International Workshop on Treebanks and Linguistic Theories最新文献

{"title":"Akkadian Treebank for early Neo-Assyrian Royal Inscriptions","authors":"M. Luukko, Aleksi Sahala, S. Hardwick, Krister Lindén","doi":"10.18653/v1/2020.tlt-1.11","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.11","url":null,"abstract":"This paper presents the first proper syntactic treebank for Akkadian, an ancient Semitic language which can only be reconstructed from its textual data. We introduce our corpus of early NeoAssyrian royal inscriptions, present some typical syntactic constructions of this genre and discuss the morphological and syntactic choices we have made. For developing a gold standard for morphological annotations, we tested the manually annotated material against BabyFST, a morphological analyzer of Akkadian. We also tested the reproducibility of the syntactic annotations using the TurkuNLP neural parser.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123205625","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}

{"title":"Dependency Relations for Sanskrit Parsing and Treebank","authors":"Amba P. Kulkarni, Pavankumar Satuluri, Sanjeev Panchal, Malay Maity, Amruta Malvade","doi":"10.18653/v1/2020.tlt-1.12","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.12","url":null,"abstract":"Dependency relations are needed for the development of a dependency treebank and a dependency parser. The guidelines1 for the development of treebank for Sanskrit proposed a set of dependency relations. Use of these relations for the development of a sentence generator and a dependency parser for Sanskrit demanded a need for an enhancement as well as a revision of these relations. In this paper, we discuss the revised version of these relations and discuss the cases where there is a possibility of multiple tagging either due to the ellipsis of certain arguments or due to the possible derivational morphological analysis. This led us to arrive at specific instructions for handling such cases during the tagging. A treebank with around 4000 sentences has been developed following these guidelines. Finally we evaluate a grammar based dependency parser for Sanskrit on this treebank and report its performance.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"35 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":"134034799","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}

{"title":"Building a Treebank for Chinese Literature for Translation Studies","authors":"Hai Hu, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Sandra Kübler, C. Lin","doi":"10.18653/v1/2020.tlt-1.2","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.2","url":null,"abstract":"We present a new Chinese Treebank in the literary domain, the Treebank for Chinese Literature (TCL), with an aim to foster translation studies by providing an annotated collection of Chinese texts from both translated and non-translated literature. In the current stage, our constituency treebank consists of 2 069 trees, annotated and cross-checked by six Chinese linguists, following and adapting the Chinese Penn Treebank (CTB) annotation guidelines. We discuss the issues that we encountered while annotating literary texts, and we demonstrate the usefulness of our treebank by comparing it against the news portion of CTB, and by analyzing the syntactic features of non-translated literary texts and translationese in Chinese.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"7 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":"117084197","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}

{"title":"Subjects tend to be coded only once: Corpus-based and grammar-based evidence for an efficiency-driven trade-off","authors":"Aleksandrs Berdicevskis, Karsten Schmidtke-Bode, Ilja A. Seržant","doi":"10.18653/v1/2020.tlt-1.8","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.8","url":null,"abstract":"Using data from the World Atlas of Language Structures and the Universal Dependencies treebanks, we provide converging evidence from linguistic typology and comparative corpus linguistics for an efficiency-based trade-off in the encoding of referentially accessible subjects. Specifically, when familiar subjects are marked as bound elements attaching to the verb, the chances of having obligatory independent subject pronouns decrease significantly across the world’s languages. At the same time, there is a trend against not encoding the subject at all, leading us to postulate an overall tendency to encode familiar subjects once and only once in a neutral topiccomment utterance. This tendency is mirrored in more fine-grained corpus data from Slavic: East Slavic languages, in contrast to the other members of the genus, have past forms without verbal subject encoding, and it is precisely with these (former participle) forms that the use of independent subject pronouns is significantly higher than with other, non-participial verb forms. By contrast, the occurrence of independent subject pronouns does not differ across various verb forms in other Slavic languages, as none of them has been affected by a loss of verbal subject encoding.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"29 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":"132641937","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}

