Diptesh Kanojia

• Doctor of Philosophy
• PhD Student at IITB-Monash Research Academy

Social media platforms enable the propagation of hateful content across different modalities such as textual, auditory, and visual, necessitating effective detection methods. While recent approaches have shown promise in handling individual modalities, their effectiveness across different modality combinations remains unexplored. This paper present...

Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing. In this paper, we propose a novel technique to mitigate over-correction by incorporating word-level Quality Estimation (QE) information during the decoding process. Thi...

This paper investigates the reference-less evaluation of machine translation for low-resource language pairs, known as quality estimation (QE). Segment-level QE is a challenging cross-lingual language understanding task that provides a quality score (0-100) to the translated output. We comprehensively evaluate large language models (LLMs) in zero/f...

Despite large language models (LLMs) being known to exhibit bias against non-mainstream varieties, there are no known labeled datasets for sentiment analysis of English. To address this gap, we introduce BESSTIE, a benchmark for sentiment and sarcasm classification for three varieties of English: Australian (en-AU), Indian (en-IN), and British (en-...

Sarcasm is a rhetorical device that is used to convey the opposite of the literal meaning of an utterance. Sarcasm is widely used on social media and other forms of computer-mediated communication motivating the use of computational models to identify it automatically. While the clear majority of approaches to sarcasm detection have been carried ou...

This exploratory study investigates the potential of multilingual Automatic Post-Editing (APE) systems to enhance the quality of machine translations for low-resource Indo-Aryan languages. Focusing on two closely related language pairs, English-Marathi and English-Hindi, we exploit the linguistic similarities to develop a robust multilingual APE mo...

This paper addresses the challenge of improving user experience on e-commerce platforms by enhancing product ranking relevant to users' search queries. Ambiguity and complexity of user queries often lead to a mismatch between the user's intent and retrieved product titles or documents. Recent approaches have proposed the use of Transformer-based mo...

This paper investigates data sampling strategies to create a benchmark for dialectal sentiment classification of Google Places reviews written in English. Based on location-based filtering, we collect a self-supervised dataset of reviews in Australian (Australian English), Indian (Indian English), and British (British English) English with self-sup...

The tutorial describes the concept of edit distances applied to research and commercial contexts. We use Translation Edit Rate (TER), Levenshtein, Damerau-Levenshtein, Longest Common Subsequence and $n$-gram distances to demonstrate the frailty of statistical metrics when comparing text sequences. Our discussion disassembles them into their essenti...

This paper investigates whether large language models (LLMs) are state-of-the-art quality estimators for machine translation of user-generated content (UGC) that contains emotional expressions, without the use of reference translations. To achieve this, we employ an existing emotion-related dataset with human-annotated errors and calculate quality...

Machine translation (MT) of user-generated content (UGC) poses unique challenges, including handling slang, emotion, and literary devices like irony and sarcasm. Evaluating the quality of these translations is challenging as current metrics do not focus on these ubiquitous features of UGC. To address this issue, we utilize an existing emotion-relat...

Leveraging large language models (LLMs) for various natural language processing tasks has led to superlative claims about their performance. For the evaluation of machine translation (MT), existing research shows that LLMs are able to achieve results comparable to fine-tuned multilingual pre-trained language models. In this paper, we explore what t...

Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a language), Creoles (languages arising from linguistic contact between multiple languages) and other low-resource...

Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the genealogical ties between Creoles and a number of highly resourced languages imply a significant potential for transfer learning, this potential is hampered due to this lack of annotated data. In this work we present Cre...

Sarcasm is a rhetorical device that is used to convey the opposite of the literal meaning of an utterance. Sarcasm is widely used on social media and other forms of computer-mediated communication motivating the use of computational models to identify it automatically. While the clear majority of approaches to sarcasm detection have been carried ou...

This study explores the use of Google Translate (GT) for translating mental healthcare (MHealth) information and evaluates its accuracy, comprehensibility, and implications for multilingual healthcare communication through analysing GT output in the MHealth domain from English to Persian, Arabic, Turkish, Romanian, and Spanish. Two datasets compris...

