Papers by Tulika Saha

7 papers
Action and Reaction Go Hand in Hand! a Multi-modal Dialogue Act Aided Sarcasm Identification (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have shown that sarcasm is reflected by the intended meaning of the speaker's utterance.
Approach: They propose to extend the MUStARD dataset to enclose dialogue acts for each dialogue . they propose a dialogue act-aided multi-modal transformer network for sarcasm identification model .
Outcome: The proposed model improves performance in dialogue act-aided sarcasm identification compared to sardasmatic identification alone.
Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter (2021.naacl-main)

Copied to clipboard

Challenge: Speech Act Classification determining the communicative intent of an utterance has been investigated widely over the years as a standalone task.
Approach: They propose a multi-modal, emotion-TA dataset called EmoTA from open-source Twitter dataset and a Dyadic Attention Mechanism framework that integrates intra-modal and inter-modal attention to fuse multiple modalities.
Outcome: The proposed framework boosts the performance of the primary task, i.e., TA classification (TAC), by benefitting from the two secondary tasks, namely, Sentiment and Emotion Analysis compared to its uni-modal and single task TAC variants.
Can you Summarize my learnings? Towards Perspective-based Educational Dialogue Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Increasing use of virtual tutors has allowed for more efficient, personalized, and interactive AI-based learning experiences.
Approach: They propose a task of Multi-modal Perspective based Dialogue Summarization (MM-PerSumm) that summarizes educational dialogues from three unique perspectives: the Student, the Tutor, and a Generic viewpoint.
Outcome: The proposed model can summarize educational dialogues from three perspectives, while student-oriented summaries should distill learning points, track progress, and suggest scope for improvement.
Towards Emotion-aided Multi-modal Dialogue Act Classification (2020.acl-main)

Copied to clipboard

Challenge: Considerable work on Dialogue Act Classification (DAC) has been done on textual inputs.
Approach: They propose to use a multimodal Emotion aware Dialogue Act dataset to explore the role of multi-modality and emotion recognition in DAC.
Outcome: The proposed dataset shows that multi-modality and emotion recognition improves DAC performance compared to uni-modal and single task DAC variants.
GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to capture and integrate global semantic information are limited due to their limited ability to capture long-range dependencies.
Approach: They propose a graph contrastive topic enhanced language model that integrates a neural topic model with a pre-trained language model to capture global contextual semantics.
Outcome: The proposed model outperforms existing methods on general domain and biomedical datasets.
A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental Agony (2022.naacl-main)

Copied to clipboard

Challenge: Mental health disorders are one of the primary causes of disability worldwide . lack of qualified and competent mental health professionals is a major problem . we propose a virtual assistant that can act as the first point of contact and comfort for mental health patients.
Approach: They propose a virtual assistant that can act as the first point of contact and comfort for mental health patients.
Outcome: The proposed system outperforms baselines in the evaluation of 7k dyadic conversations from a peer-to-peer support platform.
Meta-Learning based Deferred Optimisation for Sentiment and Emotion aware Multi-modal Dialogue Act Classification (2022.aacl-main)

Copied to clipboard

Challenge: Empirically, we show that the optimisation of multi-modal DAC, SA and ER tasks produces better results compared to its different counterparts.
Approach: They propose a dual attention mechanism that integrates sentiment tags into a multi-modal conversational framework that integrate modal attentions and multiple loss optimization.
Outcome: The proposed framework integrates sentiment tags for each utterance and learns generalized features across multiple tasks.

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