Search Results for author: Shashank Jain

Found 9 papers, 0 papers with code

Building Adaptive Acceptability Classifiers for Neural NLG

no code implementations EMNLP 2021 Soumya Batra, Shashank Jain, Peyman Heidari, Ankit Arun, Catharine Youngs, Xintong Li, Pinar Donmez, Shawn Mei, Shiunzu Kuo, Vikas Bhardwaj, Anuj Kumar, Michael White

We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches.

Sentence Synthetic Data Generation +1

Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task

no code implementations ACL (GEM) 2021 Shreyan Bakshi, Soumya Batra, Peyman Heidari, Ankit Arun, Shashank Jain, Michael White

We explore the use of self-training and acceptability classifiers with pre-trained models for natural language generation in structure-to-text settings using three GEM datasets (E2E, WebNLG-en, Schema-Guided Dialog).

Text Generation

AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model

no code implementations27 Sep 2023 Seungwhan Moon, Andrea Madotto, Zhaojiang Lin, Tushar Nagarajan, Matt Smith, Shashank Jain, Chun-Fu Yeh, Prakash Murugesan, Peyman Heidari, Yue Liu, Kavya Srinet, Babak Damavandi, Anuj Kumar

We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i. e. text, image, video, audio, IMU motion sensor), and generates textual responses.

Language Modelling Video Question Answering

Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite

no code implementations13 Jun 2023 Xiao Yang, Ahmed K. Mohamed, Shashank Jain, Stanislav Peshterliev, Debojeet Chatterjee, Hanwen Zha, Nikita Bhalla, Gagan Aneja, Pranab Mohanty

Importantly, LEDO is computationally efficient compared to methods that require loss function change, and cost-effective as the resulting data can be used in the same continuous training pipeline for production.

Label Error Detection Machine Reading Comprehension +2

A Study on the Efficiency and Generalization of Light Hybrid Retrievers

no code implementations4 Oct 2022 Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati, Barlas Oguz, Debojeet Chatterjee, Xilun Chen, Chitta Baral, Peyman Heidari

Driven by this question, we leverage an indexing-efficient dense retriever (i. e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost.

Adversarial Attack Contrastive Learning +1

Audience Creation for Consumables -- Simple and Scalable Precision Merchandising for a Growing Marketplace

no code implementations17 Nov 2020 Shreyas S, Harsh Maheshwari, Avijit Saha, Samik Datta, Shashank Jain, Disha Makhija, Anuj Nagpal, Sneha Shukla, Suyash S

Consumable categories, such as grocery and fast-moving consumer goods, are quintessential to the growth of e-commerce marketplaces in developing countries.

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