【摘 要】
：
The primary task of language translation is to faithfully pass the meaning(s)of the source text to the target language.Unfortunately,meanings often get lost
【机 构】
：
Department of Chinese and Bilingual Studies,Hong Kong Polytechnic University
【出 处】
：
第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD
论文部分内容阅读
The primary task of language translation is to faithfully pass the meaning(s)of the source text to the target language.Unfortunately,meanings often get lost or distorted in machine translation,including state-of-the-art Google Translate and Baidu Translate.Yes Translate is a Chinese-English translation tool to be maximally loyal to the source text while maintaining adequate fluency.This is implementable by avoiding risky actions of word deleting,adding and re-ordering.The tool is supported by an 116,000-words Dictionary.In an experiment on natural news articles freely selected by themselves,10 postgraduate students with good command of Chinese and English all agreed or strongly agreed that the general meaning of the translation by Yes Translate was correct and understandable.And 9 out of the 10 students agreed or strongly agreed that the general meaning of each sentence was correct.
其他文献
本文提出一种基于语言现象的文本蕴涵识别方法，该方法建立了一个语言现象识别和整体推理判断的联合分类模型，目的是对两个高度相关的任务进行统一学习，避免管道模型的错误传
情感分析是自然语言处理领域的重要研究问题。现有方法往往难以克服样本偏置与领域依赖问题，严重制约了情感分析的发展和应用。为此，本文提出了一种基于深度表示学习和高斯
Traditional approaches to the task of ACE event extraction usually rely on complicated natural language processing(NLP)tools and elaborately designed featur
In Mongolian language,there is a phenomenon that many words have the same presentation form but represent different words with different codes.Since typists
Recognizing Textual Entailment(RTE)plays an important role in NLP applications like question answering,information retrieval,etc.Most previous works either
随着深度学习和多模态融合的深入研究,问答系统从传统的纯文本方式扩展到结合图片的视觉问答,成为计算机视觉与自然语言理解的交叉研究热点.Hyeonwoo等最新提出的动态参数预测模型(DPPnet)能够简单、有效地实现问句和图片信息的融合.但是该模型在进行网络参数动态Hash分配时位置随机,缺乏图像内容空间分布的考虑.针对此不足,本文提出一种新的空间离散余弦Hash动态参数网络.算法采用全卷积方式提取保
For the difficulty of marking Vietnamese dependency tree,this paper proposed the method which combined MST algorithm and improved Nivre algorithm to build V
As a fundamental step in biomedical information extraction tasks,biomedical named entity recognition remains challenging.In recent years,the neural network
Chinese semantic dependency graph is extended from semantic dependency tree,which uses directed acyclic graphs to capture richer latent semantics of sentenc
Definition extraction is the task to identify definitional sentences automatically from unstructured text.The task can be used in the aspects of ontology ge