Welcome fellow researchers to the DeCLaRe Lab! We hereby DeCLaRe our quest to breathe cognitive and language skills of human-like depth into machines by solving challenging NLP problems, such as, dialogue comprehension and generation, commonsense reasoning, multimodal understanding, and more. Addressing such open research problems requires powerful, scalable, and data-hungry algorithms. As such, we develop cutting-edge neural models, based on sound linguistic concepts. To know more about our work, please browse our catalog of publications.
Intrigued by our logo? Read the story behind it.”
News
ACL 2024
We got four papers accepted at ACL 2024! Congratulations to all the co-authors.
Google's Gemma Academic Program Award!
We are thrilled to receive a research grant from Google! Congratulations to Rishabh.
ICLR, EACL and WWW
We got one paper at ICLR, one at EACL, and one at WWW. Congratulations to all the co-authors!
ACM MM 2023
Two papers accepted at ACM MM 2023.
Oracle Research Grant 2023
DeCLaRe Lab is proud to receive a research grant from Oracle. It will help us to train our generative models on Oracle's cloud infrastructure.
Interspeech 2023
Two papers accepted at Interspeech 2023. Congratulations to all the collaborators.
ACL 2023
Three papers accepted at ACL 2023. Congratulations to all the collaborators.
Collaboration with Microsoft Research
DeCLaRe Lab is thrilled to announce our selection for the Microsoft Research Accelerate Foundation Models Academic Research program. This program will enable us to contribute to the development of fair and responsible open source LLMs. We are excited to compare the performance of our models to OpenAI's LLMs, including GPT-4 and ChatGPT.
ICASSP 2023
Two papers accepted at ICASSP 2023. Congratulations to all the collaborators.
EACL 2023
Two papers accepted at EACL 2022. Congratulations to all the collaborators.
EMNLP 2022
Five papers accepted at EMNLP 2022. Congratulations to all the collaborators.
COLING 2022
New paper: KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks. Download Now!
ACL 2022
Prof. Soujanya Poria is serving as Publicity co-chair for ACL 2022!
ACL 2022
Prof. Soujanya Poria is serving as Workshop co-chair for AACL 2022!
New paper
Best Paper Award Honorable Mention - Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis. ICMI 2021. Read here.
New paper
New Paper - Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks. ACL 2021. Read here.
New paper
New Paper - Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction. ACL 2021. Read here.
New paper
New Paper - Federated Distillation of Natural Language Understanding with Confident Sinkhorns. Read here.
New paper
New Paper - Multi-trends Enhanced Dynamic Micro-video Recommendation. Read here.
New paper
New Paper - Multimodal Research in Vision and Language: A Review of Current and Emerging Trends. Information Fusion 77. Read here.
New paper
New Paper - Causal Augmentation for Causal Sentence Classification. ACL 2021. Read here.
New paper
New Paper - Zero-Shot Controlled Generation with Encoder-Decoder Transformers. Read here.
New paper
New Paper - Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer. ACL 2021. Read here.
New paper
New Paper - Conversational Transfer Learning for Emotion Recognition. Read here.
New paper
New Paper - Aspect Sentiment Triplet Extraction Using Reinforcement Learning. CIKM 77. Read here.
New paper
New Paper - M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversations. ICMI 2021. Read here.
New paper
New Paper - Multimodal Analysis Combining Monitoring Modalities To Elicit Cognitive States And Perform Screening For Mental Disorders. US Patent App. Read here.
New paper
New Paper - Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering. ACL 2021. Read here.
New paper
New Paper - STaCK: Sentence Ordering with Temporal Commonsense Knowledge. EMNLP 2021. Read here.
New paper
New Paper - Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis. EMNLP 2021. Read here.
New paper
New Paper - More Identifiable yet Equally Performant Transformers for Text Classification. ACL 2021. Read here.
New paper
New Paper - CIDER: Commonsense Inference for Dialogue Explanation and Reasoning. ACL 2021. Read here.
New paper
New Paper - Investigating Gender Bias in BERT. Cognitive Computation. Cognitive Computation, 1-11. Read here.
New paper
New Paper - Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey. Read here.
New paper
New Paper - Persuasive Dialogue Understanding: the Baselines and Negative Results. Neurocomputing 431. Read here.
Funding
The DeCLaRe lab has been awarded Tier 2 funding by the Ministry of Education (MoE), Singapore. We are grateful to MoE for their generosity. The project will focus on building techniques for Commonsense-aware NLP. Shoutout to the team-- Prof. Rada Mihalcea, Dr. Navonil Majumder, Prof. Alexander Gelbukh, Devamanyu Hazarika, and Deepanway Ghosal without whom it was not possible.
New paper
New paper - Aspect Sentiment Triplet Extraction Using Reinforcement Learning. CIKM 2021. Read here.
New paper
New paper - Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study. ACL-IJCNLP 2021. Read here.
New paper
New paper - Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication. Read here.
New paper
New paper - Recognizing Emotion Cause in Conversations. Cognitive Computation 13 (5). Read here.
New paper
New paper on Sentiment Analysis - Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research Read here.
Opening
We have a number of openings to join us at the DeCLaRe Lab as postdocs and research assistants/associates. Drop an email to Soujanya
Funding
The DeCLaRe lab has been awarded programmatic funding by AME. We are grateful to AME for their generosity. The project will focus on building knowledge graph-based question answering.
Funding
The DeCLaRe lab secured funding from DSO for a project on complex question answering. Thank you, DSO!
New paper
New paper on transfer learning - Hazarika, Devamanyu, Soujanya Poria, Roger Zimmermann, and Rada Mihalcea. "Emotion Recognition in Conversations with Transfer Learning from Generative Conversation Modeling. [Download the paper].