Zhiyong Luo


2022

pdf bib
篇章级小句复合体结构自动分析(Chinese Clause Complex Structure Automatic Analysis on Passage)
Zhiyong Luo (罗智勇) | Ruifang Han (韩瑞昉) | Mingming Zhang (张明明) | Yujiao Han (韩玉蛟) | Zhilin Zhao (赵志琳)
Proceedings of the 21st Chinese National Conference on Computational Linguistics

“话头话身共享关系是小句组合成小句复合体的重要语法手段,也是汉语篇章级句法语义分析的重要基础。本文通过引入窗口滑动机制,将篇章文本及其成分共享关系转换为文本片段及片段内部的成分共享关系预测问题,并针对预测结果合并与选择问题,依据话头话身共享关系的语法限定性,提出了多种候选项消除策略。实验结果表明,本文方法在缺少小句复合体边界信息条件下仍取得了与传统基于NTC的方法可比的实验结果,尤其是在确实缺失共享成分的待预测位置处的召回率提高了约0.4个百分点。”

pdf bib
基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling)
Yujiao Han (韩玉蛟) | Zhiyong Luo (罗智勇) | Mingming Zhang (张明明) | Zhilin Zhao (赵志琳) | Qing Zhang (张青)
Proceedings of the 21st Chinese National Conference on Computational Linguistics

“机器阅读理解(Machine Reading Comprehension, MRC)任务旨在让机器回答给定上下文的问题来测试机器理解自然语言的能力。目前,基于大规模预训练语言模型的神经机器阅读理解模型已经取得重要进展,但在涉及答案要素、线索要素和问题要素跨标点句、远距离关联时,答案抽取的准确率还有待提升。本文通过篇章内话头话体结构分析,建立标点句间远距离关联关系、补全共享缺失成分,辅助机器阅读理解答案抽取;设计和实现融合话头话体结构信息的机器阅读理解模型,在公开数据集CMRC2018上的实验结果表明,模型的F1值相对于基线模型提升2.4%,EM值提升6%。”

pdf bib
基于神经网络的半监督CRF中文分词(Semi-supervised CRF Chinese Word Segmentation based on Neural Network)
Zhiyong Luo (罗智勇) | Mingming Zhang (张明明) | Yujiao Han (韩玉蛟) | Zhilin Zhao (赵志琳)
Proceedings of the 21st Chinese National Conference on Computational Linguistics

“分词是中文信息处理的基础任务之一。目前全监督中文分词技术已相对成熟并在通用领域取得较好效果,但全监督方法存在依赖大规模标注语料且领域迁移能力差的问题,特别是跨领域未登录词识别性能不佳。为缓解上述问题,本文提出了一种充分利用相对易得的目标领域无标注文本、实现跨领域迁移的半监督中文分词框架;并设计实现了基于词记忆网络和序列条件熵的半监督权杒杆中文分词模型。实验结果表明本该模型在多个领域数据集上杆札值和杒杏杏杖值分别取得最高朲.朳朵朥和朱朲.朱朲朥的提升,并在多个数据集上成为当前好结果。”

2021

pdf bib
基于小句复合体的中文机器阅读理解研究(Machine Reading Comprehension Based on Clause Complex)
Ruiqi Wang (王瑞琦) | Zhiyong Luo (罗智勇) | Xiang Liu (刘祥) | Rui Han (韩瑞昉) | Shuxin Li (李舒馨)
Proceedings of the 20th Chinese National Conference on Computational Linguistics

机器阅读理解任务要求机器根据篇章文本回答相关问题。本文以抽取式机器阅读理解为例,重点考察当问题的线索要素与答案在篇章文本中跨越多个标点句时的阅读理解问题。本文将小句复合体结构自动分析任务与机器阅读理解任务融合,利用小句复合体中跨标点句话头札话体共享关系,来化简机器阅读理解任务的难度;并设计与实现了基于小句复合体的机器阅读理解模型。实验结果表明:在问题线索要素与答案跨越多个标点句时,答案抽取的精确匹配率(EM)相对于基准模型提升了3.49%,模型整体的精确匹配率提升了3.26%。

2016

pdf bib
Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts
Xingyou Wang | Weijie Jiang | Zhiyong Luo
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Sentiment analysis of short texts is challenging because of the limited contextual information they usually contain. In recent years, deep learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been applied to text sentiment analysis with comparatively remarkable results. In this paper, we describe a jointed CNN and RNN architecture, taking advantage of the coarse-grained local features generated by CNN and long-distance dependencies learned via RNN for sentiment analysis of short texts. Experimental results show an obvious improvement upon the state-of-the-art on three benchmark corpora, MR, SST1 and SST2, with 82.28%, 51.50% and 89.95% accuracy, respectively.

2004

pdf bib
An Integrated Method for Chinese Unknown Word Extraction
Zhiyong Luo | Rou Song
Proceedings of the Third SIGHAN Workshop on Chinese Language Processing