Papers by Tejas Gokhale

12 papers
Self-Supervised Test-Time Learning for Reading Comprehension (2021.naacl-main)

Copied to clipboard

Challenge: Recent work on unsupervised question answering shows that models can be trained with procedurally generated question-answer pairs and achieve performance competitive with supervised methods.
Approach: They propose a method that performs "test-time learning" on a given context . they use self-supervision to train models on synthetically generated question-answer pairs .
Outcome: The proposed method outperforms current unsupervised methods and outperformed supervised methods.
Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning (2020.emnlp-main)

Copied to clipboard

Challenge: Observable changes in the scene are reflected in captions, but actions are also linked to social aspects such as intentions, effects, and attributes that describe the agent.
Approach: They propose to generate captions from videos that describe latent aspects of the human agent's actions.
Outcome: The proposed model can be used to describe latent aspects of human actions in video clips and answer questions about videos.
MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering (2020.emnlp-main)

Copied to clipboard

Challenge: Availability of large-scale datasets has enabled statistical machine learning in vision and language understanding.
Approach: They propose a training paradigm that exposes models to perceptually similar mutations of input . they show a 10.57% improvement in the VQA-CP challenge .
Outcome: The proposed training paradigm improves on the visual question answering challenge with 10.57% accuracy.
End-to-end Knowledge Retrieval with Multi-modal Queries (2023.acl-long)

Copied to clipboard

Challenge: a new task is proposed to learn knowledge retrieval with multimodal queries . a vision-language model can retrieve knowledge using images and text inputs .
Approach: They propose a task for vision-language models to retrieve knowledge with multi-modal queries . they propose reViz, a model that integrates content from both text and image queries based on a multimodal query task .
Outcome: The proposed task performs better under zero-shot settings than previous work on cross-modal retrieval.
Side Effects of Erasing Concepts from Diffusion Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Concept erasure techniques (CETs) are used to erade text-to-image (T2I) generative models infringing on privacy, copyright and safety.
Approach: They propose a side effect evaluation benchmark to measure the robustness of CETs.
Outcome: The proposed techniques can be easily circumvented by hierarchy, prompts, and compositional variants of the target.
Semantically Distributed Robust Optimization for Vision-and-Language Inference (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods to integrate linguistic knowledge into training pipelines are under-explored.
Approach: They propose a model-agnostic method that leverages linguistic transformations to infer a set of linguistic phenomena.
Outcome: The proposed method improves on benchmark datasets with images and video and is generalizable to other V&L tasks.
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness (2022.findings-acl)

Copied to clipboard

Challenge: Data modification has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs.
Approach: They propose to use data modification to generalize to out-of-domain inputs . they also analyze their adversarial robustness using a synthetic dataset .
Outcome: The proposed data modification strategies improve OOD accuracy and AR, but data filtering hurts OOD on other tasks.
CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering (2022.emnlp-main)

Copied to clipboard

Challenge: Videos often capture objects, their visible properties, their motion, and the interactions between different objects.
Approach: They propose a video question answering dataset for reasoning about the implicit physical properties of objects in a scene.
Outcome: The proposed dataset enables evaluation under several out-of-distribution settings – videos with objects with masses, coefficients of friction, and initial velocities that are not observed in the training distribution.
Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to multimodal information retrieval (MMIR) lack generalization across different modalities and require annotated training data.
Approach: They propose a fine-tuning-free, two-stage MMIR approach that couples efficient candidate filtering with fine-grained multimodal re-ranking.
Outcome: The proposed approach outperforms supervised methods on 23 datasets.
WeaQA: Weak Supervision via Captions for Visual Question Answering (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for training visual question answering models rely on datasets with human-annotated image-quest-answer triplets.
Approach: They propose a method to train models with synthetic Q-A pairs generated procedurally from captions.
Outcome: The proposed method trains models with synthetic Q-A pairs generated from captions on three VQA benchmarks.
Unsupervised Natural Language Inference Using PHL Triplet Generation (2022.findings-acl)

Copied to clipboard

Challenge: In some cases, training samples may not be available or collecting them could be time-consuming and resource-intensive.
Approach: They propose a procedural approach that leverages sentence transformations to collect PHL triplets for training NLI models.
Outcome: The proposed model outperforms existing models on several NLI benchmarks with a set of sentence transformations.
To Find Waldo You Need Contextual Cues: Debiasing Who’s Waldo (2022.acl-short)

Copied to clipboard

Challenge: Existing datasets for Person-centric visual grounding (PCVG) are biased and over-estimated .
Approach: They propose to use a dataset for the Person-centric Visual Grounding task that requires pairing up a person’s name mentioned in a caption with a bounding box that points to the person in the image.
Outcome: The proposed dataset offers a more practical benchmark for future improvements and better performance than the original dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations