Papers by Md Shad Akhtar

14 papers
Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation (2025.findings-naacl)

Copied to clipboard

Challenge: Existing systems that generate sarcastic explanations neglect the significance of the intended irony in generating them.
Approach: They propose a multimodal sarcasm explanation that leverages the inter-modality relationships between an image and its caption to learn the intended irony for explanations.
Outcome: The proposed model outperforms existing models on the sarcastic post-processing task and shows that it is more accurate than existing models.
Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech (2024.findings-acl)

Copied to clipboard

Challenge: Existing language models to generate implicit hate explanations are lacking in many fields.
Approach: They propose to use language models to generate explicit hate posts to make it clear . they find that simpler models incorporating external toxicity signals outperform KG-infused models .
Outcome: The proposed setup produces more precise explanations than zero-shot GPT-3.5, highlighting the intricate nature of the task.
Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit remarkable capabilities in various generative tasks, but their adaptation to domain-specific intricacies remains challenging.
Approach: They propose to use a planning engine to orchestrate structuring knowledge alignment to achieve high-order planning by encapsulating domain knowledge and leveraging sheaf convolution learning to enhance its understanding of the dialogue’s structural nuances.
Outcome: The proposed framework improves on existing LLMs and shows that it can generate better summaries with better quality and better execution.
Probing Critical Learning Dynamics of PLMs for Hate Speech Detection (2024.findings-eacl)

Copied to clipboard

Challenge: Existing studies on pretrained language models (PLMs) for hate speech detection have not investigated how their performance is affected by pretraining and finetuning.
Approach: They propose to compare pretrained language models, evaluate their seed robustness, finetuning settings, and the impact of pretraining data collection time.
Outcome: The proposed models show that they are more robust than other models and that they have a better chance of performing better than domain-specific models.
DISARM: Detecting the Victims Targeted by Harmful Memes (2022.findings-naacl)

Copied to clipboard

Challenge: DISARM is a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to and then incorporates a novel contextualized deep neural network to classify whether the meme intends to harm these entities.
Approach: They propose a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to and incorporates a novel contextualized deep neural network to classify whether the meme intends to harm them.
Outcome: The proposed framework outperforms 10 unimodal and multimodal systems and reduces error rate of harmful target identification by 9 % absolute over baseline systems.
Contextual Inter-modal Attention for Multi-modal Sentiment Analysis (D18-1)

Copied to clipboard

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.
When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues (2022.acl-long)

Copied to clipboard

Challenge: Indirect speech achieves a constellation of discourse goals in human communication, but it is challenging for AI agents to comprehend such idiosyncrasies.
Approach: They propose a task to generate natural language explanations of satirical conversations using a multimodal and code-mixed dataset to capture multimodality.
Outcome: The proposed task generates natural language explanations of satirical conversations in a multimodal and code-mixed setting and surpasses baselines on almost all metrics.
Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities (2025.findings-emnlp)

Copied to clipboard

Challenge: Empirical results across four notable language models demonstrate significant improvements in attribute elicitation and user engagement.
Approach: They propose a framework that identifies and prompts users to enrich their posts by eliciting missing support attributes.
Outcome: The proposed framework improves engagement and elicits missing information from posts.
No perspective, no perception!! Perspective-aware Healthcare Answer Summarization (2024.findings-acl)

Copied to clipboard

Challenge: Healthcare Community Question Answering forums are prone to off-topic discussions and diverse answers can be challenging for readers to sift through.
Approach: They propose a task of perspective-specific answer summarization to identify different perspectives within healthcare-related responses and frame a perspective-driven abstractive summary covering all responses.
Outcome: The proposed model outperforms existing models against five baselines and shows that it is more accurate than existing models.
Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF (2024.naacl-long)

Copied to clipboard

Challenge: Existing systems that target hate speech with intent-conditioned counterspeech generate better results with longer contexts.
Approach: They propose a framework that enables counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements.
Outcome: The proposed framework outperforms existing benchmarks in intent-conditioned counterspeech generation.
Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation (2026.acl-long)

Copied to clipboard

Challenge: Recent systems exhibit conversational competence but lack structured mechanisms to evaluate adherence to core therapeutic principles.
Approach: They propose a framework to evaluate therapist-like responses for clinically grounded appropriateness and effectiveness using an ordinal scale.
Outcome: The proposed framework achieves an F-1 score of 63.34 versus the baseline Qwen3 score of 38.56 .
Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality (N18-1)

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations