基于自动识别的委婉语历时性发展变化与社会共变研究(A Study on the Diachronic Development and Social Covariance of Euphemism Based on Automatic Recognition)

no code implementations • CCL 2021 • Chenlin Zhang, Mingwen Wang, Yiming Tan, Ming Yin, Xinyi Zhang

“本文主要以汉语委婉语作为研究对象, 基于大量人工标注, 借助机器学习有监督分类方法, 实现了较高精度的委婉语自动识别, 并基于此对1946年-2017年的《人民日报》中的委婉语历时变化发展情况进行量化统计分析。从大规模数据的角度探讨委婉语历时性发展变化、委婉语与社会之间的共变关系, 验证了语言的格雷什姆规律与更新规律。”

ActionFormer: Localizing Moments of Actions with Transformers

1 code implementation • 16 Feb 2022 • Chenlin Zhang, Jianxin Wu, Yin Li

Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding.

Action Recognition audio-visual event localization +3

Improving Machine Translation Quality Estimation with Neural Network Features

no code implementations • WS 2017 • Zhiming Chen, Yiming Tan, Chenlin Zhang, Qingyu Xiang, Lilin Zhang, Maoxi Li, Mingwen Wang

Automatic Speech Recognition (ASR) Language Modelling +3