반응형 논문572 [2022-11-01] 오늘의 자연어처리 SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control Despite the growing success of diffusion models in continuous-valued domains (e.g., images), diffusion-based language models on discrete text have yet to match autoregressive language models on text generation benchmarks. In this work, we present SSD-LM -- a diffusion language model with tw.. 2022. 11. 1. [2022-11-01] 오늘의 자연어처리 When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. However, humans may not always provide explicit signals when the chatbot makes mistakes during interactions. In this work, we propose Juicer, a framework to make use of both binary and free-.. 2022. 11. 1. [2022-10-31] 오늘의 자연어처리 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which retains the major capacity of PLMs. However, ex.. 2022. 10. 31. [2022-10-30] 오늘의 자연어처리 Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning Automatic assessment of dysarthric speech is essential for sustained treatments and rehabilitation. However, obtaining atypical speech is challenging, often leading to data scarcity issues. To tackle the problem, we propose a novel automatic severity assessment method for dysarthric speech,.. 2022. 10. 30. 이전 1 ··· 112 113 114 115 116 117 118 ··· 143 다음 반응형