Junsheng Zhou


2020

pdf bib
基于神经网络的连动句识别(Recognition of serial-verb sentences based on Neural Network)
Chao Sun (孙超) | Weiguang Qu (曲维光) | Tingxin Wei (魏庭新) | Yanhui Gu (顾彦慧) | Bin Li (李斌) | Junsheng Zhou (周俊生)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

连动句是具有连动结构的句子,是汉语中的特殊句法结构,在现代汉语中十分常见且使用频繁。连动句语法结构和语义关系都很复杂,在识别中存在许多问题,对此本文针对连动句的识别问题进行了研究,提出了一种基于神经网络的连动句识别方法。本方法分两步:第一步,运用简单的规则对语料进行预处理;第二步,用文本分类的思想,使用BERT编码,利用多层CNN与BiLSTM模型联合提取特征进行分类,进而完成连动句识别任务。在人工标注的语料上进行实验,实验结果达到92.71%的准确率,F1值为87.41%。

pdf bib
基于深度学习的实体关系抽取研究综述(Review of Entity Relation Extraction based on deep learning)
Zhentao Xia (夏振涛) | Weiguang Qu (曲维光) | Yanhui Gu (顾彦慧) | Junsheng Zhou (周俊生) | Bin Li (李斌)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

作为信息抽取的一项核心子任务,实体关系抽取对于知识图谱、智能问答、语义搜索等自然语言处理应用都十分重要。关系抽取在于从非结构化文本中自动地识别实体之间具有的某种语义关系。该文聚焦句子级别的关系抽取研究,介绍用于关系抽取的主要数据集并对现有的技术作了阐述,主要分为:有监督的关系抽取、远程监督的关系抽取和实体关系联合抽取。我们对比用于该任务的各种模型,分析它们的贡献与缺 陷。最后介绍中文实体关系抽取的研究现状和方法。

pdf bib
面向中文AMR标注体系的兼语语料库构建及识别研究(Research on the Construction and Recognition of Concurrent corpus for Chinese AMR Annotation System)
Wenhui Hou (侯文惠) | Weiguang Qu (曲维光) | Tingxin Wei (魏庭新) | Bin Li (李斌) | Yanhui Gu (顾彦慧) | Junsheng Zhou (周俊生)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

兼语结构是汉语中常见的一种动词结构,由述宾短语与主谓短语共享兼语,结构复杂,给句法分析造成困难,因此兼语语料库构建及识别工作对于语义解析及下游任务都具有重要意义。但现存兼语语料库较少,面向中文AMR标注体系的兼语语料库构建仍处于空白阶段。针对这一现状,本文总结了一套兼语语料库标注规范,并构建了一定数量面向中文AMR标注体系的兼语语料库。基于构建的语料库,采用基于字符的神经网络模型识别兼语结构,并对识别结果以及未来的改进方向进行分析总结。

pdf bib
An Element-aware Multi-representation Model for Law Article Prediction
Huilin Zhong | Junsheng Zhou | Weiguang Qu | Yunfei Long | Yanhui Gu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Existing works have proved that using law articles as external knowledge can improve the performance of the Legal Judgment Prediction. However, they do not fully use law article information and most of the current work is only for single label samples. In this paper, we propose a Law Article Element-aware Multi-representation Model (LEMM), which can make full use of law article information and can be used for multi-label samples. The model uses the labeled elements of law articles to extract fact description features from multiple angles. It generates multiple representations of a fact for classification. Every label has a law-aware fact representation to encode more information. To capture the dependencies between law articles, the model also introduces a self-attention mechanism between multiple representations. Compared with baseline models like TopJudge, this model improves the accuracy of 5.84%, the macro F1 of 6.42%, and the micro F1 of 4.28%.

2016

pdf bib
AMR Parsing with an Incremental Joint Model
Junsheng Zhou | Feiyu Xu | Hans Uszkoreit | Weiguang Qu | Ran Li | Yanhui Gu
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
A Search-Based Dynamic Reranking Model for Dependency Parsing
Hao Zhou | Yue Zhang | Shujian Huang | Junsheng Zhou | Xin-Yu Dai | Jiajun Chen
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
A Fast Approach for Semantic Similar Short Texts Retrieval
Yanhui Gu | Zhenglu Yang | Junsheng Zhou | Weiguang Qu | Jinmao Wei | Xingtian Shi
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
Exploiting Chunk-level Features to Improve Phrase Chunking
Junsheng Zhou | Weiguang Qu | Fen Zhang
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2006

pdf bib
Chinese Named Entity Recognition with a Multi-Phase Model
Junsheng Zhou | Liang He | Xinyu Dai | Jiajun Chen
Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing