Papers by Asif Ekbal

All-in-One: A Deep Attentive Multi-task Learning Framework for Humour, Sarcasm, Offensive, Motivation, and Sentiment on Memes (2020.aacl-main)

Challenge:	Existing methods to mitigate unintended bias in social media platforms are re-training and adding extra parameters to the model.
Approach:	They propose a technique to mitigate unintended bias in language models by pruning the neuron weights responsible for univ bias.
Outcome:	The proposed technique achieves fairness by pruning the neuron weights responsible for unintended bias without loss of original performance.

Copied to clipboard

Dushyant Singh Chauhan, Dhanush S R, Asif Ekbal, Pushpak Bhattacharyya

On the Way to Gentle AI Counselor: Politeness Cause Elicitation and Intensity Tagging in Code-mixed Hinglish Conversations for Social Good (2024.findings-naacl)

Challenge:	Empirical results show the efficacy of our proposed multi-task framework over existing state-of-the-art systems.
Approach:	They propose a multi-task, multi-modal deep learning framework to solve multiple tasks simultaneously.
Outcome:	The proposed framework performs better than existing state-of-the-art systems on a complicated form of information, i.e., memes.

Copied to clipboard

Priyanshu Priya, Gopendra Singh, Mauajama Firdaus, Jyotsna Agrawal, Asif Ekbal

Tagging

Challenge:	Politeness is a multifaceted concept influenced by individual perceptions of what is considered polite or impolite.
Approach:	They propose a task to identify the underlying reasons behind the use of politeness and gauge the degree of politity conveyed.
Outcome:	The proposed method is compared against state-of-the-art datasets and their results show it is superior.

Hope ‘The Paragraph Guy’ explains the rest : Introducing MeSum, the Meme Summarizer (2024.findings-emnlp)

Copied to clipboard

Anas Khan, Tanik Saikh, Arpan Phukan, Asif Ekbal

A Deep Transfer Learning Method for Cross-Lingual Natural Language Inference (2022.lrec-1)

Challenge:	a lack of large datasets for supervised learning and resource-intensive vision language models have hindered the development of meme comprehension.
Approach:	They propose a framework to bridge the gap between meme comprehension and vision language models by using a multimodal dataset.
Outcome:	The proposed framework outperforms existing methods in the meme comprehension test.

Copied to clipboard

Dibyanayan Bandyopadhyay, Arkadipta De, Baban Gain, Tanik Saikh, Asif Ekbal

DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions (P19-1)

Challenge:	Natural Language Inference (NLI) is a crucial task in AI and natural language processing.
Approach:	They propose an effective transfer learning approach for cross-lingual NLI . they perform experiments on English-Hindi language pairs in cross-linguistic setting .
Outcome:	The proposed model improves the baseline model by 10% over the state-of-the-art model.

Copied to clipboard

Tirthankar Ghosal, Rajeev Verma, Asif Ekbal, Pushpak Bhattacharyya

A Sentiment and Emotion Aware Multimodal Multiparty Humor Recognition in Multilingual Conversational Setting (2022.coling-1)

Challenge:	Existing peer review system is not straightforward and requires domain knowledge, expertise, and intelligence of human reviewers, which is somewhat elusive with the current state of AI.
Approach:	They propose to use peer review texts to predict acceptance or rejection of a manuscript based on reviewer sentiment.
Outcome:	The proposed deep neural architecture achieves significant performance improvement over baselines (29% error reduction) in a recently released dataset of peer reviews.

Copied to clipboard

Dushyant Singh Chauhan, Gopendra Vikram Singh, Aseem Arora, Asif Ekbal, Pushpak Bhattacharyya

Multi-Task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment (N18-2)

Challenge:	Humor is an essential aspect of daily conversation, and people try to provoke humor in their talks.
Approach:	They propose a multitask framework that annotates Hindi utterances with sentiment and emotion classes.
Outcome:	The proposed framework improves on the recently released Hindi Humor dataset . it takes sentiment and emotion into account to understand humor .

Copied to clipboard

Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya, Amit Sheth

Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders (P19-1)

Challenge:	In recent past, social media has emerged as an active platform in the context of healthcare and medicine.
Approach:	They propose to use a novel adversarial learning approach to capture medical sentiments expressed in a medical blog to analyze the user's opinions on health-related issues.
Outcome:	The proposed framework can capture the user's opinions on health-related issues at a medical blog level.

Copied to clipboard

Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

Multilinguality

Challenge:	Existing approaches to train multiple languages with a shared encoder and multiple decoders are based on denoising autoencoding of each language and back-translating between English and multiple non-English languages.
Approach:	They propose a multilingual unsupervised NMT scheme which trains multiple languages with a shared encoder and multiple decoders.
Outcome:	The proposed model performs better than the separately trained bilingual models on monolingual corpora and improves by 1.48 BLEU points on WMT test sets.

Just a Scratch: Enhancing LLM Capabilities for Self-harm Detection through Intent Differentiation and Emoji Interpretation (2025.acl-long)

Copied to clipboard

Soumitra Ghosh, Gopendra Vikram Singh, Shambhavi Shambhavi, Sabarna Choudhury, Asif Ekbal

EmoInHindi: A Multi-label Emotion and Intensity Annotated Dataset in Hindi for Emotion Recognition in Dialogues (2022.lrec-1)

Challenge:	Self-harm detection on social media is critical for early intervention and mental health support, yet remains challenging due to the subtle, context-dependent nature of such expressions.
Approach:	They propose a framework to distinguish intent through nuanced language–emoji interplay.
Outcome:	The proposed framework improves self-harm detection and explanation tasks on three state-of-the-art LLMs.

Copied to clipboard

Gopendra Vikram Singh, Priyanshu Priya, Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

MixRevDetect: Towards Detecting AI-Generated Content in Hybrid Peer Reviews. (2025.naacl-short)

Challenge:	Existing datasets for emotion recognition in dialogues are in English . existing datasets are limited to a few languages like Hindi .
Approach:	They propose a large conversational dataset in Hindi for multi-label emotion and intensity recognition in conversations . they use a Wizard-of-Oz manner to annotate dialogues with 16 emotion labels .
Outcome:	The proposed dataset contains 1,814 dialogues with 44,247 utterances in Hindi . it is based on a Wizard-of-Oz manner and can detect emotions in conversation .

Copied to clipboard

Sandeep Kumar, Samarth Garg, Sagnik Sengupta, Tirthankar Ghosal, Asif Ekbal

Challenge:	Existing methods for detecting fully AI-generated peer reviews fail to detect finer-grained AI-generated points within mixed-authorship reviews.
Approach:	They propose a method to identify AI-generated points in peer reviews using large language models . their approach achieved an F1 score of 88.86%, significantly outperforming existing methods .
Outcome:	The proposed method outperforms existing methods in identifying AI-generated points in peer reviews.

IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis (D18-1)

Copied to clipboard

Navonil Majumder, Soujanya Poria, Alexander Gelbukh, Md. Shad Akhtar, Erik Cambria, Asif Ekbal

A Unified Framework for Emotion Identification and Generation in Dialogues (2023.eacl-srw)

Challenge:	Aspect-based sentiment analysis is a new approach to extract aspect specific sentimental information from user feedback.
Approach:	They propose a method that incorporates neighboring aspects related information into the sentiment classification of a target aspect using memory networks.
Outcome:	The proposed method outperforms the state-of-the-art by 1.6% on average in restaurant and laptop domains.

Copied to clipboard

Avinash Madasu, Mauajama Firdaus, Asif Ekbal

ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos (2024.emnlp-main)

Challenge:	Social chatbots have gained immense popularity and can be used to develop and promote social chatbot applications.
Approach:	They propose a multi-task framework that jointly identifies the emotion of a given dialogue and generates response in accordance to the identified emotion.
Outcome:	The proposed framework outperforms current state-of-the-art models with classification and generation loss.

Copied to clipboard

Arpan Phukan, Manish Gupta, Asif Ekbal

Visual Data in NLP

Challenge:	Existing studies on question generation from videos are mostly focused on generating questions about common objects and attributes.
Approach:	They propose a model architecture combining Transformers, rich context signals and a combination of cross-entropy and contrastive loss function to encourage entity-centric question generation.
Outcome:	The proposed system yields BLEU, ROUGE, CIDEr, and METEOR scores of 71.3, 78.6, 7.31, and 81.9.

When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews (2026.findings-acl)

Copied to clipboard

Sandeep Kumar, Yash Kamdar, Abid Hossain, Bharti Kumari, Tanik Saikh, Asif Ekbal

Longform Multimodal Lay Summarization of Scientific Papers: Towards Automatically Generating Science Blogs from Research Articles (2024.lrec-main)

Challenge:	Existing approaches frame reviewer disagreement as binary contradiction detection over isolated sentence pairs, abstracting away review context and obscuring differences in severity of evaluative conflict.
Approach:	They propose a fine-grained formulation of reviewer contradiction analysis that operates over full peer reviews by explicitly identifying contradiction evidence spans and assigning graded disagreement intensity scores.
Outcome:	The proposed framework outperforms strong single-agent and generic multi-agend baselines in evidence identification and intensity agreement.

Copied to clipboard

Sandeep Kumar, Guneet Singh Kohli, Tirthankar Ghosal, Asif Ekbal

Summarization

Challenge:	Science blogs and lay-speak are critical to communicating scientific information to the general public and policymakers.
Approach:	They propose to use presentation transcripts and slides to generate a scientific blog from a research article in layperson's terms.
Outcome:	The proposed approach can generate a blog text and select the most relevant figures to explain a research article in layperson’s terms, essentially a science blog.

ABLE: Personalized Disability Support with Politeness and Empathy Integration (2024.emnlp-main)

Copied to clipboard

Kshitij Mishra, Manisha Burja, Asif Ekbal

Elevating Code-mixed Text Handling through Auditory Information of Words (2023.emnlp-main)

Challenge:	Adaptive, Bespoke, Listen and Empathetic is a conversational support system for physical disabilities that tracks user personas and provides personalized support according to user person preferences.
Approach:	They propose a conversational support system that tracks user personas and integrates politeness and empathy levels into responses to ensure that support interactions are tailored to each user's characteristics and preferences.
Outcome:	The proposed system is based on a conversational dataset enriched with user profile annotations and tested on 84 users with physical disabilities.

Copied to clipboard

Mamta Mamta, Zishan Ahmad, Asif Ekbal

RPTCS: A Reinforced Persona-aware Topic-guiding Conversational System (2023.eacl-main)

Challenge:	Current language models focus on the semantic representation of words and ignore the auditory phonetic features.
Approach:	They propose an approach to create language models for handling code-mixed textual data using auditory phonetic features from SOUNDEX using auditorian information.
Outcome:	The proposed approach improves robustness against adversarial attacks on code-mixed classification tasks and improves classification results over baselines.

Copied to clipboard

Zishan Ahmad, Kshitij Mishra, Asif Ekbal, Pushpak Bhattacharyya

A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning (2020.findings-emnlp)

Challenge:	Existing systems that control concept transitions in a conversation lack a persona-aware topic transition dataset.
Approach:	They propose a persona-aware topic-guiding conversational system that leads the conversation to drift to a set of target concepts depending on the persona of the speaker and the context of the conversation.
Outcome:	The proposed system produces fluent responses with no useful information and is based on a conversational dataset with a human-in-loop only quality checks.

Copied to clipboard

Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya

CM-Off-Meme: Code-Mixed Hindi-English Offensive Meme Detection with Multi-Task Learning by Leveraging Contextual Knowledge (2024.lrec-main)

Challenge:	Existing methods to train neural network-based models for code-mixing are limited due to language specificity of code-mixed text.
Approach:	They propose a deep learning approach to generate code-mixed text from English to multiple languages without any parallel data.
Outcome:	The proposed approach generates a code-mixed text from English to multiple languages without any parallel data.

Copied to clipboard

Gitanjali Kumari, Dibyanayan Bandyopadhyay, Asif Ekbal, Vinutha B. NarayanaMurthy

Contextual Inter-modal Attention for Multi-modal Sentiment Analysis (D18-1)

Challenge:	Existing studies on detecting offensive memes have focused on identifying them as implicit and explicit . detecting memes requires contextual knowledge, but there is no such dataset for the code-mixed Hindi-English domain.
Approach:	They propose an end-to-end multitask model that integrates contextual knowledge and psycho-linguistic knowledge to detect offensive memes.
Outcome:	The proposed model is able to detect offensive memes and explicit memes in a large-scale dataset.

Copied to clipboard

Deepanway Ghosal, Md Shad Akhtar, Dushyant Chauhan, Soujanya Poria, Asif Ekbal, Pushpak Bhattacharyya

Learning to Ask: Multi-Decoder Fine-Tuning for Multi-Hop Visual Question Generation with External Knowledge (2026.findings-eacl)

Challenge:	Existing methods for multi-modal sentiment analysis are limited due to the use of text, visual and acoustic inputs.
Approach:	They propose a recurrent neural network based multi-modal attention framework that leverages contextual information for utterance-level sentiment prediction.
Outcome:	The proposed framework performs better on two multi-modal sentiment analysis benchmark datasets with accuracies of 82.31% and 79.80% for the MOSI and MOSEI datasets.

Copied to clipboard

Arpan Phukan, Manish Gupta, Asif Ekbal

When Reviewers Lock Horns: Finding Disagreements in Scientific Peer Reviews (2023.emnlp-main)

Challenge:	Traditional supervised QG methods rely on tokenlevel alignment with fixed gold labels struggle to capture diverse valid question formulations.
Approach:	They propose a model-agnostic framework that integrates multimodal inputs with a multi-decoder architecture to optimize for multiple labels per sample.
Outcome:	The proposed framework improves fluency, reasoning depth, and relevance of visual questions.

Copied to clipboard

Sandeep Kumar, Tirthankar Ghosal, Asif Ekbal

Challenge:	despite being widely accepted standard for validating scholarly research, peer-review process has faced criticism.
Approach:	They propose a task of automatically identifying contradictions among reviewers on a given article.
Outcome:	The proposed model detects contradictory statements from the review pairs and makes it publicly available for further investigations.

Transfer Learning for Humor Detection by Twin Masked Yellow Muppets (2022.aacl-short)

Copied to clipboard

Aseem Arora, Gaël Dias, Adam Jatowt, Asif Ekbal

Novelty Goes Deep. A Deep Neural Solution To Document Level Novelty Detection (C18-1)

Challenge:	Existing humor classification systems have been dealing with different forms of humor independently.
Approach:	They propose to combine different forms of humor to tackle different humor types by a shared-private multitask architecture using a transfer learning paradigm.
Outcome:	The proposed architecture shows statistically significant improvements over baselines and accounting for new state-of-the-art figures for two datasets.

Copied to clipboard

Tirthankar Ghosal, Vignesh Edithal, Asif Ekbal, Pushpak Bhattacharyya, George Tsatsaronis, Srinivasa Satya Sameer Kumar Chivukula

Paraphrasing

Challenge:	Existing methods for document-level novelty detection are limited and do not require manual feature engineering.
Approach:	They propose a deep Convolutional Neural Networks based model to classify a document as novel or redundant on the basis of documents already seen by the system.
Outcome:	The proposed model outperforms the state-of-the-art on a document-level novelty detection dataset by a margin of 5% in terms of accuracy.

Unsupervised Aspect-Level Sentiment Controllable Style Transfer (2020.aacl-main)

Copied to clipboard

Mukuntha Narayanan Sundararaman, Zishan Ahmad, Asif Ekbal, Pushpak Bhattacharyya

MEISD: A Multimodal Multi-Label Emotion, Intensity and Sentiment Dialogue Dataset for Emotion Recognition and Sentiment Analysis in Conversations (2020.coling-main)

Challenge:	Unsupervised style transfer has been explored in text.
Approach:	They propose a system where aspect-level sentiments can be controlled at the output . they propose to use unsupervised techniques such as ABSA masked-language-modelling .
Outcome:	The proposed system is successful in controlling aspect-level sentiments.

Copied to clipboard

Mauajama Firdaus, Hardik Chauhan, Asif Ekbal, Pushpak Bhattacharyya

A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining (P19-1)

Challenge:	Emotion and sentiment classification in dialogues has gained popularity in recent times . a number of datasets are imbalanced in representing different emotions and consist of an only single emotion.
Approach:	They propose to use a dataset to analyze emotions and sentiments in dialogues . they use text, audio and video to identify the correct emotions with the appropriate intensity and sentiment in an utterance of a dialogue .
Outcome:	The proposed datasets are balanced in representing different emotions and consist of only one emotion.

Copied to clipboard

Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya

Ordinal and Attribute Aware Response Generation in a Multimodal Dialogue System (P19-1)

Challenge:	Existing methods of identifying ADRs are reliable but time-consuming and offer a limited amount of ADR relevant information.
Approach:	They propose a neural network-inspired multi-task learning framework that can simultaneously extract ADRs from various sources.
Outcome:	The proposed framework achieves state-of-the-art performance on three publicly available real-world benchmark pharmacovigilance datasets, a Twitter dataset from PSB 2016 Social Me- dia Shared Task, CADEC corpus and Medline ADR corpus.

Copied to clipboard

Hardik Chauhan, Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

Standardizing Distress Analysis: Emotion-Driven Distress Identification and Cause Extraction (DICE) in Multimodal Online Posts (2023.emnlp-main)

Challenge:	Existing multimodal dialogue systems are based on unimodal sources, capturing information from text and image.
Approach:	They propose a position and attribute aware attention mechanism to learn enhanced image representation conditioned on the user utterance.
Outcome:	The proposed model outperforms the state-of-the-art models on text similarity metrics.

Copied to clipboard

Gopendra Singh, Soumitra Ghosh, Atul Verma, Chetna Painkra, Asif Ekbal

Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs (2026.acl-long)

Challenge:	Existing methods for identifying hate speech have been limited to analyzing textual content.
Approach:	They propose a method for distress identification and cause extraction from social media posts using emotional information.
Outcome:	The proposed method improves F1 and ROS scores by 1.95% and 3% relative to the best-performing baseline.

Copied to clipboard

Deepak Kumar, Baban Gain, Asif Ekbal

MedLogic-AQA: Enhancing Medicare Question Answering with Abstractive Models Focusing on Logical Structures (2024.findings-emnlp)

Challenge:	Spontaneous speech is rarely fluent, and disfluencies can degrade readability and reliability . a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning .
Approach:	They propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens . they add a contrastive learning objective that penalizes the reproduction of disfluency tokens.
Outcome:	The proposed model improves readability and reliability of ASR transcripts in three languages . disfluencies can cause misinterpretations, incoherent responses, poor user experience .

Copied to clipboard

Aizan Zafar, Kshitij Mishra, Asif Ekbal

MENDER: Multi-hop Commonsense and Domain-specific CoT Reasoning for Knowledge-grounded Empathetic Counseling of Crime Victims (2025.naacl-srw)

Challenge:	Existing question-answering systems struggle to capture intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers.
Approach:	They propose a system that harnesses first-order logic-based rules extracted from context and questions to generate well-grounded answers.
Outcome:	The proposed system generates well-grounded answers based on first-order logic-based rules extracted from context and questions.

Copied to clipboard

Abid Hossain, Priyanshu Priya, Armita Mani Tripathi, Pradeepika Verma, Asif Ekbal

Reinforced Multi-task Approach for Multi-hop Question Generation (2020.coling-main)

Challenge:	Experimental evaluations on counseling dialogue dataset, POEM validate MENDER’s efficacy in generating coherent, knowledge-grounded responses.
Approach:	They propose a multi-hop commonsensE and domaiN-specific Chain-of-Thought reasoning framework that integrates commonsense and domain knowledge via multi-hopping reasoning over the dialogue context.
Outcome:	Experimental evaluations on counseling dialogue dataset validate MENDER’s efficacy in generating coherent, empathetic, knowledge-grounded responses.

Copied to clipboard

Deepak Gupta, Hardik Chauhan, Ravi Tej Akella, Asif Ekbal, Pushpak Bhattacharyya

Low-Resource NLP

Challenge:	Empirical evaluation shows our model to outperform the single-hop question generation models on both automatic evaluation metrics such as BLEU, METEOR, and ROUGE and human evaluation metrics for quality and coverage of the generated questions.
Approach:	They propose a question-aware reward function to maximize the utilization of supporting facts in the context.
Outcome:	The proposed model outperforms single-hop neural question generation models on automatic evaluation metrics and human evaluation metrics for quality and coverage of the generated questions.

INA: An Integrative Approach for Enhancing Negotiation Strategies with Reward-Based Dialogue Agent (2023.findings-emnlp)

Copied to clipboard

Zishan Ahmad, Suman Saurabh, Vaishakh Menon, Asif Ekbal, Roshni Ramnani, Anutosh Maitra

MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi (L18-1)

Challenge:	a novel negotiation agent is designed for the online marketplace . a dialogue agent can negotiate on price and other factors .
Approach:	They propose a novel negotiation agent that is integrative in nature and can negotiate on price and other factors.
Outcome:	The proposed agent is integrative in nature and can negotiate on price and other factors.

Copied to clipboard

Deepak Gupta, Surabhi Kumari, Asif Ekbal, Pushpak Bhattacharyya

Question Answering

Challenge:	Existing work on multi-domain, multi-lingual question answering is limited to the same language.
Approach:	They curate 500 articles in six different domains from the web and create question-answer pairs . they develop a deep learning based model for classifying an input question into coarse and finer categories .
Outcome:	The proposed model accuracies 90.12% and 80.30% for coarse and finer classes . the proposed model is the first attempt to create multi-domain, multi-lingual question answering evaluation involving English and Hindi.

Incorporating Politeness across Languages in Customer Care Responses: Towards building a Multi-lingual Empathetic Dialogue Agent (2020.lrec-1)

Copied to clipboard

Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

A Unified Framework for Multilingual and Code-Mixed Visual Question Answering (2020.aacl-main)

Challenge:	Qualitative and quantitative analysis shows that our proposed model can converse in both the languages and the information shared between the languages helps in improving the performance of the overall system.
Approach:	They propose a deep learning framework that can handle different languages and incorporate courteous behaviour in generic customer care responses in a multi-lingual scenario.
Outcome:	The proposed model can converse in both languages and the information shared between the languages helps in improving the overall performance of the system.

Copied to clipboard

Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya

Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework (2024.emnlp-main)

Challenge:	Existing techniques for visual question answering focus on English questions, but many applications require a multilingual module.
Approach:	They propose a deep learning framework for multilingual and code- mixed visual question answering . they create Hindi and Code-mixed VQA datasets by exploiting linguistic properties of these languages .
Outcome:	The proposed model is capable of predicting answers from the questions in Hindi, English or Code- mixed (Hindi-English) languages.

Copied to clipboard

Gopendra Singh, Sai Vemulapalli, Mauajama Firdaus, Asif Ekbal

Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)

Challenge:	Cognitive distortion research sheds light on pervasive errors in thinking patterns . authors present method for detecting and reasoning about cognitive distortions .
Approach:	They propose a method for detecting and reasoning about cognitive distortions using Large Language Models.
Outcome:	The proposed method improves accuracy and depth of detection and reasoning tasks in a zero-shot manner.

Copied to clipboard

Deeksha Varshney, Asif Ekbal, Pushpak Bhattacharyya

COMMA-DEER: COmmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations (2022.coling-1)

Challenge:	Recent research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences.
Approach:	They propose to use a self-attention based encoder and a decoder with dot product attention mechanism to generate a viable response with a specified emotion.
Outcome:	The proposed model outperforms baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses.

