3 citations · 13 across the 15 of their papers we have counts for
16 papers
MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution
Prasoon Dev, Anirudh Sankar, Vasudeva Varma
Gated Linear Attention (GLA) Transformers advance linear recurrent models through data-dependent gating, but face a core limitation: the fixed-capacity memory matrices across all h…
Curriculum Learning for Cross-Lingual Data-to-Text Generation With Noisy Data
Kancharla Aditya Hari, Manish Gupta, Vasudeva Varma
Curriculum learning has been used to improve the quality of text generation systems by ordering the training samples according to a particular schedule in various tasks. In the con…
MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models
Rahul Mehta, Andrew Hoblitzell, Jack O'Keefe +2
Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shar…
Multilingual Bias Detection and Mitigation for Indian Languages
Ankita Maity, Anubhav Sharma, Rudra Dhar +3
Lack of diverse perspectives causes neutrality bias in Wikipedia content leading to millions of worldwide readers getting exposed by potentially inaccurate information. Hence, neut…
Neural models for Factual Inconsistency Classification with Explanations
Tathagata Raha, Mukund Choudhary, Abhinav Menon +4
Factual consistency is one of the most important requirements when editing high quality documents. It is extremely important for automatic text generation systems like summarizatio…
LLM-RM at SemEval-2023 Task 2: Multilingual Complex NER using XLM-RoBERTa
Rahul Mehta, Vasudeva Varma
Named Entity Recognition(NER) is a task of recognizing entities at a token level in a sentence. This paper focuses on solving NER tasks in a multilingual setting for complex named…
GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering
Dhaval Taunk, Lakshya Khanna, Pavan Kandru +3
Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects…
XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages
Dhaval Taunk, Shivprasad Sagare, Anupam Patil +3
Lack of encyclopedic text contributors, especially on Wikipedia, makes automated text generation for low resource (LR) languages a critical problem. Existing work on Wikipedia text…
Summarizing Indian Languages using Multilingual Transformers based Models
Dhaval Taunk, Vasudeva Varma
With the advent of multilingual models like mBART, mT5, IndicBART etc., summarization in low resource Indian languages is getting a lot of attention now a days. But still the numbe…
Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages
Bhavyajeet Singh, Pavan Kandru, Anubhav Sharma +1
Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. How…
Investigating Strategies for Clause Recommendation
Sagar Joshi, Sumanth Balaji, Jerrin Thomas +2
Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belo…
Graph-based Keyword Planning for Legal Clause Generation from Topics
Sagar Joshi, Sumanth Balaji, Aparna Garimella +1
Generating domain-specific content such as legal clauses based on minimal user-provided information can be of significant benefit in automating legal contract generation. In this p…
Towards Proactively Forecasting Sentence-Specific Information Popularity within Online News Documents
Sayar Ghosh Roy, Anshul Padhi, Risubh Jain +2
Multiple studies have focused on predicting the prospective popularity of an online document as a whole, without paying attention to the contributions of its individual parts. We i…
XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages
Shivprasad Sagare, Tushar Abhishek, Bhavyajeet Singh +3
Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been develope…
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh +3
Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need automated generation of descriptive text in low resource (LR) languages from English fact…
Transformer Models for Text Coherence Assessment
Tushar Abhishek, Daksh Rawat, Manish Gupta +1
Coherence is an important aspect of text quality and is crucial for ensuring its readability. It is essential desirable for outputs from text generation systems like summarization,…