1 code implementation • EMNLP (CINLP) 2021 • Fiona Anting Tan, Devamanyu Hazarika, See-Kiong Ng, Soujanya Poria, Roger Zimmermann
Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification.
no code implementations • EMNLP 2020 • Dhanasekar Sundararaman, Shijing Si, Vivek Subramanian, Guoyin Wang, Devamanyu Hazarika, Lawrence Carin
We propose a new methodology to assign and learn embeddings for numbers.
no code implementations • EACL (AdaptNLP) 2021 • Abhinav Ramesh Kashyap, Laiba Mehnaz, Bhavitvya Malik, Abdul Waheed, Devamanyu Hazarika, Min-Yen Kan, Rajiv Ratn Shah
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains.
1 code implementation • 20 May 2023 • Chao Zhao, Spandana Gella, Seokhwan Kim, Di Jin, Devamanyu Hazarika, Alexandros Papangelis, Behnam Hedayatnia, Mahdi Namazifar, Yang Liu, Dilek Hakkani-Tur
We hope this task and dataset can promote further research on TOD and subjective content understanding.
1 code implementation • 17 Feb 2023 • Yan Xu, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.
no code implementations • 16 Feb 2023 • Mahdi Namazifar, Devamanyu Hazarika, Dilek Hakkani-Tur
Moreover, we argue that the bias term of the value linear transformation has a more prominent role than that of the bias term of the query linear transformation.
no code implementations • 10 Feb 2023 • Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tur
This work focuses on in-context data augmentation for intent detection.
Ranked #1 on
Intent Detection
on HWU64 5-shot
no code implementations • 2 Feb 2023 • Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür
For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.
1 code implementation • 26 Oct 2022 • Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.
1 code implementation • NAACL 2022 • Devamanyu Hazarika, Yingting Li, Bo Cheng, Shuai Zhao, Roger Zimmermann, Soujanya Poria
In this work, we hope to address that by (i) Proposing simple diagnostic checks for modality robustness in a trained multimodal model.
1 code implementation • ACL 2022 • Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann, Soujanya Poria
Automatic transfer of text between domains has become popular in recent times.
1 code implementation • Findings (NAACL) 2022 • Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks.
1 code implementation • 22 Jun 2021 • Navonil Majumder, Deepanway Ghosal, Devamanyu Hazarika, Alexander Gelbukh, Rada Mihalcea, Soujanya Poria
We empirically show that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics.
no code implementations • 11 Jun 2021 • Devamanyu Hazarika, Mahdi Namazifar, Dilek Hakkani-Tür
In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero-shot.
1 code implementation • 22 Dec 2020 • Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Pengfei Hong, Romila Ghosh, Abhinaba Roy, Niyati Chhaya, Alexander Gelbukh, Rada Mihalcea
We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong Transformer-based baselines.
Ranked #1 on
Recognizing Emotion Cause in Conversations
on RECCON
no code implementations • NAACL 2021 • Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann
Domain divergence plays a significant role in estimating the performance of a model in new domains.
no code implementations • 19 Oct 2020 • Shagun Uppal, Sarthak Bhagat, Devamanyu Hazarika, Navonil Majumdar, Soujanya Poria, Roger Zimmermann, Amir Zadeh
Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data.
2 code implementations • 7 May 2020 • Devamanyu Hazarika, Roger Zimmermann, Soujanya Poria
In this paper, we aim to learn effective modality representations to aid the process of fusion.
1 code implementation • ACL 2020 • Deepanway Ghosal, Devamanyu Hazarika, Abhinaba Roy, Navonil Majumder, Rada Mihalcea, Soujanya Poria
Cross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of sentiment analysis.
1 code implementation • 1 May 2020 • Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Rada Mihalcea
Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago.
1 code implementation • 11 Oct 2019 • Devamanyu Hazarika, Soujanya Poria, Roger Zimmermann, Rada Mihalcea
We propose an approach, TL-ERC, where we pre-train a hierarchical dialogue model on multi-turn conversations (source) and then transfer its parameters to a conversational emotion classifier (target).
