Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)

Marie-Catherine de Marneffe, Teresa Lynn, Sebastian Schuster (Editors)

Anthology ID:
Brussels, Belgium
Association for Computational Linguistics
Bib Export formats:

pdf bib
Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
Marie-Catherine de Marneffe | Teresa Lynn | Sebastian Schuster

pdf bib
Assessing the Impact of Incremental Error Detection and Correction. A Case Study on the Italian Universal Dependency Treebank
Chiara Alzetta | Felice Dell’Orletta | Simonetta Montemagni | Maria Simi | Giulia Venturi

Detection and correction of errors and inconsistencies in “gold treebanks” are becoming more and more central topics of corpus annotation. The paper illustrates a new incremental method for enhancing treebanks, with particular emphasis on the extension of error patterns across different textual genres and registers. Impact and role of corrections have been assessed in a dependency parsing experiment carried out with four different parsers, whose results are promising. For both evaluation datasets, the performance of parsers increases, in terms of the standard LAS and UAS measures and of a more focused measure taking into account only relations involved in error patterns, and at the level of individual dependencies.

pdf bib
Using Universal Dependencies in cross-linguistic complexity research
Aleksandrs Berdicevskis | Çağrı Çöltekin | Katharina Ehret | Kilu von Prince | Daniel Ross | Bill Thompson | Chunxiao Yan | Vera Demberg | Gary Lupyan | Taraka Rama | Christian Bentz

We evaluate corpus-based measures of linguistic complexity obtained using Universal Dependencies (UD) treebanks. We propose a method of estimating robustness of the complexity values obtained using a given measure and a given treebank. The results indicate that measures of syntactic complexity might be on average less robust than those of morphological complexity. We also estimate the validity of complexity measures by comparing the results for very similar languages and checking for unexpected differences. We show that some of those differences that arise can be diminished by using parallel treebanks and, more importantly from the practical point of view, by harmonizing the language-specific solutions in the UD annotation.

Expletives in Universal Dependency Treebanks
Gosse Bouma | Jan Hajic | Dag Haug | Joakim Nivre | Per Erik Solberg | Lilja Øvrelid

Although treebanks annotated according to the guidelines of Universal Dependencies (UD) now exist for many languages, the goal of annotating the same phenomena in a cross-linguistically consistent fashion is not always met. In this paper, we investigate one phenomenon where we believe such consistency is lacking, namely expletive elements. Such elements occupy a position that is structurally associated with a core argument (or sometimes an oblique dependent), yet are non-referential and semantically void. Many UD treebanks identify at least some elements as expletive, but the range of phenomena differs between treebanks, even for closely related languages, and sometimes even for different treebanks for the same language. In this paper, we present criteria for identifying expletives that are applicable across languages and compatible with the goals of UD, give an overview of expletives as found in current UD treebanks, and present recommendations for the annotation of expletives so that more consistent annotation can be achieved in future releases.

Challenges in Converting the Index Thomisticus Treebank into Universal Dependencies
Flavio Massimiliano Cecchini | Marco Passarotti | Paola Marongiu | Daniel Zeman

This paper describes the changes applied to the original process used to convert the Index Thomisticus Treebank, a corpus including texts in Medieval Latin by Thomas Aquinas, into the annotation style of Universal Dependencies. The changes are made both to harmonise the Universal Dependencies version of the Index Thomisticus Treebank with the two other available Latin treebanks and to fix errors and inconsistencies resulting from the original process. The paper details the treatment of different issues in PoS tagging, lemmatisation and assignment of dependency relations. Finally, it assesses the quality of the new conversion process by providing an evaluation against a gold standard.

Er ... well, it matters, right? On the role of data representations in spoken language dependency parsing
Kaja Dobrovoljc | Matej Martinc

Despite the significant improvement of data-driven dependency parsing systems in recent years, they still achieve a considerably lower performance in parsing spoken language data in comparison to written data. On the example of Spoken Slovenian Treebank, the first spoken data treebank using the UD annotation scheme, we investigate which speech-specific phenomena undermine parsing performance, through a series of training data and treebank modification experiments using two distinct state-of-the-art parsing systems. Our results show that utterance segmentation is the most prominent cause of low parsing performance, both in parsing raw and pre-segmented transcriptions. In addition to shorter utterances, both parsers perform better on normalized transcriptions including basic markers of prosody and excluding disfluencies, discourse markers and fillers. On the other hand, the effects of written training data addition and speech-specific dependency representations largely depend on the parsing system selected.

Mind the Gap: Data Enrichment in Dependency Parsing of Elliptical Constructions
Kira Droganova | Filip Ginter | Jenna Kanerva | Daniel Zeman

In this paper, we focus on parsing rare and non-trivial constructions, in particular ellipsis. We report on several experiments in enrichment of training data for this specific construction, evaluated on five languages: Czech, English, Finnish, Russian and Slovak. These data enrichment methods draw upon self-training and tri-training, combined with a stratified sampling method mimicking the structural complexity of the original treebank. In addition, using these same methods, we also demonstrate small improvements over the CoNLL-17 parsing shared task winning system for four of the five languages, not only restricted to the elliptical constructions.

