Grammar Formalisms beyond Context-Free Grammars and their use for Machine Learning Tasks

超越上下文无关语法的语法形式及其在机器学习任务中的用途

• 批准号: 183821958
• 负责人: Professorin Dr. Laura Kallmeyer
• 金额: --
• 依托单位: Abteilung für Computerlinguistik
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2010
• 资助国家: 德国
• 起止时间: 2009-12-31 至 2020-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/183821958?language=en
• 关键词: Grammar; Formalisms; beyond; Context; Free

The aim of this project is to develop new models and algorithms forprobabilistic parsing and for statistical machine translation, usingformalisms such as Linear Context-Free Rewriting Systems (LCFRSs),i.e., extensions of Context-Free Grammars that combine aspects ofsynchronous grammars with the capacity to describe discontinuities.Both, parsing and machine translation, face the challenge that theyhave to deal with non-local dependencies, to put it differently, withdiscontinuous units in a sentence that belong together. One way toaccount for these non-local phenomena is to use formalisms that candescribe more than just context-free structures. In the first part ofthe project, this has already been successfully done in parsing, wherewe use LCFRS. We plan to continue this line of research in the secondpart of the project. Concerning syntax-based statistical machinetranslation, we have shown in the first part of the project thatsynchronous LCFRS can describe the sometimes complex alignments oneencounters in parallel corpora. In the second part of the project wetherefore aim at completing the (already started) implementation of astatistical machine translation system based on synchronous LCFRS.

这个项目的目的是为概率分析和统计机器翻译开发新的模型和算法，使用线性上下文自由重写系统（LCFRSs）等形式。上下文无关语法的扩展，它将同步语法的各个方面与描述不连续性的能力相结合。解析和机器翻译都面临着必须处理非局部依赖关系的挑战，换句话说，句子中属于一起的不连续单元。解释这些非局部现象的一种方法是使用可以描述不仅仅是上下文无关结构的形式主义。在项目的第一部分中，这已经在解析中成功地完成了，其中我们使用了LCFRS。我们计划在项目的第二部分继续这方面的研究。关于基于语法的统计机器翻译，我们已经在项目的第一部分中展示了同步LCFRS可以描述在并行语料库中遇到的有时复杂的对齐。因此，在项目的第二部分，我们的目标是完成（已经开始的）基于同步LCFRS的统计机器翻译系统的实现。

项目成果

Data-Oriented Parsing with Discontinuous Constituents and Function Tags

• DOI: 10.15398/jlm.v4i1.100
• 发表时间: 2016-04
• 期刊: J. Lang. Model.
• 作者: Andreas van Cranenburgh;R. Scha;R. Bod

A Neural Graph-based Approach to Verbal MWE Identification

基于神经图的言语 MWE 识别方法

• DOI: 10.18653/v1/w19-5113
• 发表时间: 2019
• 作者: Waszczuk;R. Ehren;R. Stodden ;L. Kallmeyer
• 通讯作者: L. Kallmeyer

Hierarchical Machine Translation With Discontinuous Phrases

具有不连续短语的分层机器翻译

• DOI: 10.18653/v1/w15-3028
• 发表时间: 2015
• 作者: Kaeshammer

Discontinuous parsing with continuous trees

• DOI: 10.18653/v1/w16-0906
• 发表时间: 2016
• 作者: Wolfgang Maier;Timm Lichte

Statistical Parsing of Tree Wrapping Grammars

• DOI: 10.18653/v1/2020.coling-main.595
• 发表时间: 2020-12
• 作者: Tatiana Bladier;J. Waszczuk;Laura Kallmeyer