36 citations · 80 across the 10 of their papers we have counts for
11 papers
Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference
Soumil Mandal
Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated…
AdvCodeMix: Adversarial Attack on Code-Mixed Data
Sourya Dipta Das, Ayan Basak, Soumil Mandal +1
Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on…
Team Neuro at SemEval-2020 Task 8: Multi-Modal Fine Grain Emotion Classification of Memes using Multitask Learning
Sourya Dipta Das, Soumil Mandal
In this article, we describe the system that we used for the memotion analysis challenge, which is Task 8 of SemEval-2020. This challenge had three subtasks where affect based sent…
Code-Mixed to Monolingual Translation Framework
Sainik Kumar Mahata, Soumil Mandal, Dipankar Das +1
The use of multilingualism in the new generation is widespread in the form of code-mixed data on social media, and therefore a robust translation system is required for catering to…
SMT vs NMT: A Comparison over Hindi & Bengali Simple Sentences
Sainik Kumar Mahata, Soumil Mandal, Dipankar Das +1
In the present article, we identified the qualitative differences between Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) outputs. We have tried to answe…
Strategies for Language Identification in Code-Mixed Low Resource Languages
Soumil Mandal, Sankalp Sanand
In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we presen…
Language Identification in Code-Mixed Data using Multichannel Neural Networks and Context Capture
Soumil Mandal, Anil Kumar Singh
An accurate language identification tool is an absolute necessity for building complex NLP systems to be used on code-mixed data. Lot of work has been recently done on the same, bu…
Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance
Soumil Mandal, Karthick Nanmaran
Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data co…
Preparing Bengali-English Code-Mixed Corpus for Sentiment Analysis of Indian Languages
Soumil Mandal, Sainik Kumar Mahata, Dipankar Das
Analysis of informative contents and sentiments of social users has been attempted quite intensively in the recent past. Most of the systems are usable only for monolingual data an…
Language Identification of Bengali-English Code-Mixed data using Character & Phonetic based LSTM Models
Soumil Mandal, Sourya Dipta Das, Dipankar Das
Language identification of social media text still remains a challenging task due to properties like code-mixing and inconsistent phonetic transliterations. In this paper, we prese…
Analyzing Roles of Classifiers and Code-Mixed factors for Sentiment Identification
Soumil Mandal, Dipankar Das
Multilingual speakers often switch between languages to express themselves on social communication platforms. Sometimes, the original script of the language is preserved, while usi…