no code implementations • Findings (NAACL) 2022 • Jin Cao, Chandana Satya Prakash, Wael Hamza
However, given the trend of larger pre-trained models, fine-tuning these models for each downstream task is parameter-inefficient and computationally-expensive deeming this approach sub-optimal for adoption by NLU systems.
no code implementations • 15 Jun 2022 • Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, Davide Bernardi, Abhishek Bhagia, Claudio Delli Bovi, Jin Cao, Rakesh Chada, Amit Chauhan, Luoxin Chen, Anurag Dwarakanath, Satyam Dwivedi, Turan Gojayev, Karthik Gopalakrishnan, Thomas Gueudre, Dilek Hakkani-Tur, Wael Hamza, Jonathan Hueser, Kevin Martin Jose, Haidar Khan, Beiye Liu, Jianhua Lu, Alessandro Manzotti, Pradeep Natarajan, Karolina Owczarzak, Gokmen Oz, Enrico Palumbo, Charith Peris, Chandana Satya Prakash, Stephen Rawls, Andy Rosenbaum, Anjali Shenoy, Saleh Soltan, Mukund Harakere Sridhar, Liz Tan, Fabian Triefenbach, Pan Wei, Haiyang Yu, Shuai Zheng, Gokhan Tur, Prem Natarajan
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference intent-classification +5
1 code implementation • Findings (NAACL) 2022 • Shuyang Li, Mukund Sridhar, Chandana Satya Prakash, Jin Cao, Wael Hamza, Julian McAuley
Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge -- their types.
1 code implementation • 20 Apr 2022 • Mohamed Trabelsi, Jeff Heflin, Jin Cao
We study the zero-shot learning case on the target domain, and demonstrate that our method learns the EM task and transfers knowledge to the target domain.
1 code implementation • 22 Jun 2021 • Haowei Jiang, Feiwei Qin, Jin Cao, Yong Peng, Yanli Shao
The recurrent network architecture is a widely used model in sequence modeling, but its serial dependency hinders the computation parallelization, which makes the operation inefficient.
no code implementations • EACL 2021 • Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, Julian McAuley
Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs.
no code implementations • 11 Nov 2020 • Cheng-I Lai, Jin Cao, Sravan Bodapati, Shang-Wen Li
Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only intents without the slot values, or models were trained on a large amount of in-house data.
1 code implementation • 30 Oct 2020 • Mohamed Trabelsi, Jin Cao, Jeff Heflin
Generating schema labels automatically for column values of data tables has many data science applications such as schema matching, and data discovery and linking.
no code implementations • 9 Oct 2020 • Jin Cao, Jun Wang, Wael Hamza, Kelly Vanee, Shang-Wen Li
The light encoder architecture separates the shared pre-trained networks from the mappings of generally encoded knowledge to specific domains of SLU, allowing for the domain adaptation to be performed solely at the light encoder and thus increasing efficiency.
no code implementations • 7 Sep 2020 • Jin Cao, Dewei Zhong
A well-known result states that finding a Longest Common Subsequence (LCS) for $L$ strings is NP-hard, e. g., the computational complexity is exponential in $L$.
no code implementations • 7 Sep 2020 • Jin Cao, Yibo Zhao, Linjun Zhang, Jason Li
The key to our approach is a computationally lightweight forward addition algorithm that we developed to recursively extract the functional dependencies between table columns that are scalable to tables with many columns.
no code implementations • 16 Oct 2019 • Jin Cao, Hossein Movasati, Shing-Tung Yau
We describe an algebra of meromorphic functions on the Siegel domain of genus two which contains Siegel modular forms for an arithmetic index six subgroup of the symplectic group and it is closed under three canonical derivations of the Siegel domain.
Algebraic Geometry Mathematical Physics Complex Variables Mathematical Physics
no code implementations • 12 Sep 2019 • Huseyin Uzunalioglu, Jin Cao, Chitra Phadke, Gerald Lehmann, Ahmet Akyamac, Ran He, Jeongran Lee, Maria Able
Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists.
no code implementations • 11 Dec 2017 • Maryam Fazel-Zarandi, Shang-Wen Li, Jin Cao, Jared Casale, Peter Henderson, David Whitney, Alborz Geramifard
In this paper, we focus on learning robust dialog policies to recover from these errors.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2