Copied to clipboard

Soumitra Ghosh, Gopendra Vikram Singh, Asif Ekbal, Pushpak Bhattacharyya

Unintended Bias Detection and Mitigation in Misogynous Memes (2024.eacl-long)

Challenge:	Mental health is a critical component of the United Nations’ Sustainable Development Goals (SDGs), particularly Goal 3 which aims to provide “good health and well-being”.
Approach:	They propose a task of detecting emotional reasoning and accompanying emotions in conversations that is manually annotated at the utterance level.
Outcome:	The proposed model achieves 6% accuracy and 4.62% accuracy on the emotion detection task and 3.56% accuracy, and 3.31% F1 on the ER detection task, compared to the existing state-of-the-art model.

Copied to clipboard

Gitanjali Kumari, Anubhav Sinha, Asif Ekbal

M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought (2024.emnlp-main)

Challenge:	Existing models that detect misogyny are not able to detect unintended biases in memes, perpetuating harmful stereotypes and reinforcing negative attitudes.
Approach:	They propose to measure and mitigate unintentional bias in misogynous memes detection models by using a contextualized scene graph-based multimodal network (CTXSGMNet) they also evaluate their generalizability by evaluating their performance on a few benchmark meme datasets.
Outcome:	The proposed model achieves state-of-the-art performance on the SemEval-2022 Task 5 (MAMI task) dataset, showcasing its promising performance in terms of Equity of Odds and F1 score.

Copied to clipboard

Gitanjali Kumari, Kirtan Jain, Asif Ekbal

HindiMD: A Multi-domain Corpora for Low-resource Sentiment Analysis (2022.lrec-1)

Challenge:	Recent studies have shown that Large Language Models (LLMs) neglect cultural diversity and key aspects like emotion and contextual knowledge hidden in the visual modalities.
Approach:	They propose a framework for misogynous meme identification using a multimodal multimodal prompting principle and a CLIP-based classifier.
Outcome:	The proposed framework performs well on the SemEval-2022 task 5 dataset, and is generalizable across different datasets.

Copied to clipboard

null Mamta, Asif Ekbal, Pushpak Bhattacharyya, Tista Saha, Alka Kumar, Shikha Srivastava

Adversarial Sample Generation for Aspect based Sentiment Classification (2022.findings-aacl)

Challenge:	Social media platforms such as Twitter and Facebook are a new channel of information dissemination for many negative groups for recruitment.
Approach:	They propose to use a social media sentiment analysis corpus annotated with the sentiment classes positive, negative and neutral to investigate the polarity of user-expressed opinions.
Outcome:	The proposed model is based on a set of benchmark datasets for sentiment analysis across a range of domains and languages.

Copied to clipboard

null Mamta, Asif Ekbal

Sentence Level Temporality Detection using an Implicit Time-sensed Resource (L18-1)

Challenge:	Existing approaches to attack adversarial samples in natural language processing are ineffective . initial attacks perturb characters or words in sentences, resulting in grammatical incorrect or out-of-context sentences.
Approach:	They propose an attack algorithm that generates adversarial samples for a given aspect, maintaining more semantic coherency.
Outcome:	The proposed method outperforms the state-of-the-art methods in perturbation ratio, success rate, and semantic coherence.

Copied to clipboard

Sabyasachi Kamila, Asif Ekbal, Pushpak Bhattacharyya

Tagging

Challenge:	Temporal sense detection of any word is an important aspect for detecting temporality at the sentence level.
Approach:	They build a temporal resource based on a semi-supervised learning approach . they use past, present, future, neutral and atemporal senses to tag sentences .
Outcome:	The proposed resource is based on a semi-supervised learning approach . it is used to tag sentences with past, present and future temporal senses .

Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes (2024.findings-emnlp)

Copied to clipboard

Dibyanayan Bandyopadhyay, Mohammed Hasanuzzaman, Asif Ekbal

Courteously Yours: Inducing courteous behavior in Customer Care responses using Reinforced Pointer Generator Network (N19-1)

Challenge:	Existing models for detecting offensive memes lack transparency and are often unreliability in safety-critical applications.
Approach:	They propose a framework that uses a Structural Causal Model to predict the class of an input meme based on meme input and causal concepts, allowing for transparent interpretation.
Outcome:	The proposed framework is able to predict class of an input meme based on meme input and causal concepts, allowing for transparent interpretation.

Copied to clipboard

Hitesh Golchha, Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

e-THERAPIST: I suggest you to cultivate a mindset of positivity and nurture uplifting thoughts (2023.emnlp-main)

Challenge:	In order to ensure customer satisfaction and retention, it is imperative for customer care agents and chatbots to be cordial and emphatic to the customer.
Approach:	They propose a deep learning framework that automatically transforms neutral customer care responses into courteous replies by stylistic transfer.
Outcome:	The proposed model can generate courteous expressions consistent with the emotional state of the customer while preserving the content.

Copied to clipboard

Kshitij Mishra, Priyanshu Priya, Manisha Burja, Asif Ekbal

TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection (L18-1)

Challenge:	Existing mental health workforce is struggling to meet the needs adequately.
Approach:	They propose a novel polite interpersonal psychotherapy dialogue system that is annotated at two levels: dialogue-level and utterance-level.
Outcome:	The proposed system can address depression, anxiety, schizophrenia and other mental health issues.

Copied to clipboard

Tirthankar Ghosal, Amitra Salam, Swati Tiwari, Asif Ekbal, Pushpak Bhattacharyya

Multi-domain Tweet Corpora for Sentiment Analysis: Resource Creation and Evaluation (2020.lrec-1)

Challenge:	Detecting novelty of an entire document is an AI frontier problem . present state-of-the-art text matching techniques are unable to process such redundancy.
Approach:	They propose a document-level novelty detection resource that can be used to benchmark techniques . they crawl news documents across several domains and use it to find out whether they contain new information .
Outcome:	The proposed dataset is compared with a standard system for document novelty detection . the proposed system can detect elements that have not appeared before, or new or original .

