no code implementations • SIGDIAL (ACL) 2021 • Peyman Heidari, Arash Einolghozati, Shashank Jain, Soumya Batra, Lee Callender, Ankit Arun, Shawn Mei, Sonal Gupta, Pinar Donmez, Vikas Bhardwaj, Anuj Kumar, Michael White
In this paper, we study the utilization of pre-trained language models to enable few-shotNatural Language Generation (NLG) in task-oriented dialog systems.
no code implementations • EMNLP 2021 • Soumya Batra, Shashank Jain, Peyman Heidari, Ankit Arun, Catharine Youngs, Xintong Li, Pinar Donmez, Shawn Mei, Shiunzu Kuo, Vikas Bhardwaj, Anuj Kumar, Michael White
We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches.
no code implementations • 12 Feb 2024 • Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu, Shicong Zhao, Longfang Zhao, Ankit Ramchandani, Xin Luna Dong, Anuj Kumar
We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities.
no code implementations • 22 Nov 2023 • Tadbhagya Kumar, Anuj Kumar, Pinaki Pal
Proof-of-concept studies are performed with physics-constrained neuralODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions.
no code implementations • 17 Nov 2023 • Gustavo Sganzerla Martinez, Mansi Dutt, Anuj Kumar, David J Kelvin
Determining the physicochemical properties of a protein can reveal important insights in their structure, biological functions, stability, and interactions with other molecules.
no code implementations • 27 Sep 2023 • Seungwhan Moon, Andrea Madotto, Zhaojiang Lin, Tushar Nagarajan, Matt Smith, Shashank Jain, Chun-Fu Yeh, Prakash Murugesan, Peyman Heidari, Yue Liu, Kavya Srinet, Babak Damavandi, Anuj Kumar
We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i. e. text, image, video, audio, IMU motion sensor), and generates textual responses.
Ranked #7 on Video Question Answering on STAR Benchmark
no code implementations • 6 Apr 2023 • Anuj Kumar, Tarek Echekki
A combustion chemistry acceleration scheme is developed based on deep operator networks (DeepONets).
no code implementations • 10 Sep 2022 • Shakti Kumar, Anuj Kumar
In recent years, the detection of melanoma using image processing techniques has become a dominant research field.
no code implementations • 9 Sep 2022 • Sarita Gautam, Anuj Kumar
Autonomous vehicles are growing rapidly, in well-developed nations like America, Europe, and China.
no code implementations • EACL 2021 • Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta
Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales.
no code implementations • 18 Jan 2021 • Michael S. Jolly, Anuj Kumar, Vincent R. Martinez
This paper studies the dissipative generalized surface quasi-geostrophic equations in a supercritical regime where the order of the dissipation is small relative to order of the velocity, and the velocities are less regular than the advected scalar by up to one order of derivative.
Analysis of PDEs 76D03, 35Q35, 35Q86, 35K59, 35B65, 34K37
no code implementations • COLING 2020 • Ankit Arun, Soumya Batra, Vikas Bhardwaj, Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan, Michael White
In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production.
no code implementations • EMNLP 2020 • Armen Aghajanyan, Jean Maillard, Akshat Shrivastava, Keith Diedrick, Mike Haeger, Haoran Li, Yashar Mehdad, Ves Stoyanov, Anuj Kumar, Mike Lewis, Sonal Gupta
In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session.
2 code implementations • 12 Jun 2020 • Yitong Tseo, M. I. Salkola, Ahmed Mohamed, Anuj Kumar, Freddy Abnousi
Clinical trials predicate subject eligibility on a diversity of criteria ranging from patient demographics to food allergies.
no code implementations • CONLL 2019 • Seungwhan Moon, Pararth Shah, Anuj Kumar, Rajen Subba
We introduce Episodic Memory QA, the task of answering personal user questions grounded on memory graph (MG), where episodic memories and related entity nodes are connected via relational edges.
no code implementations • IJCNLP 2019 • Seungwhan Moon, Pararth Shah, Rajen Subba, Anuj Kumar
To implement such a system, we collect a new corpus of memory grounded conversations, which comprises human-to-human role-playing dialogs given synthetic memory graphs with simulated attributes.
no code implementations • WS 2019 • Jinfeng Rao, Kartikeya Upasani, Anusha Balakrishnan, Michael White, Anuj Kumar, Rajen Subba
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
no code implementations • 27 Sep 2019 • Jack Goetz, Kshitiz Malik, Duc Bui, Seungwhan Moon, Honglei Liu, Anuj Kumar
To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency.
no code implementations • ICLR 2020 • Duc Bui, Kshitiz Malik, Jack Goetz, Honglei Liu, Seungwhan Moon, Anuj Kumar, Kang G. Shin
Furthermore, we show that user embeddings learned in FL and the centralized setting have a very similar structure, indicating that FURL can learn collaboratively through the shared parameters while preserving user privacy.
no code implementations • ACL 2019 • Seungwhan Moon, Pararth Shah, Anuj Kumar, Rajen Subba
We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes.
no code implementations • 1 Dec 2018 • Honglei Liu, Anuj Kumar, Wenhai Yang, Benoit Dumoulin
This may require constant exploration of various options that the system may have for the user and obtaining signals of user preferences on those.
no code implementations • EMNLP 2018 • Sonal Gupta, Rushin Shah, Mrinal Mohit, Anuj Kumar, Mike Lewis
Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots.
1 code implementation • 23 Feb 2018 • Dmitriy Serdyuk, Yongqiang Wang, Christian Fuegen, Anuj Kumar, Baiyang Liu, Yoshua Bengio
Spoken language understanding system is traditionally designed as a pipeline of a number of components.
Natural Language Understanding Spoken Language Understanding