Ranked #18 on
Emotion Recognition in Conversation
on DailyDialog
1 code implementation • ACL 2019 • Santiago Castro, Devamanyu Hazarika, Ver{\'o}nica P{\'e}rez-Rosas, Roger Zimmermann, Rada Mihalcea, Soujanya Poria
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
1 code implementation • 5 Jun 2019 • Santiago Castro, Devamanyu Hazarika, Verónica Pérez-Rosas, Roger Zimmermann, Rada Mihalcea, Soujanya Poria
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
no code implementations • 22 Feb 2019 • Rajiv Bajpai, Devamanyu Hazarika, Kunal Singh, Sruthi Gorantla, Erik Cambria, Roger Zimmerman
With the multitude of companies and organizations abound today, ranking them and choosing one out of the many is a difficult and cumbersome task.
2 code implementations • 1 Nov 2018 • Navonil Majumder, Soujanya Poria, Devamanyu Hazarika, Rada Mihalcea, Alexander Gelbukh, Erik Cambria
Emotion detection in conversations is a necessary step for a number of applications, including opinion mining over chat history, social media threads, debates, argumentation mining, understanding consumer feedback in live conversations, etc.
Ranked #3 on
Emotion Recognition in Conversation
on SEMAINE
Emotion Classification
Emotion Recognition in Conversation
+2
9 code implementations • ACL 2019 • Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, Rada Mihalcea
We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations.
1 code implementation • EMNLP 2018 • Devamanyu Hazarika, Soujanya Poria, Rada Mihalcea, Erik Cambria, Roger Zimmermann
Emotion recognition in conversations is crucial for building empathetic machines.
Ranked #38 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
General Classification
+2
1 code implementation • NAACL 2018 • Devamanyu Hazarika, Soujanya Poria, Prateek Vij, Gangeshwar Krishnamurthy, Erik Cambria, Roger Zimmermann
Aspect-based Sentiment Analysis is a fine-grained task of sentiment classification for multiple aspects in a sentence.
1 code implementation • NAACL 2018 • Devamanyu Hazarika, Soujanya Poria, Amir Zadeh, Erik Cambria, Louis-Philippe Morency, Roger Zimmermann
Emotion recognition in conversations is crucial for the development of empathetic machines.
Ranked #40 on
Emotion Recognition in Conversation
on IEMOCAP
1 code implementation • COLING 2018 • Devamanyu Hazarika, Soujanya Poria, Sruthi Gorantla, Erik Cambria, Roger Zimmermann, Rada Mihalcea
The literature in automated sarcasm detection has mainly focused on lexical, syntactic and semantic-level analysis of text.
Ranked #1 on
Sarcasm Detection
on SARC (all-bal)
no code implementations • 19 Mar 2018 • Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Erik Cambria, Alexander Gelbukh, Amir Hussain
We compile baselines, along with dataset split, for multimodal sentiment analysis.
no code implementations • 30 Aug 2017 • Amarjot Singh, Devamanyu Hazarika, Aniruddha Bhattacharya
Automation of brain matter segmentation from MR images is a challenging task due to the irregular boundaries between the grey and white matter regions.
3 code implementations • 9 Aug 2017 • Tom Young, Devamanyu Hazarika, Soujanya Poria, Erik Cambria
Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains.
no code implementations • 29 Jul 2017 • Erik Cambria, Devamanyu Hazarika, Soujanya Poria, Amir Hussain, R. B. V. Subramaanyam
We propose a framework for multimodal sentiment analysis and emotion recognition using convolutional neural network-based feature extraction from text and visual modalities.
2 code implementations • ACL 2017 • Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Majumder, Amir Zadeh, Louis-Philippe Morency
Multimodal sentiment analysis is a developing area of research, which involves the identification of sentiments in videos.
Ranked #3 on
Emotion Recognition in Conversation
on CPED
Emotion Recognition in Conversation
General Classification
+4
3 code implementations • COLING 2016 • Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Prateek Vij
Sarcasm detection is a key task for many natural language processing tasks.