinya Renduchintala, Sumit Bhatia, Ganesh Ramakrishnan

Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks.

Language Modelling

All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation

no code implementations9 Nov 2023 Pragyan Banerjee, Abhinav Java, Surgan Jandial, Simra Shahid, Shaz Furniturewala, Balaji Krishnamurthy, Sumit Bhatia

Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks.

Fairness Language Modelling +1

Neuro-Symbolic RDF and Description Logic Reasoners: The State-Of-The-Art and Challenges

no code implementations9 Aug 2023 Gunjan Singh, Sumit Bhatia, Raghava Mutharaju

Ontologies are used in various domains, with RDF and OWL being prominent standards for ontology development.

Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems

no code implementations14 Jul 2023 Shivani Kumar, Sumit Bhatia, Milan Aggarwal, Tanmoy Chakraborty

To this end, we propose UNIT, a UNified dIalogue dataseT constructed from conversations of existing datasets for different dialogue tasks capturing the nuances for each of them.

HyHTM: Hyperbolic Geometry based Hierarchical Topic Models

1 code implementation16 May 2023 Simra Shahid, Tanay Anand, Nikitha Srikanth, Sumit Bhatia, Balaji Krishnamurthy, Nikaash Puri

We present HyHTM - a Hyperbolic geometry based Hierarchical Topic Models - that addresses these limitations by incorporating hierarchical information from hyperbolic geometry to explicitly model hierarchies in topic models.

Topic Models

INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models

no code implementations11 May 2023 H S V N S Kowndinya Renduchintala, KrishnaTeja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh Iyer, Balaji Krishnamurthy

A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size.

Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation

1 code implementation25 Apr 2023 Michael Llordes, Debasis Ganguly, Sumit Bhatia, Chirag Agarwal

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations.

Retrieval

Expressive Reasoning Graph Store: A Unified Framework for Managing RDF and Property Graph Databases

1 code implementation13 Sep 2022 Sumit Neelam, Udit Sharma, Sumit Bhatia, Hima Karanam, Ankita Likhyani, Ibrahim Abdelaziz, Achille Fokoue, L. V. Subramaniam

Resource Description Framework (RDF) and Property Graph (PG) are the two most commonly used data models for representing, storing, and querying graph data.

Translation

LM-CORE: Language Models with Contextually Relevant External Knowledge

1 code implementation Findings (NAACL) 2022 Jivat Neet Kaur, Sumit Bhatia, Milan Aggarwal, Rachit Bansal, Balaji Krishnamurthy

Large transformer-based pre-trained language models have achieved impressive performance on a variety of knowledge-intensive tasks and can capture factual knowledge in their parameters.

Knowledge Probing Language Modelling

CyCLIP: Cyclic Contrastive Language-Image Pretraining

1 code implementation28 May 2022 Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan A. Rossi, Vishwa Vinay, Aditya Grover

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness.

Representation Learning Visual Reasoning +1

Why Did You Not Compare With That? Identifying Papers for Use as Baselines

1 code implementation20 Jan 2022 Manjot Bedi, Tanisha Pandey, Sumit Bhatia, Tanmoy Chakraborty

We frame the problem as a binary classification task where all the references in a paper are to be classified as either baselines or non-baselines.

Binary Classification Classification

SERC: Syntactic and Semantic Sequence based Event Relation Classification

no code implementations3 Nov 2021 Kritika Venkatachalam, Raghava Mutharaju, Sumit Bhatia

We propose an LSTM based model for temporal and causal relation classification that captures the interrelations between the three encoded features.

Classification Natural Language Inference +4

Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships

no code implementations20 Oct 2021 Biswesh Mohapatra, Sumit Bhatia, Raghava Mutharaju, G. Srinivasaraghavan

However, most of the existing KG embeddings only consider the network structure of the graph and ignore the semantics and the characteristics of the underlying ontology that provides crucial information about relationships between entities in the KG.

Link Prediction Question Answering

No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge

no code implementations AKBC Workshop CSKB 2021 Jivat Neet Kaur, Sumit Bhatia, Milan Aggarwal, Rachit Bansal, Balaji Krishnamurthy

This allows the training of the language model to be de-coupled from the external knowledge source and the latter can be updated without affecting the parameters of the language model.

Language Modelling

ECIR 2020 Workshops: Assessing the Impact of Going Online

no code implementations14 May 2020 Sérgio Nunes, Suzanne Little, Sumit Bhatia, Ludovico Boratto, Guillaume Cabanac, Ricardo Campos, Francisco M. Couto, Stefano Faralli, Ingo Frommholz, Adam Jatowt, Alípio Jorge, Mirko Marras, Philipp Mayr, Giovanni Stilo

In this report, we describe the experience of organizing the ECIR 2020 Workshops in this scenario from two perspectives: the workshop organizers and the workshop participants.

Link Prediction using Graph Neural Networks for Master Data Management

no code implementations7 Mar 2020 Balaji Ganesan, Srinivas Parkala, Neeraj R Singh, Sumit Bhatia, Gayatri Mishra, Matheen Ahmed Pasha, Hima Patel, Somashekar Naganna

Learning graph representations of n-ary relational data has a number of real world applications like anti-money laundering, fraud detection, and customer due diligence.

Fraud Detection Link Prediction +1

Topic-Specific Sentiment Analysis Can Help Identify Political Ideology

no code implementations WS 2018 Sumit Bhatia, Deepak P

Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues.

Sentiment Analysis

Bernoulli Embeddings for Graphs

no code implementations25 Mar 2018 Vinith Misra, Sumit Bhatia

Just as semantic hashing can accelerate information retrieval, binary valued embeddings can significantly reduce latency in the retrieval of graphical data.

Information Retrieval Quantization +1

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