• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference of the European Chapter of the Association for Computational Linguistics >The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations
【24h】

The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations

机译：平行意义库：迈向具有构成意义表示法的多语种翻译语料库

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The Parallel Meaning Bank is a cor pus of translations annotated with shared, formal meaning representations compris ing over 11 million words divided over four languages (English, German, Ital ian, and Dutch). Our approach is based on cross-lingual projection: automatically produced (and manually corrected) se mantic annotations for English sentences are mapped onto their word-aligned trans lations, assuming that the translations are meaning-preserving. The semantic anno tation consists of five main steps: (i) seg mentation of the text in sentences and lexi cal items; (ii) syntactic parsing with Com binatory Categorial Grammar; (iii) uni versal semantic tagging; (iv) symboliza-tion; and (v) compositional semantic anal ysis based on Discourse Representation Theory. These steps are performed us ing statistical models trained in a semi-supervised manner. The employed annota tion models are all language-neutral. Our first results are promising.
机译：并行意思库是翻译的一部分，带有共享的正式意思表示，包括超过1100万个单词，分为四种语言（英语，德语，意大利语和荷兰语）。我们的方法基于跨语言投影：假设翻译是保留含义的，则自动为英语句子生成（并手动纠正）的语义注释会映射到其单词对齐的翻译中。语义注释包括五个主要步骤：（i）对句子和词汇项中的文本进行分段; （ii）使用组合分类语法进行句法分析; （iii）通用语义标记; （iv）符号化; （v）基于话语表征理论的成分语义分析。这些步骤是通过以半监督方式训练的统计模型执行的。所采用的注释模型均与语言无关。我们的第一个结果是有希望的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号