Copied to clipboard

null Mamta, Asif Ekbal, Pushpak Bhattacharyya, Shikha Srivastava, Alka Kumar, Tista Saha

EM-PERSONA: EMotion-assisted Deep Neural Framework for PERSONAlity Subtyping from Suicide Notes (2022.coling-1)

Challenge:	a huge amount of content is being generated every day due to the pervasiveness of social media.
Approach:	They firstly create a multi-domain tweet sentiment corpora and then establish a deep neural network based baseline framework to address the above mentioned issues.
Outcome:	The proposed dataset achieves 84.65% accuracy for sentiment analysis using a neural network, long short term memory, and gated recurrent unit (GRU).

Copied to clipboard

Soumitra Ghosh, Dhirendra Kumar Maurya, Asif Ekbal, Pushpak Bhattacharyya

Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation (2022.naacl-main)

Challenge:	Suicide continues to be one of the significant causes of death worldwide . EMotion-assisted personality subtyping is a novel approach to identify personality traits from suicide notes .
Approach:	They propose to use a PERSONAlity Detection Framework to identify personality traits from suicide notes and annotate them using a benchmark dataset.
Outcome:	The proposed method outperforms baselines on comprehensive evaluation using multiple state-of-the-art systems.

Copied to clipboard

Deeksha Varshney, Akshara Prabhakar, Asif Ekbal

‘Quis custodiet ipsos custodes?’ Who will watch the watchmen? On Detecting AI-generated peer-reviews (2024.emnlp-main)

Challenge:	Empirical results show that our proposed model outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment.
Approach:	They propose a model which uses large-scale commonsense and named entity based knowledge to ground dialogue on external knowledge and topic-specific knowledge associated with each utterance.
Outcome:	The proposed model outperforms the state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Sandeep Kumar, Mohit Sahu, Vardhan Gacche, Tirthankar Ghosal, Asif Ekbal

Robustness in NLP

Challenge:	Recent studies have focused on generic AI-generated text detection or estimating fraction of peer-reviews that can be AI-generated.
Approach:	They propose a model that detects whether a peer-review is written by ChatGPT and a reviewer-generated model that generates similar outputs upon re-prompting.
Outcome:	The proposed model is more robust, but paraphrasing is more effective.

MMM: An Emotion and Novelty-aware Approach for Multilingual Multimodal Misinformation Detection (2022.findings-aacl)

Copied to clipboard

Vipin Gupta, Rina Kumari, Nischal Ashok, Tirthankar Ghosal, Asif Ekbal

Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation (2021.findings-emnlp)

Challenge:	Increasing presence of multimedia content on the web promotes misinformation . detecting this category of misleading information is almost impossible without prior knowledge .
Approach:	They propose a novel multilingual multimodal misinformation dataset that includes background knowledge of misleading articles.
Outcome:	The proposed model outperforms the state-of-the-art on misinformation detection task.

Copied to clipboard

Humair Raj Khan, Deepak Gupta, Asif Ekbal

PAL to Lend a Helping Hand: Towards Building an Emotion Adaptive Polite and Empathetic Counseling Conversational Agent (2023.acl-long)

Challenge:	Existing methods for training language-vision models only consider monolingual learning, especially English.
Approach:	They propose to extend an English language-vision model into a multilingual and code-mixed model by using knowledge distillation techniques.
Outcome:	The proposed model outperforms existing models on multilingual and code-mixed VQA datasets on eleven languages.

Copied to clipboard

Kshitij Mishra, Priyanshu Priya, Asif Ekbal

MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation (2025.findings-acl)

Challenge:	The social stigma associated with mental illness prevents individuals from addressing their issues and getting assistance.
Approach:	They propose to build a Polite and empAthetic conversational agent PAL to lay down the counseling support to substance addicts and crime victims.
Outcome:	The proposed agent is scalable and can be easily modified with different modules of preference models as per need.

Copied to clipboard

Gitanjali Kumari, Jitendra Solanki, Asif Ekbal

Visual Data in NLP

Challenge:	Toxic memes spread harmful and offensive content and pose a significant challenge in online environments.
Approach:	They propose a framework to mitigate toxicity in toxic memes by leveraging a set of pre-trained models that can interpret the visual and textual components of memes.
Outcome:	The proposed framework reduces toxicity on publicly available meme datasets by 10-20% compared to the previous methods.

We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism (2025.findings-emnlp)

Copied to clipboard

Priyanshu Priya, Saurav Dudhate, Desai Vishesh Yasheshbhai, Asif Ekbal

Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality (N18-1)

Challenge:	Argumentation mechanisms are integrated into negotiation dialogue systems to improve conflict resolution and adaptability.
Approach:	They propose a dataset of Argumentation Profile, Preference Profile, and Buying Style Profiles to generate personality-driven dialogues in negotiation dialogue systems.
Outcome:	The proposed task improves argumentation mechanisms and adaptability by aligning interactions with individuals’ preferences and styles.

Copied to clipboard

Md Shad Akhtar, Palaash Sawant, Sukanta Sen, Asif Ekbal, Pushpak Bhattacharyya

Can Large Language Models Unlock Novel Scientific Research Ideas? (2025.emnlp-main)

Challenge:	Efficient word representations play an important role in solving various problems related to NLP, data mining, text mining etc.
Approach:	They propose to leverage bilingual word embeddings learned through a parallel corpus to minimize the effect of data sparsity.
Outcome:	The proposed model is tested against state-of-the-art methods in two experimental setups.

Copied to clipboard

Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif Ekbal

Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain (2022.lrec-1)

Challenge:	Large Language Models (LLMs) and ChatGPT have marked a turning point in the integration of Artificial Intelligence (AI) into people’s everyday lives.
Approach:	They conduct a human evaluation of the novelty, relevancy, and feasibility of the generated future research ideas.
Outcome:	The proposed models generate more diverse ideas than GPT-4, GPT-3.5, and Gemini 1.0.

