A Latent Variable Model of Synchronous Syntactic-Semantic Parsing for Multiple Languages
A Latent Variable Model of Synchronous Syntactic-Semantic Parsing for Multiple Languages
复制标题
DOI：
10.3115/1596409.1596415
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Andrea Gesmundo;James Henderson;Paola Merlo;Ivan Titov
中科院分区：
文献类型：
--
作者：
Andrea Gesmundo;James Henderson;Paola Merlo;Ivan Titov
受2009年CoNLL共享任务语言数量多(7种)和开发时间短(2个月)的激励，我们利用潜在变量来避免昂贵的手工特征工程过程，允许潜在变量从数据中归纳特征。我们采用了一个已有的句法-语义依存联合分析的生成潜变量模型，该模型是为英语开发的，并将其应用于六种新的语言，并进行了最小的调整。解析器跨语言的健壮性表明该解析器具有非常通用的功能集。分析器的高性能表明它的潜在变量成功地提取了有效的特征。该系统总体排名第三，宏观平均F1得分为82.14%，仅比最好的系统差0.5%。
Motivated by the large number of languages (seven) and the short development time (two months) of the 2009 CoNLL shared task, we exploited latent variables to avoid the costly process of hand-crafted feature engineering, allowing the latent variables to induce features from the data. We took a pre-existing generative latent variable model of joint syntactic-semantic dependency parsing, developed for English, and applied it to six new languages with minimal adjustments. The parser's robustness across languages indicates that this parser has a very general feature set. The parser's high performance indicates that its latent variables succeeded in inducing effective features. This system was ranked third overall with a macro averaged F1 score of 82.14%, only 0.5% worse than the best system.