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 1602.07749cs.CL
收藏

基于循环神经网络的提及检测鲁棒性

Toward Mention Detection Robustness with Recurrent Neural Networks

New York University(纽约大学);IBM T.J. Watson Research Center(IBM托马斯·J·沃森研究中心)

Thien Huu Nguyen, Avirup Sil, Georgiana Dinu, Radu Florian

摘要:

自然语言处理(NLP)的一个关键挑战是在应用程序域和语言之间产生良好的性能。在这项工作中,我们研究的提及检测系统的鲁棒性,在信息抽取的基本任务之一,通过循环神经网络(RNN)。与传统方法相比,RNN的优势在于它们能够捕获大范围的上下文,并隐式地将在大型语料库上训练的词嵌入调整为特定于任务的词表示,但仍然保留了原始的语义概括,以便在跨领域中有所帮助。我们对RNN架构的系统评估表明,RNN不仅在一般环境中优于最好的报告系统(相对误差降低高达9%),而且在英语跨域环境中也达到了最先进的性能。对于其他语言,RNN在荷兰语的命名实体识别的类似任务上明显优于传统方法(相对错误减少高达22%)。

英文摘要:

One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages. In this work, we investigate the robustness of the mention detection systems, one of the fundamental tasks in information extraction, via recurrent neural networks (RNNs). The advantage of RNNs over the traditional approaches is their capacity to capture long ranges of context and implicitly adapt the word embeddings, trained on a large corpus, into a task-specific word representation, but still preserve the original semantic generalization to be helpful across domains. Our systematic evaluation for RNN architectures demonstrates that RNNs not only outperform the best reported systems (up to 9\% relative error reduction) in the general setting but also achieve the state-of-the-art performance in the cross-domain setting for English. Regarding other languages, RNNs are significantly better than the traditional methods on the similar task of named entity recognition for Dutch (up to 22\% relative error reduction).

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。

↑