arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1606.04279cs.CL
收藏

低资源语言的跨语言形态标注

Cross-Lingual Morphological Tagging for Low-Resource Languages

University of Oxford(牛津大学);Google Inc.(谷歌公司)

Jan Buys, Jan A. Botha

摘要:

形态丰富的语言通常缺乏开发准确的自然语言处理工具所需的注释语言资源。我们提出了适合于训练形态标签丰富的标签集低资源的语言,而不使用直接监督模型。我们的方法扩展了现有的方法投影跨语言的词性标签,使用bitext推断一个给定的单词类型或令牌的可能的标签上的约束。我们提出了一个标记模型,使用Wsabie,一个判别式嵌入为基础的模型与基于排名的学习。在我们对11种语言的评估中,该模型的平均性能与基线弱监督HMM相当,同时更具可扩展性。多语言实验表明,该方法在相关语言对之间进行投影时表现最好。尽管固有的有损投影,我们表明,我们的模型预测的形态标签提高了下游性能的解析器平均+0.6 LAS。

英文摘要:

Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource languages without using direct supervision. Our approach extends existing approaches of projecting part-of-speech tags across languages, using bitext to infer constraints on the possible tags for a given word type or token. We propose a tagging model using Wsabie, a discriminative embedding-based model with rank-based learning. In our evaluation on 11 languages, on average this model performs on par with a baseline weakly-supervised HMM, while being more scalable. Multilingual experiments show that the method performs best when projecting between related language pairs. Despite the inherently lossy projection, we show that the morphological tags predicted by our models improve the downstream performance of a parser by +0.6 LAS on average.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