Copied to clipboard

Ankush Agarwal, Raj Gite, Shreya Laddha, Pushpak Bhattacharyya, Satyanarayan Kar, Asif Ekbal, Prabhjit Thind, Rajesh Zele, Ravi Shankar

PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation (2022.coling-1)

Challenge:	Existing Question Answering systems for commercial aviation use a large number of documents . a Knowledge Graph (KG) guided Deep Learning (DL) based system can be used to query the documents based on accident reports .
Approach:	They propose a Knowledge Graph (KG) guided Deep Learning (DL) based Question Answering system to cater to these requirements.
Outcome:	The proposed system achieves 7% and 40% increase in accuracy over existing systems.

Copied to clipboard

Kshitij Mishra, Azlaan Mustafa Samad, Palak Totala, Asif Ekbal

Sentiment and Emotion help Sarcasm? A Multi-task Learning Framework for Multi-Modal Sarcasm, Sentiment and Emotion Analysis (2020.acl-main)

Challenge:	Empathy plays a crucial role in mediating the persuasive effects as it evokes cognitive and emotional processing conducive to persuasion.
Approach:	They propose to use a maximum likelihood estimate loss based model to design an efficient reward function consisting of five sub rewards viz. persuasion, emotion, Politeness-Strategy Consistency, Dialogue-Coherence and Non-repetitiveness.
Outcome:	The proposed system increases the rate of persuasive responses with emotion and politeness acknowledgement compared to the current state-of-the-art dialogue models while maintaining the linguistic quality.

Copied to clipboard

Dushyant Singh Chauhan, Dhanush S R, Asif Ekbal, Pushpak Bhattacharyya

TRIP NEGOTIATOR: A Travel Persona-aware Reinforced Dialogue Generation Model for Personalized Integrative Negotiation in Tourism (2024.findings-emnlp)

Challenge:	Existing systems for sarcasm detection are limited by the use of sarcasm . sarasm is often used to convey thinly veiled disapproval humorously.
Approach:	They propose a multi-task deep learning framework to solve sarcasm problems simultaneously . they manually annotate a sarcsm dataset with sentiment and emotion classes .
Outcome:	The proposed framework is able to solve sarcasm, sentiment and emotion problems in a multi-modal conversational scenario.

Copied to clipboard

Priyanshu Priya, Desai Yasheshbhai, Ratnesh Joshi, Roshni Ramnani, Anutosh Maitra, Shubhashis Sengupta, Asif Ekbal

Transforming Code Understanding: Clustering-Based Retrieval for Improved Summarization in Domain-Specific Languages (2025.coling-industry)

Challenge:	Incorporating traveler preferences, constraints, and expectations allows for customizing negotiation strategies, resulting in a more personalized and integrative experience.
Approach:	They propose a novel travel persona-aware Reinforced dIalogue generation model for personalized integrative negotiation in the tourism domain.
Outcome:	The proposed system generates coherent and diverse responses consistent with the traveler's personality.

Copied to clipboard

Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee, Aryan Sahoo, Saswati Dana, Palanivel Kodeswaran, Sayandeep Sen, Asif Ekbal, Dinesh Garg

PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues (2026.acl-long)

Challenge:	Existing natural language summaries of domain-specific languages are limited due to their recency and complexity.
Approach:	They propose a clustering-based technique to retrieve in-context examples that are semantically closer to the test example and propose eBPF prompt generation technique that yields superior-quality code summary generation.
Outcome:	The proposed method improves the eBPF code summarization accuracy by 12.9 BLEU points over other prompting techniques.

Copied to clipboard

Prajwal Vijay Kajare, Priyanshu Priya, Bikash Santra, Asif Ekbal

A Deep Neural Network based Approach for Entity Extraction in Code-Mixed Indian Social Media Text (L18-1)

Challenge:	Emotion plays a pivotal role in shaping negotiation outcomes, influencing trust, cooperation, and long-term relationships.
Approach:	They propose an Emotion-aware Negotiation Strategy-informed Chain-of-Thought reasoning mechanism which mimics human negotiation by perceiving, understanding, using, and managing emotions.
Outcome:	The proposed system generates interpretable emotions and improves negotiation effectiveness on job interviews and resource allocation datasets.

Copied to clipboard

Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya

Context-aware Interactive Attention for Multi-modal Sentiment and Emotion Analysis (D19-1)

Challenge:	a huge number of people use social media to express and exchange information in their own languages.
Approach:	They propose to use a code-mixed environment to extract higher level features from text . they use 'gadget' algorithm that automatically discovers higher level feature from text.
Outcome:	The proposed approach is generic and does not make use of handcrafted features or rules.

Copied to clipboard

Dushyant Singh Chauhan, Md Shad Akhtar, Asif Ekbal, Pushpak Bhattacharyya

Medical Sentiment Analysis using Social Media: Towards building a Patient Assisted System (L18-1)

Challenge:	Multi-modal analysis is a field emerging in the fields of natural language processing, computer vision and speech processing . multimodal analysis uses a variety of information from multiple sources to build efficient systems . acoustic and visual information can provide better information for classification decisions .
Approach:	They propose a recurrent neural network based approach for multi-modal sentiment and emotion analysis . they employ a context-aware attention module to exploit the correspondence among neighboring utterances .
Outcome:	The proposed model learns inter-modal interaction among participating modalities through auto-encoder mechanism . it is compared with existing state-of-the-art models on five standard multi-modal affect analysis datasets .

Copied to clipboard

Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya

CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation (2022.emnlp-main)

Challenge:	a study conducted by the pew Internet & American Life Project 1 shows that almost 80 percent of Internet users have explored health-related topic online.
Approach:	They propose to crawl medical forums with opinions about medical condition self narrated by users.
Outcome:	The proposed system is based on opinions about medical condition self-narrated by users on medical forums.

Copied to clipboard

Deeksha Varshney, Aizan Zafar, Niranshu Behera, Asif Ekbal

ScholarlyRead: A New Dataset for Scientific Article Reading Comprehension (2020.lrec-1)

Challenge:	Prior research has provided a single poorly graded label for the entire utterance, which may mislead model training and/or lead to erroneous assessment.
Approach:	They propose to use telemedicine to carry on a natural conversation and understand the meanings of words to respond with a coherent dialog.
Outcome:	telemedicine has been shown to be effective in carrying on a natural conversation and understanding the meanings of words to respond with a coherent dialog.

