Stylistic MR-to-Text Generation Using Pre-trained Language Models

no code implementations • ICON 2021 • Kunal Pagarey, Kanika Kalra, Abhay Garg, Saumajit Saha, Mayur Patidar, Shirish Karande

We explore the ability of pre-trained language models BART, an encoder-decoder model, GPT2 and GPT-Neo, both decoder-only models for generating sentences from structured MR tags as input.

POS Sentence +1

Performance of BERT on Persuasion for Good

no code implementations • ICON 2021 • Saumajit Saha, Kanika Kalra, Manasi Patwardhan, Shirish Karande

We consider the task of automatically classifying the persuasion strategy employed by an utterance in a dialog.

Knowledge Transfer for Pseudo-code Generation from Low Resource Programming Language

no code implementations • 16 Mar 2023 • Ankita Sontakke, Kanika Kalra, Manasi Patwardhan, Lovekesh Vig, Raveendra Kumar Medicherla, Ravindra Naik, Shrishti Pradhan

In this paper, we focus on transferring the knowledge acquired by the code-to-pseudocode neural model trained on a high resource PL (C++) using parallel code-pseudocode data.

Code Generation Transfer Learning +1

Understanding Advertisements with BERT

no code implementations • ACL 2020 • Kanika Kalra, Bhargav Kurma, Silpa Vadakkeeveetil Sreelatha, Manasi Patwardhan, Kar, Shirish e

This achieves an accuracy of 89. 69{\%}, which is an improvement of 4. 7{\%}.

Image Captioning Sentence +1

Ashwin: Plug-and-Play System for Machine-Human Image Annotation

no code implementations • 8 Sep 2016 • Anand Sriraman, Mandar Kulkarni, Rahul Kumar, Kanika Kalra, Purushotam Radadia, Shirish Karande

We present an end-to-end machine-human image annotation system where each component can be attached in a plug-and-play fashion.