Devamanyu Hazarika

Applied Scientist
Amazon Alexa AI devamanyu@u.nus.edu

LinkTwitterLinkedInLink

As an Applied Scientist at Amazon AGI, I specialize in the cutting-edge fields of Conversational AI, Dialog Systems, and Large Language Models. I earned my Ph.D. in 2021 from the National University of Singapore, under the esteemed guidance of Dr. Roger Zimmermann, and had the privilege of mentorship from academic and industry luminaries, such as Dr. Soujanya Poria, Dr. Rada Mihalcea, Dr. Dilek Hakkani-Tur, Dr. Yang Liu, and others.

In the academic community, I have taken on leadership roles as an Area Chair for premier NLP conferences, including ACL 2023, EMNLP 2023, and AAAI 2023/2024. My contributions have been recognized through multiple accolades, such as an Outstanding Reviewer Award at ACL '21, an Outstanding Paper Award from IEEE CIM, and the Research Achievement Award from NUS in 2019.

By actively merging the realms of academic research and practical application, I am committed to pushing the boundaries of what's possible in Conversational AI.

News

Affiliations

Selected Publications
Complete List: Google Scholar | Latest Work:   Amazon Science

CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs

Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tür, Yang Liu, Mahdi Namazifar, EMNLP 2023 (Main)

[Paper]

Using In-Context Learning to Improve Dialogue Safety

Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür, EMNLP 2023 (Findings)

[Paper]

"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge

Chao Zhao, Spandana Gella, Seokhwan Kim, Di Jin, Devamanyu Hazarika, Alexandros Papangelis, Behnam Hedayatnia, Mahdi Namazifar, Yang Liu, Dilek Hakkani-Tur, Sigdial 2023

[Paper]

KILM: Knowledge Injection into Encoder-Decoder Language Models  (Oral)

Yan Xu, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür, ACL 2023 (Main)

[Paper]

Selective in-context data augmentation for intent detection using pointwise V-information

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tür, EACL 2023 

[Paper]

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning (Oral)

Yifan Chen*, Devamanyu Hazarika*, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tür , EMNLP 2022  (Main)  *Equal Contribution 

[Paper] [Slides]

Empowering Parameter-Efficient Transfer Learning by Recognizing the Kernel

Structure in Attention

Yifan Chen*, Devamanyu Hazarika*, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tür, NAACL 2022  *Equal Contribution 

[Paper] 

Analyzing Modality Robustness in Multimodal Sentiment Analysis

Devamanyu Hazarika*, Y Li*, B Cheng, S Zhao, Roger Zimmermann, Soujanya Poria, NAACL 2022  *Equal Contribution 

[Paper] [Code] [Slides]

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer (Oral)

Aabhinav Kashyap*, Devamanyu Hazarika*, Min-Yen Kan, Roger Zimmermann, Soujanya Poria, ACL 2022  *Equal Contribution

[Paper] [Code]

Attention Biasing and Context Augmentation for Zero-Shot Control of Encoder-Decoder Transformers for Natural Language Generation

Devamanyu Hazarika, Mahdi Namazifar, and Dilek Hakkani-Tur, AAAI 2022   

[Paper] [Arxiv]

Domain Divergences: a Survey and Empirical Analysis

 Abhinav Kashyap, Devamanyu Hazarika, Min-Yen Kan, and Roger Zimmermann, NAACL 2021    

[Paper]

Methods for Numeracy-Preserving Word Embeddings

D Sundararaman, S Si, V Subramanian, G Wang, D Hazarika, L Carin, EMNLP 2020 

[Paper]

Misa: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis

D Hazarika, R Zimmermann, S Poria, ACM MM 2020 

[Paper] [Code]

Kingdom: Knowledge-Guided Domain Adaptation for Sentiment Analysis

D Ghosal, D Hazarika, A Roy, N Majumder, R Mihalcea, S Poria, ACL 2020 

[Paper] [Code]

Towards Multimodal Sarcasm Detection (An Obviously Perfect Paper)

S Castro, D Hazarika, V Pérez-Rosas, R Zimmermann, R Mihalcea, S Poria, ACL 2020 

[Paper] [Code]

Contextually Grounded Affective Analysis of Media

D Hazarika, Thesis '21  

Recognizing Emotion Cause in Conversations

S Poria, N Majumder, D Hazarika, D Ghosal, R Bhardwaj, S Y B Jian, P Hong, R Ghosh, A Roy, N Chhaya, A Gelbukh, R Mihalcea, Cognitive Computation '21  

[Paper] [Code]

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research

S Poria, D Hazarika, N Majumder, R Mihalcea, IEEE Transactions on Affective Computing '20 

[Paper]

Multimodal Research in Vision and Language: A Review of Current and Emerging Trends

S Uppal, S Bhagat, D Hazarika, N Majumder, S Poria, R Zimmermann, A Zadeh, Information Fusion '22  

[Paper] 

Conversational Transfer Learning for Emotion Recognition

D Hazarika, S Poria, R Zimmermann, R Mihalcea, Information Fusion '21 

[Paper] [Code]

Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer

AR Kashyap, L Mehnaz, B Malik, A Waheed, D Hazarika, M-Y Kan, and R Shah, Adapt-NLP, EACL 2021   

[Paper]

Causal Augmentation for Causal Sentence Classification

FA Tan, D Hazarika, S K Ng, S Poria, R Zimmermann, CL+NLP 2021   

[Paper] [Code]