CDCPP:跨领域中文标点符号预测(CDCPP: Cross-Domain Chinese Punctuation Prediction)

no code implementations • CCL 2020 • Pengyuan Liu, Weikang Wang, Likun Qiu, Bingjie Du

多目标情感分类中文数据集构建及分析研究(Construction and Analysis of Chinese Multi-Target Sentiment Classification Dataset)

no code implementations • CCL 2020 • Pengyuan Liu, Yongsheng Tian, Chengyu Du, Likun Qiu

目标级情感分类任务是要得到句子中特定评价目标的情感倾向。一个评论句中往往存在多个目标, 多个目标的情感可能一致, 也可能不一致。但在已有针对目标级情感分类的评测数据集中:1)大多数是一个句子一个目标;2)在少数有多个目标的句子中, 多个目标情感倾向分布很不均衡, 多个目标情感一致的情形占较大优势。数据集本身的缺陷限制了模型针对多个目标进行情感分类的提升空间。针对以上问题, 本文构建了一个针对多目标情感分类的中文数据集, 人工标注了6339个评价目标, 共2071条数据。该数据集:1)评价目标个数分布平衡;2)情感正负极性分布平衡;3)多目标情感倾向分布平衡。随后, 本文利用多个目标情感分类的主流模型在该数据集上进行了实验与比较分析。结果表明现有主流模型尚不能对存在多个目标且目标情感倾向性不一致实例中的目标进行很好的分类, 尤其是目标的情感倾向为中性时。多目标情感分类任务具有一定的难度与挑战性。

Sentiment Analysis Sentiment Classification

Improving Cross-Domain Chinese Word Segmentation with Word Embeddings

1 code implementation • NAACL 2019 • Yuxiao Ye, Yue Zhang, Weikang Li, Likun Qiu, Jian Sun

Cross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS.

Chinese Word Segmentation Segmentation +1

Syntactic Dependencies and Distributed Word Representations for Analogy Detection and Mining

no code implementations • EMNLP 2015 • Likun Qiu, Yue Zhang, Yanan Lu

Information Retrieval Machine Translation +3

ZORE: A Syntax-based System for Chinese Open Relation Extraction

no code implementations • EMNLP 2014 • Likun Qiu, Yue Zhang

Relation Relation Extraction

Multi-view Chinese Treebanking

no code implementations • COLING 2014 • Likun Qiu, Yue Zhang, Peng Jin, Houfeng Wang

Dependency Parsing Machine Translation

Exploiting Discourse Relations for Sentiment Analysis

no code implementations • COLING 2012 • Fei Wang, Yunfang Wu, Likun Qiu

Sentiment Analysis