Related papers: Normalization of Transliterated Words in Code-Mixe…
This paper discusses the results obtained for different techniques applied for performing the sentiment analysis of social media (Twitter) code-mixed text written in Hinglish. The various stages involved in performing the sentiment analysis…
In this system paper we present our contribution to the Constraint 2021 COVID-19 Fake News Detection Shared Task, which poses the challenge of classifying COVID-19 related social media posts as either fake or real. In our system, we address…
The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…
This research project aimed to overcome the challenge of analysing human language relationships, facilitate the grouping of languages and formation of genealogical relationship between them by developing automated comparison techniques.…
Twitter with over 500 million users globally, generates over 100,000 tweets per minute . The 140 character limit per tweet, perhaps unintentionally, encourages users to use shorthand notations and to strip spellings to their bare minimum…
Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when conversing with…
With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…
Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To…
Phylogenetic trees can be reconstructed from the matrix which contains the distances between all pairs of languages in a family. Recently, we proposed a new method which uses normalized Levenshtein distances among words with same meaning…
Code-mixing is increasingly prevalent in interactions between humans and large language models, yet existing work often reduces it to a translation or convertibility problem, making it difficult to assess whether a model's switching…
In today's interconnected and multilingual world, code-mixing of languages on social media is a common occurrence. While many Natural Language Processing (NLP) tasks like sentiment analysis are mature and well designed for monolingual text,…
Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an…
Despite success in many domains, neural models struggle in settings where train and test examples are drawn from different distributions. In particular, in contrast to humans, conventional sequence-to-sequence (seq2seq) models fail to…
The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…
Text normalization - the conversion of text from written to spoken form - is traditionally assumed to be an ill-formed task for language models. In this work, we argue otherwise. We empirically show the capacity of Large-Language Models…
Linguistic typology aims to capture structural and semantic variation across the world's languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that…
Detecting semantic similarities between sentences is still a challenge today due to the ambiguity of natural languages. In this work, we propose a simple approach to identifying semantically similar questions by combining the strengths of…
Variation in language is ubiquitous, particularly in newer forms of writing such as social media. Fortunately, variation is not random, it is often linked to social properties of the author. In this paper, we show how to exploit social…
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…
Text embedding models are widely used in natural language processing applications. However, their capability is often benchmarked on tasks that do not require understanding nuanced numerical information in text. As a result, it remains…