1.5k citations
- Research!America (United States)US21 papers
- Samsung (South Korea)KR17 papers
- Korea Advanced Institute of Science and TechnologyKR9 papers
- Korea Institute of Science and TechnologyKR7 papers
- University of CambridgeGB5 papers
- University of Southern CaliforniaUS5 papers
- Imperial College LondonGB4 papers
- Purdue University West LafayetteUS4 papers
- Samsung Electronics (South Korea)KR4 papers
- Samsung (India)IN4 papers
- Stanford UniversityUS4 papers
- Texas A&M UniversityUS4 papers
5 papers · 2 filters
Automatic Mixed-Precision Quantization Search of BERT
Changsheng Zhao, Ting Hua, Yilin Shen +2
Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. However, these models usually contain millions of paramet…
Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21
Lintang Sutawika, Jan Christian Blaise Cruz
In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT'21 Large Scale Multilingual Translation Task - Small Track 2. We s…
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU
Yilin Shen, Yen-Chang Hsu, Avik Ray +1
Intent classification is a major task in spoken language understanding (SLU). Since most models are built with pre-collected in-domain (IND) training utterances, their ability to d…
A Coarse to Fine Question Answering System based on Reinforcement Learning
Yu Wang, Hongxia Jin
In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choo…
A character representation enhanced on-device Intent Classification
Sudeep Deepak Shivnikar, Himanshu Arora, Harichandana B S S
Intent classification is an important task in natural language understanding systems. Existing approaches have achieved perfect scores on the benchmark datasets. However they are n…