no code implementations • 24 May 2024 • Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha
From our analysis, we show that: (1) The community's efforts have been primarily targeted towards reducing hallucinations related to visual recognition (VR) prompts (e. g., prompts that only require describing the image), thereby ignoring hallucinations for cognitive prompts (e. g., prompts that require additional skills like reasoning on contents of the image).
1 code implementation • 30 Mar 2024 • Chandra Kiran Reddy Evuru, Sreyan Ghosh, Sonal Kumar, Ramaneswaran S, Utkarsh Tyagi, Dinesh Manocha
We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP.
1 code implementation • 30 Mar 2024 • Sonal Kumar, Sreyan Ghosh, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
We curate Compun, a novel benchmark with 400 unique and commonly used CNs, to evaluate the effectiveness of VLMs in interpreting CNs.
no code implementations • 3 Feb 2024 • Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S, Deepali Aneja, Zeyu Jin, Ramani Duraiswami, Dinesh Manocha
Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets.
1 code implementation • 23 Jan 2024 • Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah
Also, the best version of DatUS^2 outperforms the existing state-of-the-art method for the unsupervised dense semantic segmentation task with 15. 02% MiOU and 21. 47% Pixel accuracy on the SUIM dataset.
Ranked #1 on Unsupervised Semantic Segmentation on SUIM
no code implementations • 30 Nov 2023 • Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar, Purva Chiniya, Dinesh Manocha
We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and the visual cues of its corresponding environment.
1 code implementation • 24 Oct 2023 • Sreyan Ghosh, Chandra Kiran Evuru, Sonal Kumar, S Ramaneswaran, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
We present DALE, a novel and effective generative Data Augmentation framework for low-resource LEgal NLP.
no code implementations • 12 Oct 2023 • Sreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Evuru, S. Ramaneswaran, S. Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs.
1 code implementation • 18 Sep 2023 • Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Ramani Duraiswami, Dinesh Manocha
We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore.
no code implementations • 19 Aug 2023 • Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Sakshi Singh, Sanjoy Chowdhury, Dinesh Manocha
This paper presents ASPIRE (Language-guided data Augmentation for SPurIous correlation REmoval), a simple yet effective solution for expanding the training dataset with synthetic images without spurious features.
1 code implementation • 1 Jun 2023 • Sreyan Ghosh, Utkarsh Tyagi, Manan Suri, Sonal Kumar, S Ramaneswaran, Dinesh Manocha
In addition, we demonstrate the application of ACLM to other domains that suffer from data scarcity (e. g., biomedical).
1 code implementation • 18 May 2023 • Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
Though data augmentation has shown to be highly effective for low-resource NER in general, existing data augmentation techniques fail to produce factual and diverse augmentations for BioNER.
1 code implementation • 2 Mar 2023 • Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
The tremendous growth of social media users interacting in online conversations has led to significant growth in hate speech, affecting people from various demographics.
no code implementations • 27 Nov 2022 • Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Manan Suri, Rajiv Ratn Shah
Based on early-fusion and self-attention-based multimodal interaction between text and acoustic modalities, in this paper, we propose a novel multimodal architecture for disfluency detection from individual utterances.
1 code implementation • 30 Mar 2022 • Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla, Rajiv Ratn Shah, S. Umesh
Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text.
1 code implementation • SEMEVAL 2021 • Sreyan Ghosh, Sonal Kumar
We also explore a dependency parsing approach where we extract spans from the input sentence under the supervision of target span boundaries and rank our spans using a biaffine model.
1 code implementation • 10 Jan 2021 • Sreyan Ghosh, Sonal Kumar, Harsh Jalan, Hemant Yadav, Rajiv Ratn Shah
This paper describes our proposed system for the AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides.