高级检索
    曾碧卿, 曾锋, 韩旭丽, 商齐. 基于交互特征表示的评价对象抽取模型[J]. 计算机研究与发展, 2021, 58(1): 224-232. DOI: 10.7544/issn1000-1239.2021.20190305
    引用本文: 曾碧卿, 曾锋, 韩旭丽, 商齐. 基于交互特征表示的评价对象抽取模型[J]. 计算机研究与发展, 2021, 58(1): 224-232. DOI: 10.7544/issn1000-1239.2021.20190305
    Zeng Biqing, Zeng Feng, Han Xuli, Shang Qi. Aspect Extraction Model Based on Interactive Feature Representation[J]. Journal of Computer Research and Development, 2021, 58(1): 224-232. DOI: 10.7544/issn1000-1239.2021.20190305
    Citation: Zeng Biqing, Zeng Feng, Han Xuli, Shang Qi. Aspect Extraction Model Based on Interactive Feature Representation[J]. Journal of Computer Research and Development, 2021, 58(1): 224-232. DOI: 10.7544/issn1000-1239.2021.20190305

    基于交互特征表示的评价对象抽取模型

    Aspect Extraction Model Based on Interactive Feature Representation

    • 摘要: 评价对象抽取是对象级情感分析的关键任务之一,评价对象抽取结果会直接影响对象级情感分类的准确率.在评价对象抽取任务中,借助手工特征加强模型性能的方式既消耗时间又耗费人力.针对数据规模小、特征信息不充分等问题,提出一种基于交互特征表示的评价对象抽取模型(aspect extraction model based on interactive feature representation, AEMIFR).相比其他模型,AEMIFR模型结合字符级嵌入与单词嵌入,捕获单词的语义特征、字符的形态特征以及字符与词语之间的内在联系.而且,AEMIFR模型获取文本的局部特征表示和上下文依赖特征表示,并学习2种特征表示之间的交互关系,增强2种特征之间的相似特征的重要性,减少无用特征对模型的消极影响,以及学习更高质量的特征表示.最后在SemEval 2014,SemEval 2015,SemEval 2016中的数据集L-14,R-14,R-15,R-16上进行实验,取得具有竞争力的效果.

       

      Abstract: Aspect extraction is one of the key tasks in aspect level sentiment analysis, whose result will directly affect the accuracy of aspect level sentiment classification. In aspect extraction task, it is both time and labor consuming to enhance the performance of the model by handcraft features. Aiming at resolving the problems of insufficient data scale, insufficient feature information, etc., aspect extraction model based on interactive feature representation (AEMIFR) is proposed. Compared with other models, AEMIFR combines character level embedding and word embedding to capture the semantic features of words, the morphological features of characters and the internal relationship between characters and words. Furthermore, AEMIFR obtains the local feature representation and context-dependent feature representation of text, learns the interaction between the two feature representations, enhances the importance of similar features between the two feature representations, reduces the negative impact of useless features on the model, and learns higher quality feature representations. Finally experiments are conducted on the data sets L-14, R-14, R-15 and R-16 in SimEval 2014, SemEval 2015 and SemEval 2016, and the competitive effect is achieved.

       

    /

    返回文章
    返回