Evaluation of machine translation (MT) is vital to determine the effectiveness of MT systems. This paper investigates quality estimation (QE) for machine translation (MT) for low-resource Indic languages. We analyse the influence of language relatedness within linguistic families and integrate various pre-trained encoders within the MonoTransQuest(...

Named Entity Recognition (NER) is a foundational NLP task that aims to provide class labels like Person, Location, Organisation, Time, and Number to words in free text. Named Entities can also be multi-word expressions where the additional I-O-B annotation information helps label them during the NER annotation process. While English and European la...

Wordnets are rich lexico-semantic resources. Linked wordnets are extensions of wordnets, which link similar concepts in wordnets of different languages. Such resources are extremely useful in many Natural Language Processing (NLP) applications, primarily those based on knowledge-based approaches. In such approaches, these resources are considered a...

In today's digital world language technology has gained importance. Several softwares, have been developed and are available in the field of computational linguistics. Such tools play a crucial role in making classical language texts easily accessible. Some Indian philosophical schools have contributed towards various techniques of verbal cognition...

This paper describes additional aspects of a digital tool called the 'Textual History Tool'. We describe its various salient features with special reference to those of its features that may help the philologist digitize commentaries and sub-commentaries on a text. This tool captures the historical evolution of a text through various temporal stage...

Wordnets are rich lexico-semantic resources. Linked wordnets are extensions of wordnets, which link similar concepts in wordnets of different languages. Such resources are extremely useful in many Natural Language Processing (NLP) applications, primarily those based on knowledge-based approaches. In such approaches, these resources are considered a...

Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, Information Retrieval and Computational Phylogenetics. Unidentified cognate pairs can pose a challenge to these applications and result in a degradation of performance. In this paper, we detect cognate word pairs among...

Dense word vectors or 'word embeddings' which encode semantic properties of words, have now become integral to NLP tasks like Machine Translation (MT), Question Answering (QA), Word Sense Disambiguation (WSD), and Information Retrieval (IR). In this paper, we use various existing approaches to create multiple word embeddings for 14 Indian languages...

Gaze behaviour has been used as a way to gather cognitive information for a number of years. In this paper, we discuss the use of gaze behaviour in solving different tasks in natural language processing (NLP) without having to record it at test time. This is because the collection of gaze behaviour is a costly task, both in terms of time and money....

Cognates are present in multiple variants of the same text across different languages (e.g., "hund" in German and "hound" in English language mean "dog"). They pose a challenge to various Natural Language Processing (NLP) applications such as Machine Translation, Cross-lingual Sense Disambiguation, Computational Phylogenetics, and Information Retri...

Cognates are variants of the same lexical form across different languages; for example 'fonema' in Spanish and 'phoneme' in English are cognates, both of which mean 'a unit of sound'. The task of automatic detection of cognates among any two languages can help downstream NLP tasks such as Cross-lingual Information Retrieval, Computational Phylogene...

Automatic detection of cognates helps downstream NLP tasks of Machine Translation, Cross-lingual Information Retrieval, Computational Phylogenetics and Cross-lingual Named Entity Recognition. Previous approaches for the task of cognate detection use orthographic, phonetic and semantic similarity based features sets. In this paper, we propose a nove...

Computational Humour (CH) has attracted the interest of Natural Language Processing and Computational Linguistics communities. Creating datasets for automatic measurement of humour quotient is difficult due to multiple possible interpretations of the content. In this work, we create a multi-modal humour-annotated dataset (∼40 hours) using stand-up...

Computational Humour (CH) has attracted the interest of Natural Language Processing and Computational Linguistics communities. Creating datasets for automatic measurement of humour quotient is difficult due to multiple possible interpretations of the content. In this work, we create a multi-modal humour-annotated dataset ($\sim$40 hours) using stan...

Automatic essay grading (AEG) is a process in which machines assign a grade to an essay written in response to a topic, called the prompt. Zero-shot AEG is when we train a system to grade essays written to a new prompt which was not present in our training data. In this paper, we describe a solution to the problem of zero-shot automatic essay gradi...

Gaze behaviour has been used as a way to gather cognitive information for a number of years. In this paper, we discuss the use of gaze behaviour in solving different tasks in natural language processing (NLP) without having to record it at test time. This is because the collection of gaze behaviour is a costly task, both in terms of time and money....

The gaze behaviour of a reader is helpful in solving several NLP tasks such as automatic essay grading, named entity recognition, sarcasm detection $\textit{etc.}$ However, collecting gaze behaviour from readers is costly in terms of time and money. In this paper, we propose a way to improve automatic essay grading using gaze behaviour, where the g...

Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain (known as the target domain) is unavailable or insufficient. However, the decision to choose a domain (known as the source domain) to leverage from is, at best, intuitive. In this paper, we investigate text similarity m...

Cognates are present in multiple variants of the same text across different languages. Computational Phylogenetics uses algorithms and techniques to analyze these variants and infer phylogenetic trees for a hypothesized accurate representation based on the output of the computational algorithm used. In our work, we detect cognates among a few India...

Predicting a reader's rating of text quality is a challenging task that involves estimating different subjective aspects of the text, like structure, clarity, etc. Such subjective aspects are better handled using cognitive information. One such source of cognitive information is gaze behaviour. In this paper, we show that gaze behaviour does indeed...

The Sanskrit grammatical tradition which has commenced with Panini's Astadhyayi mostly as a Padasastra has culminated as a Vakyasastra, at the hands of Bhartrhari. The grammarian-philosopher Bhartrhari and his authoritative work 'Vakyapadiya' have been a matter of study for modern scholars, at least for more than 50 years, since Ashok Aklujkar subm...

We present a quantitative, data-driven machine learning approach to mitigate the problem of unpredictability of Computer Science Graduate School Admissions. In this paper, we discuss the possibility of a system which may help prospective applicants evaluate their Statement of Purpose (SOP) based on our system output. We, then, identify feature sets...

Sarcasm Suite is a browser-based engine that deploys five of our past papers in sarcasm detection and generation. The sarcasm detection modules use four kinds of incongruity: sentiment incongruity, semantic incongruity, historical context incongruity and conversational context incongruity. The sarcasm generation module is a chatbot that responds sa...

Measuring reading effort is useful for practical purposes such as designing learning material and personalizing text comprehension environment. We propose a quantification of reading effort by measuring the complexity of eye-movement patterns of readers. We call the measure Scanpath Complexity. Scanpath complexity is modeled as a function of variou...

In this paper, we propose a novel mechanism for enriching the feature vector, for the task of sarcasm detection, with cognitive features extracted from eye-movement patterns of human readers. Sarcasm detection has been a challenging research problem, and its importance for NLP applications such as review summarization, dialog systems and sentiment...

Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic levels. To address this, we propose to augment traditional features used for sentiment analysis and sarcasm detection, with cognitive features derived from the eye-movement patterns of readers. Statistical classifi...

We present the Civique system for emergency detection in urban areas by monitoring micro blogs like Tweets. The system detects emergency related events, and classifies them into appropriate categories like " fire " , " accident " , " earthquake " , etc. We demonstrate our ideas by classifying Twitter posts in real time, visualizing the ongoing even...

Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic levels. To address this, we propose to augment traditional features used for sentiment analysis and sarcasm detection, with cognitive features derived from the eye-movement patterns of readers. Statistical classifi...

In this paper, we propose a novel mechanism for enriching the feature vector, for the task of sarcasm detection, with cogni-tive features extracted from eye-movement patterns of human readers. Sarcasm detection has been a challenging research problem , and its importance for NLP applications such as review summarization, dialog systems and sentimen...

We present a WordNet like structured resource for slang words and neologisms on the internet. The dynamism of language is often an indication that current language technology tools trained on today's data, may not be able to process the language in the future. Our resource could be (1) used to augment the WordNet, (2) used in several Natural Langua...

Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence of such lexical resources, multilingual topic models have been used to create coarse lexical resources in the past, using a Cartesian product approach. Our results show that for morphologically rich languages like H...

Sarcasm understandability or the ability to understand textual sarcasm depends upon readers' language proficiency, social knowledge, mental state and attentiveness. We introduce a novel method to predict the sarcasm understandability of a reader. Presence of incongruity in textual sarcasm often elicits distinctive eye-movement behavior by human rea...

Sarcasm understandability or the ability to understand tex-tual sarcasm depends upon readers' language proficiency, social knowledge, mental state and attentiveness. We introduce a novel method to predict the sarcasm understandability of a reader. Presence of incongruity in textual sarcasm often elicits distinctive eye-movement behavior by human re...

WordNet has proved to be immensely useful for Word Sense Disambiguation, and thence Machine translation, Information Retrieval and Question Answering. It can also be used as a dictionary for educational purposes. The semantic nature of concepts in a Word-Net motivates one to try to express this meaning in a more visual way. In this paper, we descri...

This paper reports the work of creating bilingual mappings in English for certain synsets of Hindi wordnet, the need for doing this, the methods adopted and the tools created for the task. Hindi wordnet, which forms the foundation for other In-dian language wordnets, has been linked to the English WordNet. To maximize linkages, an important strateg...

India is a country with 22 officially recognized languages and 17 of these have WordNets, a crucial resource. Web browser based interfaces are available for these WordNets, but are not suited for mobile devices which deters people from effectively using this resource. We present our initial work on developing mobile applications and browser extensi...

We present TransChat , an open source, cross platform, Indian language Instant Messaging (IM) application that facilitates cross lingual textual communication over English and multiple Indian Languages. The application is a client-server IM architecture based chat system with multiple Statistical Machine Translation (SMT) engines working towards ef...

Parallel corpora are often injected with bilingual dictionaries for improved Indian language machine translation (MT). In absence of such dictionaries, a coarse dictionary may be required. This paper demonstrates the use of a multilingual topic model for creating coarse dictionaries for English-Hindi MT. We compare our approaches with: (a) a baseli...

WordNet is an online lexical resource which expresses unique concepts in a language. English WordNet is the first WordNet which was developed at Princeton University. Over a period of time, many language WordNets were developed by various organizations all over the world. It has always been a challenge to store the WordNet data. Some WordNets are s...

WordNet is an online lexical resource which expresses unique concepts in a language. English WordNet is the first WordNet which was developed at Princeton University. Over a period of time, many language WordNets were developed by various organizations all over the world. It has always been a challenge to store the WordNet data. Some WordNets are s...

We present our work on developing fifteen Hierarchical Phrase Based Statistical Machine Translation (HPB-SMT) systems for five Indian language pairs namely Bengali-Hindi, English-Hindi, Marathi-Hindi, Tamil-Hindi, and Telugu-Hindi, in three domains each, HEALTH, TOURISM and GENERAL. We named them PanchBhoota, as these systems are elemental in natur...

We present a Parallel Corpora Management tool that aides parallel corpora generation for the task of Machine Translation (MT). It takes source and target text of a corpus for any language pair in text file format, or zip archives containing multiple corresponding text files. Then, it provides with a helpful interface to lexicographers for manual tr...

The task of Word Sense Disambiguation (WSD) incorporates in its definition the role of 'context'. We present our work on the development of a tool which allows for automatic acquisition and ranking of 'context clues' for WSD. These clue words are extracted from the contexts of words appearing in a large monolin-gual corpus. These mined collection o...

Word Sense Disambiguation (WSD) approaches have reported good accuracies in recent years. However, these approaches can be classified as weak AI systems. According to the classical definition, a strong AI based WSD system should perform the task of sense disambiguation in the same manner and with similar accuracy as human beings. In order to accomp...

Does context help determine sense? This question might seem frivolous, even preposterous to anybody sensible. However, our long time research on Word Sense Disambiguation (WSD) shows that in almost all disambigua-tion algorithms, the sense distribution parameter P(S/W), where P is the probability of the sense of a word W being S, plays the deciding...