Copied to clipboard

Tanik Saikh, Asif Ekbal, Pushpak Bhattacharyya

A Platform for Event Extraction in Hindi (2020.lrec-1)

Challenge:	Existing studies on MRC on scholarly articles have focused on general domain datasets of news articles and elementary school-level storybooks.
Approach:	They propose to generate automatic questions from span-of-word-based scholarly articles’ Reading Comprehension dataset with approximately 10K manually checked passage-question-answer instances.
Outcome:	The proposed model yields the F1 score of 37.31% and is useful for building Question-Answering (QA) systems on scientific articles.

Copied to clipboard

Sovan Kumar Sahoo, Saumajit Saha, Asif Ekbal, Pushpak Bhattacharyya

Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards (2023.findings-emnlp)

Challenge:	Event Extraction is an important task in the widespread field of NLP, but there is no benchmark setup in Hindi.
Approach:	They propose an Event Extraction framework for Hindi language and develop deep learning based models to set as the baselines.
Outcome:	The proposed framework crawls more than seventeen hundred disaster related Hindi news articles from various news sources.

Copied to clipboard

Baban Gain, Ramakrishna Appicharla, Soumya Chennabasavaraj, Nikesh Garera, Asif Ekbal, Muthusamy Chelliah

Multilinguality

Challenge:	Creating a synthetic parallel corpus from noisy data is also difficult due to its noisy nature.
Approach:	They propose a training methodology that fine-tunes the NMT system only using source-side data to balance adequacy and fluency.
Outcome:	The proposed method surpasses the MLE-based fine-tuning approach by achieving a 1.9 BLEU improvement.

PoliSe: Reinforcing Politeness Using User Sentiment for Customer Care Response Generation (2022.coling-1)

Copied to clipboard

Mauajama Firdaus, Asif Ekbal, Pushpak Bhattacharyya

Text Generation

Challenge:	Human-machine interactions have increased rapidly assisting humans in their everyday lives.
Approach:	They propose to automatically identify the sentiment of the user and transform the neutral responses into polite responses conforming to the sentiment and the conversational history.
Outcome:	The proposed approach achieves superior performance compared to baseline models.

Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis (N19-1)

Copied to clipboard

Md Shad Akhtar, Dushyant Chauhan, Deepanway Ghosal, Soujanya Poria, Asif Ekbal, Pushpak Bhattacharyya

MultiDM-GCN: Aspect-guided Response Generation in Multi-domain Multi-modal Dialogue System using Graph Convolutional Network (2020.findings-emnlp)

Challenge:	Existing frameworks for sentiment and emotion analysis are not efficient for inter-task learning.
Approach:	They propose a multi-task learning framework that performs sentiment and emotion analysis together.
Outcome:	The proposed framework improves on a CMU-MOSEI dataset for sentiment and emotion analysis.

Copied to clipboard

Mauajama Firdaus, Nidhi Thakur, Asif Ekbal

Fine-Grained Temporal Orientation and its Relationship with Psycho-Demographic Correlates (N18-1)

Challenge:	Existing research suggests that engaging conversations include visual cues (e.g., a video or images) or audio cue.
Approach:	They propose a multi-modal conversational framework that generates the responses following the different aspects of a product or service to cater to the user's needs.
Outcome:	The proposed framework outperforms baselines for the task-oriented dialogue setup.

Copied to clipboard

Sabyasachi Kamila, Mohammed Hasanuzzaman, Asif Ekbal, Pushpak Bhattacharyya, Andy Way

Text Classification

Challenge:	Temporal orientation refers to an individual’s tendency to connect to the psychological concepts of past, present or future and affects personality, motivation, emotion, decision making and stress coping processes.
Approach:	They propose to use a minimally supervised method to classify tweets in one of three temporal categories, past, present, and future, and a deep bi-directional long-term memory (BLSTM) to measure correlation between sentiment view of temporal orientation and different psycho-demographic factors.
Outcome:	The proposed method achieves 78.27% accuracy on a manually created test set.

MedEx: Enhancing Medical Question-Answering with First-Order Logic based Reasoning and Knowledge Injection (2025.coling-main)

Copied to clipboard

Aizan Zafar, Kshitij Mishra, Asif Ekbal

Structured Data in NLP

Challenge:	Existing knowledge triples are ineffective in medical question-answering because of superfluous data and inability to capture complex relationships between symptoms and treatments.
Approach:	They propose a first-order logical reasoning model that uses First-Order Logic to model intricate relationships between diseases and treatments.
Outcome:	The proposed model captures the interplay of symptoms, diseases, and treatments, enhancing context comprehension.

Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems (2022.findings-naacl)

Copied to clipboard

Azlaan Mustafa Samad, Kshitij Mishra, Mauajama Firdaus, Asif Ekbal

Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy (C18-1)

Challenge:	Existing models for persuasive dialogue lack emotion annotated data, so we use transformers to provide emotion based feedbacks to our RL agent.
Approach:	They propose to use a language model to generate empathetic persuasive dialogues . they annotate existing data with emotions and build transformers to provide feedbacks based on emotion.
Outcome:	The proposed model increases the rate of generating persuasive responses compared to state-of-the-art models while maintaining the language quality.

Copied to clipboard

Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, Shubhashis Sengupta

Question Answering

Challenge:	Existing QA systems that answer factual questions with short answers are rare in practice.
Approach:	They propose a proposed two-layered taxonomy technique for semantic question matching . they augment state-of-the-art deep learning models with question classes from a deep learning based question classifier .
Outcome:	The proposed technique achieves state-of-the-art on an open-domain dataset.

Knowledge-enhanced Response Generation in Dialogue Systems: Current Advancements and Emerging Horizons (2024.lrec-tutorials)

Copied to clipboard

Priyanshu Priya, Deeksha Varshney, Mauajama Firdaus, Asif Ekbal