{"title":"How tight is your language? A semantic typology based on Mutual Information","authors":"N. Levshina","doi":"10.18653/v1/2020.tlt-1.7","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.7","url":null,"abstract":"Languages differ in the degree of semantic flexibility of their syntactic roles. For example, English and Indonesian are considered more flexible with regard to the semantics of subjects, whereas German and Japanese are less flexible. In Hawkins’ classification, more flexible languages are said to have a loose fit, and less flexible ones are those that have a tight fit. This classification has been based on manual inspection of example sentences. The present paper proposes a new, quantitative approach to deriving the measures of looseness and tightness from corpora. We use corpora of online news from the Leipzig Corpora Collection in thirty typologically and genealogically diverse languages and parse them syntactically with the help of the Universal Dependencies annotation software. Next, we compute Mutual Information scores for each language using the matrices of lexical lemmas and four syntactic dependencies (intransitive subjects, transitive subject, objects and obliques). The new approach allows us not only to reproduce the results of previous investigations, but also to extend the typology to new languages. We also demonstrate that verb-final languages tend to have a tighter relationship between lexemes and syntactic roles, which helps language users to recognize thematic roles early during comprehension. 1 Theoretical background and aims of the paper This paper proposes a quantitative bottom-up corpus-based approach to cross-linguistic comparison, determining how tightly or loosely different lexemes can be mapped on basic syntactic roles. The idea goes back to Hawkins (1986: 121– 127, 1995; see also Müller-Gotama 1994), who coined the terms ‘tight-fit’ and ‘loose-fit’ languages. The former have unique surface forms that map onto more constrained meanings, whereas the latter have more vague forms with less constrained meanings. For instance, Present-Day English has fewer semantic restrictions on the subject and object than Old English, German or Russian. Consider several examples below. (1) a. Locative: This tent sleeps four. b. Temporal: 2020 witnessed a spread of the highly infectious coronavirus disease. c. Instrument: 10 Euros will buy you a meal. d. Source: The roof leaks water. While these sentences are perfectly acceptable in English, their German or Russian equivalents would be unacceptable or strange. This means that subjects in English are less semantically restricted than subjects in German and Russian (see also Plank 1984). Tightness and looseness have several components. Semantic flexibility of arguments is only one of them. Other features of tight languages include formal case marking, avoidance of raisings and long WH-movements and lower reliance on context in interpretation. Languages can change their degree of tightness. English is a well-known example of shifting from tight to loose (Hawkins 1986). As the case was lost, the zero-marked NPs in Middle English became more dependent on the verb for theta-role assignment. This i","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"72 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":"127674566","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}

{"title":"Clause-Level Tense, Mood, Voice and Modality Tagging for German","authors":"Tillmann Dönicke","doi":"10.18653/v1/2020.tlt-1.1","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.1","url":null,"abstract":"We present a language-independent clausizer (clause splitter) based on Universal Dependencies (Nivre et al., 2016), and a clause-level tagger for grammatical tense, mood, voice and modality in German. The paper recapitulates verbal inflection in German—always juxtaposed with its close relative English—and transforms the linguistic theory into a rule-based algorithm. We achieve state-of-the-art accuracies of 92.6% for tense, 79.0% for mood, 93.8% for voice and 79.8% for modality in the literary domain. Our implementation is available at https://gitlab.gwdg. de/tillmann.doenicke/tense-tagger.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"37 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":"128817033","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}

