Unsupervised Language agnostic WER Standardization

no code implementations • 9 Mar 2023 • Satarupa Guha, Rahul Ambavat, Ankur Gupta, Manish Gupta, Rupeshkumar Mehta

However, WER fails to provide a fair evaluation of human perceived quality in presence of spelling variations, abbreviations, or compound words arising out of agglutination.

speech-recognition Speech Recognition +1

Unsupervised Contextualized Document Representation

1 code implementation • EMNLP (sustainlp) 2021 • Ankur Gupta, Vivek Gupta

In this paper, we address this issue by proposing SCDV+BERT(ctxd), a simple and effective unsupervised representation that combines contextualized BERT (Devlin et al., 2019) based word embedding for word sense disambiguation with SCDV soft clustering approach.

Sentence Similarity Word Sense Disambiguation

BreakingBERT@IITK at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables

no code implementations • SEMEVAL 2021 • Aditya Jindal, Ankur Gupta, Jaya Srivastava, Preeti Menghwani, Vijit Malik, Vishesh Kaushik, Ashutosh Modi

There are two subtasks, in which given a table and a statement/fact, the subtask A is to determine whether the statement is inferred from the tabular data and the subtask B is to determine which cells in the table provide evidence for the former subtask.

Fact Verification Natural Language Inference

BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with Tables

1 code implementation • 7 Apr 2021 • Aditya Jindal, Ankur Gupta, Jaya Srivastava, Preeti Menghwani, Vijit Malik, Vishesh Kaushik, Ashutosh Modi

Given a table and a statement/fact, subtask A determines whether the statement is inferred from the tabular data, and subtask B determines which cells in the table provide evidence for the former subtask.

Fact Verification Natural Language Inference

TruthBot: An Automated Conversational Tool for Intent Learning, Curated Information Presenting, and Fake News Alerting

no code implementations • 31 Jan 2021 • Ankur Gupta, Yash Varun, Prarthana Das, Nithya Muttineni, Parth Srivastava, Hamim Zafar, Tanmoy Chakraborty, Swaprava Nath

Each class is implemented as a separate module that uses either its own curated knowledge-base or searches the web to obtain the correct information.

Chatbot

3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding

1 code implementation • CVPR 2014 • Ankur Gupta, Julieta Martinez, James J. Little, Robert J. Woodham

We describe a new approach to transfer knowledge across views for action recognition by using examples from a large collection of unlabelled mocap data.

Action Recognition Temporal Action Localization

Counterfactual Estimation and Optimization of Click Metrics for Search Engines

no code implementations • 7 Mar 2014 • Lihong Li, Shunbao Chen, Jim Kleban, Ankur Gupta

Optimizing an interactive system against a predefined online metric is particularly challenging, when the metric is computed from user feedback such as clicks and payments.

Causal Inference

Automated Switching System for Skin Pixel Segmentation in Varied Lighting

no code implementations • 17 Apr 2013 • Ankit Chaudhary, Ankur Gupta

In Computer Vision, colour-based spatial techniquesoften assume a static skin colour model.