Pushpak Bhattacharyya
professor
Over the past two decades, dialogue modeling has made significant stride...
Large language models (LLMs) have demonstrated remarkable performance in...
Speech Emotion Recognition (SER) is the task of identifying the emotion
...
Storytelling is the lifeline of the entertainment industry – movies, TV
...
In the medical domain, several disease treatment procedures have been
do...
Disfluencies commonly occur in conversational speech. Speech with
disflu...
Quality Estimation (QE) is the task of evaluating the quality of a
trans...
Well-formed context aware image captions and tags in enterprise content ...
Hyperbole and metaphor are common in day-to-day communication (e.g., "I ...
Conversational speech often consists of deviations from the speech plan,...
In this work, we present our deployment-ready Speech-to-Speech Machine
T...
We aim to investigate whether UNMT approaches with self-supervised
pre-t...
In this paper, we show that the combination of Phrase Pair Injection and...
The integration of knowledge graphs with deep learning is thriving in
im...
Conventionally, the radiologist prepares the diagnosis notes and shares ...
While sentiment and emotion analysis have been studied extensively, the
...
Movies reflect society and also hold power to transform opinions. Social...
Named Entity Recognition (NER) is a foundational NLP task that aims to
p...
Wordnets are rich lexico-semantic resources. Linked wordnets are extensi...
Wordnets are rich lexico-semantic resources. Linked wordnets are extensi...
This paper describes additional aspects of a digital tool called the 'Te...
Automatic Cognate Detection (ACD) is a challenging task which has been
u...
Dense word vectors or 'word embeddings' which encode semantic properties...
Gaze behaviour has been used as a way to gather cognitive information fo...
Cognates are present in multiple variants of the same text across differ...
Cognates are variants of the same lexical form across different language...
Automatic detection of cognates helps downstream NLP tasks of Machine
Tr...
Question Answering systems these days typically use template-based langu...
Prepositions are frequently occurring polysemous words. Disambiguation o...
Computational Humour (CH) has attracted the interest of Natural Language...
We explore the impact of leveraging the relatedness of languages that be...
Recent advances in Unsupervised Neural Machine Translation (UNMT) have
m...
The anthology of spoken languages today is inundated with textual
inform...
Relation Extraction is an important task in Information Extraction which...
We propose a knowledge-based approach for extraction of Cause-Effect (CE...
Automatic essay grading (AEG) is a process in which machines assign a gr...
Most research in the area of automatic essay grading (AEG) is geared tow...
Recently the NLP community has started showing interest towards the
chal...
Most of the past work in relation extraction deals with relations occurr...
The gaze behaviour of a reader is helpful in solving several NLP tasks s...
Cross-domain sentiment analysis (CDSA) helps to address the problem of d...
In this work, we present an extensive study of statistical machine
trans...
In this paper, we propose a new metric for Machine Translation (MT)
eval...
Denoising-based Unsupervised Neural Machine Translation (U-NMT) models
t...
The problem of event extraction is a relatively difficult task for low
r...
Related tasks often have inter-dependence on each other and perform bett...
Owing to the exponential rise in the electronic medical records, informa...
Fake news, rumor, incorrect information, and misinformation detection ar...
Transfer learning approaches for Neural Machine Translation (NMT) train ...
Suggestion mining is increasingly becoming an important task along with
...