arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.04208cs.CL
收藏

基于神经半马尔可夫条件随机场的鲁棒词性标注

Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging

Center for Information and Language Processing (CIS), LMU Munich(慕尼黑大学信息与语言处理中心(CIS));University of Patras(帕特雷大学);Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心(BCAI))

Apostolos Kemos, Heike Adel, Hinrich Schütze

摘要:

标记的更高级模型已被证明在处理标记内噪声和词汇表外单词方面是有效的。但这些模型仍然依赖于正确的令牌边界。在本文中,我们提出了一种新的端到端的字符级模型,并证明了它的有效性,在多语言设置和令牌边界是嘈杂的。我们的模型是一个半马尔可夫条件随机场,具有用于字符和段表示的神经网络。它不需要tokenizer。该模型与各种语言的最先进的基线相匹配,并且在嘈杂的英语版本的词性标记基准数据集上的表现明显优于它们。我们的代码和噪声数据集可以在http://cistern.cis.lmu.de/semiCRF上公开获得。

英文摘要:

Character-level models of tokens have been shown to be effective at dealing with within-token noise and out-of-vocabulary words. But these models still rely on correct token boundaries. In this paper, we propose a novel end-to-end character-level model and demonstrate its effectiveness in multilingual settings and when token boundaries are noisy. Our model is a semi-Markov conditional random field with neural networks for character and segment representation. It requires no tokenizer. The model matches state-of-the-art baselines for various languages and significantly outperforms them on a noisy English version of a part-of-speech tagging benchmark dataset. Our code and the noisy dataset are publicly available at http://cistern.cis.lmu.de/semiCRF.

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。

↑