发布求助
文献互助 智能选刊 最新文献

Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)最新文献

筛选
英文 中文
Improving the Annotations in the Turkish Universal Dependency Treebank 改进了土耳其通用依赖树库中的注解
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-8013
Utku Türk, Furkan Atmaca, Saziye Betül Özates, Balkiz Öztürk Basaran, Tunga Güngör, Arzucan Özgür
{"title":"Improving the Annotations in the Turkish Universal Dependency Treebank","authors":"Utku Türk, Furkan Atmaca, Saziye Betül Özates, Balkiz Öztürk Basaran, Tunga Güngör, Arzucan Özgür","doi":"10.18653/v1/W19-8013","DOIUrl":"https://doi.org/10.18653/v1/W19-8013","url":null,"abstract":"This study focuses on a comprehensive analysis and manual re-annotation of the Turkish IMST-UD Treebank, which was automatically converted from the IMST Treebank (Sulubacak et al., 2016b). In accordance with the Universal Dependencies’ guidelines and the necessities of Turkish grammar, the existing treebank was revised. The current study presents the revisions that were made alongside the motivations behind the major changes. Moreover, it reports the parsing results of a transition-based dependency parser and a graph-based dependency parser obtained over the previous and updated versions of the treebank. In light of these results, we have observed that the re-annotation of the Turkish IMST-UD treebank improves performance with regards to dependency parsing.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114377978","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}
引用次数: 6
Universal Dependencies for Mbyá Guaraní mby<e:1> Guaraní的通用依赖
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-8008
Guillaume Thomas
{"title":"Universal Dependencies for Mbyá Guaraní","authors":"Guillaume Thomas","doi":"10.18653/v1/W19-8008","DOIUrl":"https://doi.org/10.18653/v1/W19-8008","url":null,"abstract":"This paper presents the first treebank of Mbyá Guaraní, a Tupí-Guaraní language spoken in Argentina, Brazil and Paraguay. The Mbyá treebank is part of Universal Dependencies, a project that aims to create a set of guidelines for the consistent grammatical annotation of typologically different languages. We describe the composition of the treebank, and non-trivial choices that were made in the adaptation of Universal Dependencies guidelines to the annotation of Mbyá.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117160082","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}
引用次数: 10
Survey of Uralic Universal Dependencies development 乌拉尔语普遍依赖关系发展概况
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-8009
N. Partanen, Jack Rueter
{"title":"Survey of Uralic Universal Dependencies development","authors":"N. Partanen, Jack Rueter","doi":"10.18653/v1/W19-8009","DOIUrl":"https://doi.org/10.18653/v1/W19-8009","url":null,"abstract":"This paper attempts to evaluate some of the systematic differences in Uralic Universal Dependencies treebanks from a perspective that would help to introduce reasonable improvements in treebank annotation consistency within this language family. The study finds that the coverage of Uralic languages in the project is already relatively high, and the majority of typically Uralic features are already present and can be discussed on the basis of existing treebanks. Some of the idiosyncrasies found in individual treebanks stem from language-internal grammar traditions, and could be a target for harmonization in later phases.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127855183","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}
引用次数: 10
Building a treebank for Occitan: what use for Romance UD corpora? 为欧西坦建立一个树库:对罗曼蒂克语料库有什么用?
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-8002
A. Miletic, M. Bras, Louise Esher, J. Sibille, Marianne Vergez-Couret
{"title":"Building a treebank for Occitan: what use for Romance UD corpora?","authors":"A. Miletic, M. Bras, Louise Esher, J. Sibille, Marianne Vergez-Couret","doi":"10.18653/v1/W19-8002","DOIUrl":"https://doi.org/10.18653/v1/W19-8002","url":null,"abstract":"This paper describes the application of delexicalized cross-lingual parsing on Occitan with a view to building the first dependency treebank of this language. Occitan is a Romance language spoken in the south of France and in parts of Italy and Spain. It is a relatively low-resourced language and does not have a syntactically annotated corpus as of yet. In order to facilitate the manual annotation process, we train parsing models on the existing Romance corpora from the Universal Dependencies project and apply them to Occitan. Special attention is given to the effect of this cross-lingual annotation on the work of human annotators in terms of annotation speed and ease.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127962933","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}
引用次数: 4
Developing Universal Dependencies for Wolof 开发Wolof的通用依赖
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-8003
Cheikh M. Bamba Dione
{"title":"Developing Universal Dependencies for Wolof","authors":"Cheikh M. Bamba Dione","doi":"10.18653/v1/W19-8003","DOIUrl":"https://doi.org/10.18653/v1/W19-8003","url":null,"abstract":"This paper presents work on the creation of a Universal Dependency (UD) treebank for Wolof as the first UD treebank within the Northern Atlantic branch of the Niger-Congo languages. The paper reports on various issues related to word segmentation for tokenization and the mapping of PoS tags, morphological features and dependency relations to existing conventions for annotating Wolof. It also outlines some specific constructions as a starting point for discussing several more general UD annotation guidelines, in particular for noun class marking, deixis encoding, and focus marking.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123212218","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}
引用次数: 12
Recursive LSTM Tree Representation for Arc-Standard Transition-Based Dependency Parsing 基于arc标准转换的依赖解析的递归LSTM树表示
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-8012
Mohab Elkaref, Bernd Bohnet
