반응형 오늘의 자연어 처리572 [2023-01-14] 오늘의 자연어처리 Semantic Web Enabled Geographic Question Answering Framework: GeoTR With the considerable growth of linked data, researchers have focused on how to increase the availability of semantic web technologies to provide practical usages for real life systems. Question answering systems are an example of real-life systems that communicate directly with end users, understand user intention and generate .. 2023. 1. 14. [2023-01-13] 오늘의 자연어처리 Dual Learning for Large Vocabulary On-Device ASR Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are used to train the other model. Dual learning has seen some use in speech processing by pairing ASR and TTS as d.. 2023. 1. 13. [2023-01-12] 오늘의 자연어처리 BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm The performance of speech-processing models is heavily influenced by the speech corpus that is used for training and evaluation. In this study, we propose BAlanced Script PROducer (BASPRO) system, which can automatically construct a phonetically balanced and rich set of Chinese sentences for collecting.. 2023. 1. 12. [2023-01-11] 오늘의 자연어처리 ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student such that the student can be directly finetuned on downstream ta.. 2023. 1. 11. 이전 1 ··· 92 93 94 95 96 97 98 ··· 143 다음 반응형