{"title":"Automatic Extraction of Tree-Wrapping Grammars for Multiple Languages","authors":"Tatiana Bladier, Laura Kallmeyer, Rainer Osswald, J. Waszczuk","doi":"10.18653/v1/2020.tlt-1.5","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.5","url":null,"abstract":"We present an algorithm for extracting Tree-Wrapping Grammars (TWGs) for multiple languages from constituency treebanks. The TWG formalism, which is inspired by Tree Adjoining Grammar (TAG), has been developed for the formalization of Role and Reference Grammar (RRG). We describe the extraction of TWGs for English, German, French and Russian from the multilingual RRG corpus RRGparbank. A special focus is given to how non-local dependencies are treated by the extraction algorithm. In TWGs, non-local dependencies are considered as arising from local dependencies in elementary trees by the operation of ‘wrapping substitution’. The extracted grammars are validated by using them in a subsequent parsing step. 1 Background: Tree-Wrapping Grammars The Tree Wrapping Grammar (TWG) formalism (Kallmeyer et al., 2013; Kallmeyer, 2016; Osswald and Kallmeyer, 2018) is a tree-rewriting formalism much in the spirit of Tree Adjoining Grammar (TAG) (Joshi and Schabes, 1997) that has been developed for the formalization of Role and Reference Grammar (RRG) (Van Valin, 2005; Van Valin, 2010), a theory of grammar with a strong emphasis on typological concerns. A TWG consists of a finite set of elementary trees which can be combined by the following three operations: a) (simple) substitution (replacing a leaf by a new tree), b) sister adjunction (adding a new tree as a subtree to an internal node), and c) wrapping substitution (splitting the new tree at a d(ominance)-edge, filling a substitution node with the lower part and adding the upper part to the root of the target tree). As in (lexicalized) TAG, the elementary trees of a TWG are assumed to encode the argument projection of their lexical anchors. Figure 1 shows an application of wrapping substitution for generating the German sentence in (1) (the dashed line indicates a d-edge).1","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"19 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":"132460219","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}

{"title":"Estimating POS Annotation Consistency of Different Treebanks in a Language","authors":"Akshay Aggarwal, Daniel Zeman","doi":"10.18653/v1/2020.tlt-1.9","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.9","url":null,"abstract":"We introduce a new symmetric measure (called θpos) that utilises the non-symmetric KLcpos3 measure (Rosa and Žabokrtský, 2015) to allow us to compare the annotation consistency between different treebanks of a given language, annotated under the same guidelines. We can set a threshold for this new measure so that a pair of treebanks can be considered harmonious in their annotation if θpos does not surpass the threshold. For the calculation of the threshold, we estimate the effects of (i) the size variation, and (ii) the genre variation in the considered pair of treebanks. The estimations are based on data from treebanks of distinct language families, making the threshold less dependent on the properties of individual languages. We demonstrate the utility of the proposed measure by listing the treebanks in Universal Dependencies version 2.5 (UDv2.5) (Zeman et al., 2019) data that are annotated consistently with other treebanks of the same language. However, the measure could be used to assess inter-treebank annotation consistency under other (non-UD) annotation guidelines as well.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"40 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":"132843639","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}

{"title":"Fine-Grained Morpho-Syntactic Analysis for the Under-Resourced Language Chaghatay","authors":"K. Steimel, Akbar Amat, Arienne Dwyer, Sandra Kübler","doi":"10.18653/v1/2020.tlt-1.4","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.4","url":null,"abstract":"We investigate part of speech (POS) tagging for Chaghatay, a historical language with a considerable amount of morphology but few available resources such as POS annotated corpora. In a situation where we have little training data but a large POS tagset, it is not obvious which method will be best to obtain an accurate POS tagger. We experiment with a conditional random field and a Recurrent Neural Network, augmenting the models with coarse grained POS tag information, and by utilizing additional data, either additional unannotated data used to train a language model or annotated data from a modern relative, Uyghur. Our results show that the combination of an RNN and pretraining with coarse grained POS tags reaches the highest accuracy of 76.17%.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"40 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":"114667207","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}

{"title":"Cross-Lingual Domain Adaptation for Dependency Parsing","authors":"Sara Stymne","doi":"10.18653/v1/2020.tlt-1.6","DOIUrl":"https://doi.org/10.18653/v1/2020.tlt-1.6","url":null,"abstract":"We show how we can adapt parsing to low-resource domains by combining treebanks across languages for a parser model with treebank embeddings. We demonstrate how we can take advantage of in-domain treebanks from other languages, and show that this is especially useful when only out-of-domain treebanks are available for the target language. The method is also extended to low-resource languages by using out-of-domain treebanks from related languages. Two parameter-free methods for applying treebank embeddings at test time are proposed, which give competitive results to tuned methods when applied to Twitter data and transcribed speech. This gives us a method for selecting treebanks and training a parser targeted at any combination of domain and language.","PeriodicalId":124685,"journal":{"name":"International Workshop on Treebanks and Linguistic Theories","volume":"126 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":"116692106","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}