{"title":"Toward a cognitive dependency grammar of Hungarian","authors":"András Imrényi","doi":"10.18653/v1/W19-7710","DOIUrl":"https://doi.org/10.18653/v1/W19-7710","url":null,"abstract":"","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122998607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The goal of this paper is to provide a description of the syntax of exceptive constructions within a dependency framework. These constructions are introduced in English by the markers except, but, except for, apart from, other than, etc. Examining their syntactic properties across a variety of languages shows that they imply two main types of constructions: The paradigmatic - EC and the hypotactic - EC. The first type shares many properties with coordination, and it can be integrated into the paradigmatic lists/piles phenomena in which two segments of the utterance pile up on the same syntactic position and whose most famous case is coordination.
本文的目的是提供依赖性框架中异常结构的语法描述。这些结构在英语中由except, but, except for, apart from, other than等标记引入。在各种语言中考察它们的句法特征表明，它们暗示着两种主要类型的结构:聚合- EC和形合- EC。第一种类型与配位有许多相似之处，它可以被整合到话语的两个片段在同一句法位置上堆积的聚合列表/堆现象中，其中最著名的例子是配位。
{"title":"Exceptive constructions. A Dependency-based Analysis","authors":"M. Galal, Sylvain Kahane, Yomna Safwat","doi":"10.18653/v1/W19-7720","DOIUrl":"https://doi.org/10.18653/v1/W19-7720","url":null,"abstract":"The goal of this paper is to provide a description of the syntax of exceptive constructions within a dependency framework. These constructions are introduced in English by the markers except, but, except for, apart from, other than, etc. Examining their syntactic properties across a variety of languages shows that they imply two main types of constructions: The paradigmatic - EC and the hypotactic - EC. The first type shares many properties with coordination, and it can be integrated into the paradigmatic lists/piles phenomena in which two segments of the utterance pile up on the same syntactic position and whose most famous case is coordination.","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128980472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marie Mikulová, V. Kolářová, J. Panevová, E. Hajicová
The data of the Prague Czech-English Dependency Treebank (a member of the family of Prague Dependency Treebanks) have served as a basis for the comparative study of delimiting adverbial meanings of the local relation “within the given place”. The Czech prepositional groups containing the prepositions v, na, and u with the above meaning are compared with their English equivalents, using a more subtle differentiation into three semantic subgroups of "inside", "on the surface" and "at the given place". Our analysis confirms that though every language structures the reality in a different way, certain tendencies may be observed in the relation of the forms and their functions that eventually result in a more detailed classification. The contribution presents results of an ongoing work.
{"title":"Delimiting Adverbial Meanings. A corpus-based comparative study on Czech spatial prepositions and their English equivalents","authors":"Marie Mikulová, V. Kolářová, J. Panevová, E. Hajicová","doi":"10.18653/v1/W19-7718","DOIUrl":"https://doi.org/10.18653/v1/W19-7718","url":null,"abstract":"The data of the Prague Czech-English Dependency Treebank (a member of the family of Prague Dependency Treebanks) have served as a basis for the comparative study of delimiting adverbial meanings of the local relation “within the given place”. The Czech prepositional groups containing the prepositions v, na, and u with the above meaning are compared with their English equivalents, using a more subtle differentiation into three semantic subgroups of \"inside\", \"on the surface\" and \"at the given place\". Our analysis confirms that though every language structures the reality in a different way, certain tendencies may be observed in the relation of the forms and their functions that eventually result in a more detailed classification. The contribution presents results of an ongoing work.","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132431416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dependency parsing as sequence labeling has recently proved to be a relevant alternative to the traditional transitionand graph-based approaches. It offers a good trade-off between parsing accuracy and speed. However, recent work on dependency parsing as sequence labeling ignore the pre-processing time of Part-of-Speech tagging – which is required for this task – in the evaluation of speed while other studies showed that Part-of-Speech tags are not essential to achieve state-ofthe-art parsing scores. In this paper, we compare the accuracy and speed of shared and stacked multi-task learning strategies – as well as a strategy that combines both – to learn Part-of-Speech tagging and dependency parsing in a single sequence labeling pipeline. In addition, we propose an alternative encoding of the dependencies as labels which does not use Part-of-Speech tags and improves dependency parsing accuracy for most of the languages we evaluate.
{"title":"Dependency Parsing as Sequence Labeling with Head-Based Encoding and Multi-Task Learning","authors":"Ophélie Lacroix","doi":"10.18653/v1/W19-7716","DOIUrl":"https://doi.org/10.18653/v1/W19-7716","url":null,"abstract":"Dependency parsing as sequence labeling has recently proved to be a relevant alternative to the traditional transitionand graph-based approaches. It offers a good trade-off between parsing accuracy and speed. However, recent work on dependency parsing as sequence labeling ignore the pre-processing time of Part-of-Speech tagging – which is required for this task – in the evaluation of speed while other studies showed that Part-of-Speech tags are not essential to achieve state-ofthe-art parsing scores. In this paper, we compare the accuracy and speed of shared and stacked multi-task learning strategies – as well as a strategy that combines both – to learn Part-of-Speech tagging and dependency parsing in a single sequence labeling pipeline. In addition, we propose an alternative encoding of the dependencies as labels which does not use Part-of-Speech tags and improves dependency parsing accuracy for most of the languages we evaluate.","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124780852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lexical preferences encoded as association metrics have been shown to improve performance on structural ambiguities that are still challenging for modern parsers. This paper introduces a mechanism to include lexical preferences into a neural transition-based dependency parser for German. We compare pointwise mutual information (PMI) and embedding-based scores. Both the PMI-based model and the embedding-based model outperform the baseline significantly. The best model is PMI-based and increases overall performance by 0.26 LAS points over the baseline.
{"title":"Association Metrics in Neural Transition-Based Dependency Parsing","authors":"Patricia Fischer, Sebastian Pütz, Daniël de Kok","doi":"10.18653/v1/W19-7722","DOIUrl":"https://doi.org/10.18653/v1/W19-7722","url":null,"abstract":"Lexical preferences encoded as association metrics have been shown to improve performance on structural ambiguities that are still challenging for modern parsers. This paper introduces a mechanism to include lexical preferences into a neural transition-based dependency parser for German. We compare pointwise mutual information (PMI) and embedding-based scores. Both the PMI-based model and the embedding-based model outperform the baseline significantly. The best model is PMI-based and increases overall performance by 0.26 LAS points over the baseline.","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127122336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
How to Parse Low-Resource Languages : Cross-Lingual Parsing, Target Language Annotation, or Both?
如何解析低资源语言:跨语言解析，目标语言注释，还是两者兼而有之?
{"title":"How to Parse Low-Resource Languages: Cross-Lingual Parsing, Target Language Annotation, or Both?","authors":"Ailsa Meechan-Maddon, Joakim Nivre","doi":"10.18653/v1/W19-7713","DOIUrl":"https://doi.org/10.18653/v1/W19-7713","url":null,"abstract":"How to Parse Low-Resource Languages : Cross-Lingual Parsing, Target Language Annotation, or Both?","PeriodicalId":443459,"journal":{"name":"Proceedings of the Fifth International Conference on Dependency Linguistics (Depling, SyntaxFest 2019)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127365142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：