{"title":"Recursive LSTM Tree Representation for Arc-Standard Transition-Based Dependency Parsing","authors":"Mohab Elkaref, Bernd Bohnet","doi":"10.18653/v1/W19-8012","DOIUrl":"https://doi.org/10.18653/v1/W19-8012","url":null,"abstract":"We propose a method to represent dependency trees as dense vectors through the recursive application of Long Short-Term Memory networks to build Recursive LSTM Trees (RLTs). We show that the dense vectors produced by Recursive LSTM Trees replace the need for structural features by using them as feature vectors for a greedy Arc-Standard transition-based dependency parser. We also show that RLTs have the ability to incorporate useful information from the bi-LSTM contextualized representation used by Cross and Huang (2016) and Kiperwasser and Goldberg (2016b). The resulting dense vectors are able to express both structural information relating to the dependency tree, as well as sequential information relating to the position in the sentence. The resulting parser only requires the vector representations of the top two items on the parser stack, which is, to the best of our knowledge, the smallest feature set ever published for Arc-Standard parsers to date, while still managing to achieve competitive results.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"39 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":"132917492","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}
引用次数: 1
Improving UD processing via satellite resources for morphology 利用卫星资源改进形态学的UD处理
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-8004
K. Dobrovoljc, T. Erjavec, Nikola Ljubesic
{"title":"Improving UD processing via satellite resources for morphology","authors":"K. Dobrovoljc, T. Erjavec, Nikola Ljubesic","doi":"10.18653/v1/W19-8004","DOIUrl":"https://doi.org/10.18653/v1/W19-8004","url":null,"abstract":"This paper presents the conversion of the reference language resources for Croatian and Slovenian morphology processing to UD morphological specifications. We show that the newly available training corpora and inflectional dictionaries improve the baseline stanfordnlp performance obtained on officially released UD datasets for lemmatization, morphology prediction and dependency parsing, illustrating the potential value of such satellite UD resources for languages with rich morphology.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"11 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":"123359743","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}
引用次数: 3
Universal Dependencies in a galaxy far, far away... What makes Yoda’s English truly alien 宇宙依赖关系在遥远的星系…是什么让尤达的英语如此异类
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-8005
N. Levshina
{"title":"Universal Dependencies in a galaxy far, far away... What makes Yoda’s English truly alien","authors":"N. Levshina","doi":"10.18653/v1/W19-8005","DOIUrl":"https://doi.org/10.18653/v1/W19-8005","url":null,"abstract":"This paper investigates the word order used by Yoda, a character from the Star Wars universe. His clauses typically contain an Object, Oblique and/or non-finite part of the predicate followed by the subject and the finite predicate/auxiliary/copula, e.g. Help you it will. Using the sentences in Yodish from the scripts of the Star War films, this paper examines three crosslinguistically common tendencies, which can be explained by optimization of processing: the trade-off between entropy of S and O order and morphological cues, minimization of dependency lengths, and the tendency to place the verb in the end of a clause. For comparison, a standardized version of Yoda’s sentences is used, as well as the Universal Dependencies corpora. The results of quantitative analyses indicate that Yodish is less adjusted to human processor’s needs than standard English and other human languages.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, 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":"133185650","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}
引用次数: 1
Building minority dependency treebanks, dictionaries and computational grammars at the same time—an experiment in Karelian treebanking 同时建立少数依赖关系树库、字典和计算语法——卡累利阿树库的实验
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-8016
Flammie A. Pirinen
{"title":"Building minority dependency treebanks, dictionaries and computational grammars at the same time—an experiment in Karelian treebanking","authors":"Flammie A. Pirinen","doi":"10.18653/v1/W19-8016","DOIUrl":"https://doi.org/10.18653/v1/W19-8016","url":null,"abstract":"Building a treebank from scratch can easily be an elaborate, highly time consuming task, especially when working with a minority language with moderately complex morphology and no existing resources. It is also then typically true that language experts and informants with suitable skill sets are a very scarce resource. In this experiment I have attempted to work in parallel on building NLP resources while gathering and annotating the treebank. In particular, I aim to build a decent coverage morphologically annotated lexicon suitable for rule-based morphological analysis as well as accompanying rules for basic morphosyntactic analysis. I propose here a workflow, that I have found useful in avoiding redoing same work with related NLP resource construction.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"119 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":"132018035","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}
引用次数: 11
Towards an adequate account of parataxis in Universal Dependencies 对普遍依赖中意合的充分解释
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019) Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-8011
Lars Ahrenberg
{"title":"Towards an adequate account of parataxis in Universal Dependencies","authors":"Lars Ahrenberg","doi":"10.18653/v1/W19-8011","DOIUrl":"https://doi.org/10.18653/v1/W19-8011","url":null,"abstract":"The parataxis relation as defined for Universal Dependencies 2.0 is general and, for this reason, sometimes hard to distinguish from competing analyses, such as coordination, conj, or apposition, appos. The specific subtypes that are listed for parataxis are also quite different in character. In this study we first show that the actual practice by UD-annotators is varied, using the parallel UD (PUD-) treebanks as data. We then review the current definitions and guidelines and suggest improvements.","PeriodicalId":294555,"journal":{"name":"Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019)","volume":"36 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":"132202643","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}
引用次数: 1
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信