融合多粒度特征的低资源语言词性标注和依存分析联合模型

A Joint Modelof POS Tagging and Dependency Parsing with Multi-Granularity Features for Low-resource Language

研究低资源语言的词性标注和依存分析对推动低资源自然语言处理任务有着重要的作用。针对低资源语言词嵌入表示,已有工作并没有充分利用字符、子词层面信息编码,导致模型无法利用不同粒度的特征。对此,该文提出融合多粒度特征的词嵌入表示,利用不同的语言模型分别获得字符、子词以及词语层面的语义信息,将三种粒度的词嵌入进行拼接,达到丰富语义信息的目的,缓解由于标注数据稀缺导致的依存分析模型性能不佳的问题。进一步将词性标注和依存分析模型进行联合训练,使模型之间能相互共享知识,降低词性标注错误在依存分析任务上的线性传递。以泰语、越南语为研究对象,在宾州树库数据集上的试验表明,该文方法相比于基线模型的UAS、LAS、POS均有明显提升。

The part-of-speech tagging and dependency parsing of low-resource languages plays an important role in promoting low-resource language processing.For low-resource languages,we propose a word embedding representation that integrates multi-granularity features,and apply different language models at the character,sub-word and word level.Word embeddings in three granularities are then combined to enrich semantic information.The part-of-speech tagging and dependency parsing model are further jointly trained,sharing knowledge with each other to alleviate the pipeline error accumulation.Taking Thai and Vietnamese from the Penn Treebank data set,the proposed method significantly out-performs the baseline model according to UAS,LAS,and POS index.