7.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Harish-Chandra Research InstituteIN27 papers
- International Institute of Information TechnologyIN23 papers
- Homi Bhabha National InstituteIN20 papers
- Indian Institute of Science Education and Research ThiruvananthapuramIN20 papers
- Indian Institute of Science BangaloreIN15 papers
- Indian Institute of Technology HyderabadIN14 papers
- Institute of Physics, BhubaneshwarIN11 papers
- Birla Institute of Technology and Science, PilaniIN10 papers
- National University of SingaporeSG9 papers
- Indian Institute of Technology KanpurIN8 papers
- Université Libre de BruxellesBE8 papers
- Birla Institute of Technology and Science - Hyderabad CampusIN7 papers
57 papers · 1 filter
Enhancing AI Safety Through the Fusion of Low Rank Adapters
Satya Swaroop Gudipudi, Sreeram Vipparla, Harpreet Singh +2
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models gen…
COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models
Priyanshul Govil, Hemang Jain, Vamshi Krishna Bonagiri +4
Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating th…
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…
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…
Battling Hateful Content in Indic Languages HASOC '21
Aditya Kadam, Anmol Goel, Jivitesh Jain +7
The extensive rise in consumption of online social media (OSMs) by a large number of people poses a critical problem of curbing the spread of hateful content on these platforms. Wi…
Adversarial Examples for Evaluating Math Word Problem Solvers
Vivek Kumar, Rishabh Maheshwary, Vikram Pudi
Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets. However, the extent to which existing MWP solvers tr…
A Strong Baseline for Query Efficient Attacks in a Black Box Setting
Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
Existing black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not…
A Dynamic Head Importance Computation Mechanism for Neural Machine Translation
Akshay Goindani, Manish Shrivastava
Multiple parallel attention mechanisms that use multiple attention heads facilitate greater performance of the Transformer model for various applications e.g., Neural Machine Trans…
More Parameters? No Thanks!
Zeeshan Khan, Kartheek Akella, Vinay P. Namboodiri +1
This work studies the long-standing problems of model capacity and negative interference in multilingual neural machine translation MNMT. We use network pruning techniques and obse…
Text Simplification by Tagging
Kostiantyn Omelianchuk, Vipul Raheja, Oleksandr Skurzhanskyi
Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models,…
Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes
Anvesh Rao Vijjini, Kaveri Anuranjana, Radhika Mamidi
While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness…
Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers
Ishan Sanjeev Upadhyay, Nikhil E, Anshul Wadhawan +1
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embedd…
Multichannel LSTM-CNN for Telugu Technical Domain Identification
Sunil Gundapu, Radhika Mamidi
With the instantaneous growth of text information, retrieving domain-oriented information from the text data has a broad range of applications in Information Retrieval and Natural…
Transformer based Automatic COVID-19 Fake News Detection System
Sunil Gundapu, Radhika Mamidi
Recent rapid technological advancements in online social networks such as Twitter have led to a great incline in spreading false information and fake news. Misinformation is especi…
Summaformers @ LaySumm 20, LongSumm 20
Sayar Ghosh Roy, Nikhil Pinnaparaju, Risubh Jain +2
Automatic text summarization has been widely studied as an important task in natural language processing. Traditionally, various feature engineering and machine learning based syst…
Leveraging Multilingual Transformers for Hate Speech Detection
Sayar Ghosh Roy, Ujwal Narayan, Tathagata Raha +2
Detecting and classifying instances of hate in social media text has been a problem of interest in Natural Language Processing in the recent years. Our work leverages state of the…
A Context Aware Approach for Generating Natural Language Attacks
Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial exampl…
Clickbait in Hindi News Media : A Preliminary Study
Vivek Kaushal, Kavita Vemuri
A corpus of Hindi news headlines shared on Twitter was created by collecting tweets of 5 mainstream Hindi news sources for a period of 4 months. 7 independent annotators were recru…
Exploring Pair-Wise NMT for Indian Languages
Kartheek Akella, Sai Himal Allu, Sridhar Suresh Ragupathi +4
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages. Multilingual NMT models have demonstrated a reasonable amo…
Generating Natural Language Attacks in a Hard Label Black Box Setting
Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi
We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that craft…
Towards Code-switched Classification Exploiting Constituent Language Resources
Tanvi Dadu, Kartikey Pant
Code-switching is a commonly observed communicative phenomenon denoting a shift from one language to another within the same speech exchange. The analysis of code-switched data oft…
Fighting an Infodemic: COVID-19 Fake News Dataset
Parth Patwa, Shivam Sharma, Srinivas Pykl +6
Along with COVID-19 pandemic we are also fighting an `infodemic'. Fake news and rumors are rampant on social media. Believing in rumors can cause significant harm. This is further…
Word Level Language Identification in English Telugu Code Mixed Data
Sunil Gundapu, Radhika Mamidi
In a multilingual or sociolingual configuration Intra-sentential Code Switching (ICS) or Code Mixing (CM) is frequently observed nowadays. In the world, most of the people know mor…
Development of POS tagger for English-Bengali Code-Mixed data
Tathagata Raha, Sainik Kumar Mahata, Dipankar Das +1
Code-mixed texts are widespread nowadays due to the advent of social media. Since these texts combine two languages to formulate a sentence, it gives rise to various research probl…