Integration complexity and the order of cosisters
William Dyer

The cost of integrating dependent constituents to their heads is thought to involve the distance between dependent and head and the complexity of the integration (Gibson, 1998). The former has been convincingly addressed by Dependency Distance Minimization (DDM) (cf. Liu et al., 2017). The current study addresses the latter by proposing a novel theory of integration complexity derived from the entropy of the probability distribution of a dependent’s heads. An analysis of Universal Dependency corpora provides empirical evidence regarding the preferred order of isomorphic cosisters—sister constituents of the same syntactic form on the same side of their head—such as the adjectives in pretty blue fish. Integration complexity, alongside DDM, allows for a general theory of constituent order based on integration cost.

SUD or Surface-Syntactic Universal Dependencies: An annotation scheme near-isomorphic to UD
Kim Gerdes | Bruno Guillaume | Sylvain Kahane | Guy Perrier

This article proposes a surface-syntactic annotation scheme called SUD that is near-isomorphic to the Universal Dependencies (UD) annotation scheme while following distributional criteria for defining the dependency tree structure and the naming of the syntactic functions. Rule-based graph transformation grammars allow for a bi-directional transformation of UD into SUD. The back-and-forth transformation can serve as an error-mining tool to assure the intra-language and inter-language coherence of the UD treebanks.

Coordinate Structures in Universal Dependencies for Head-final Languages
Hiroshi Kanayama | Na-Rae Han | Masayuki Asahara | Jena D. Hwang | Yusuke Miyao | Jinho D. Choi | Yuji Matsumoto

This paper discusses the representation of coordinate structures in the Universal Dependencies framework for two head-final languages, Japanese and Korean. UD applies a strict principle that makes the head of coordination the left-most conjunct. However, the guideline may produce syntactic trees which are difficult to accept in head-final languages. This paper describes the status in the current Japanese and Korean corpora and proposes alternative designs suitable for these languages.

Investigating NP-Chunking with Universal Dependencies for English
Ophélie Lacroix

Chunking is a pre-processing task generally dedicated to improving constituency parsing. In this paper, we want to show that universal dependency (UD) parsing can also leverage the information provided by the task of chunking even though annotated chunks are not provided with universal dependency trees. In particular, we introduce the possibility of deducing noun-phrase (NP) chunks from universal dependencies, focusing on English as a first example. We then demonstrate how the task of NP-chunking can benefit PoS-tagging in a multi-task learning setting – comparing two different strategies – and how it can be used as a feature for dependency parsing in order to learn enriched models.

Marrying Universal Dependencies and Universal Morphology
Arya D. McCarthy | Miikka Silfverberg | Ryan Cotterell | Mans Hulden | David Yarowsky

The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language. Each project also provides corpora of annotated text in many languages—UD at the token level and UniMorph at the type level. As each corpus is built by different annotators, language-specific decisions hinder the goal of universal schemata. With compatibility of tags, each project’s annotations could be used to validate the other’s. Additionally, the availability of both type- and token-level resources would be a boon to tasks such as parsing and homograph disambiguation. To ease this interoperability, we present a deterministic mapping from Universal Dependencies v2 features into the UniMorph schema. We validate our approach by lookup in the UniMorph corpora and find a macro-average of 64.13% recall. We also note incompatibilities due to paucity of data on either side. Finally, we present a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects.

Enhancing Universal Dependency Treebanks: A Case Study
Joakim Nivre | Paola Marongiu | Filip Ginter | Jenna Kanerva | Simonetta Montemagni | Sebastian Schuster | Maria Simi

We evaluate two cross-lingual techniques for adding enhanced dependencies to existing treebanks in Universal Dependencies. We apply a rule-based system developed for English and a data-driven system trained on Finnish to Swedish and Italian. We find that both systems are accurate enough to bootstrap enhanced dependencies in existing UD treebanks. In the case of Italian, results are even on par with those of a prototype language-specific system.

Enhancing Universal Dependencies for Korean
Youngbin Noh | Jiyoon Han | Tae Hwan Oh | Hansaem Kim

In this paper, for the purpose of enhancing Universal Dependencies for the Korean language, we propose a modified method for mapping Korean Part-of-Speech(POS) tagset in relation to Universal Part-of-Speech (UPOS) tagset in order to enhance the Universal Dependencies for the Korean Language. Previous studies suggest that UPOS reflects several issues that influence dependency annotation by using the POS of Korean predicates, particularly the distinctiveness in using verb, adjective, and copula.

UD-Japanese BCCWJ: Universal Dependencies Annotation for the Balanced Corpus of Contemporary Written Japanese
Mai Omura | Masayuki Asahara

In this paper, we describe a corpus UD Japanese-BCCWJ that was created by converting the Balanced Corpus of Contemporary Written Japanese (BCCWJ), a Japanese language corpus, to adhere to the UD annotation schema. The BCCWJ already assigns dependency information at the level of the bunsetsu (a Japanese syntactic unit comparable to the phrase). We developed a program to convert the BCCWJ to UD based on this dependency structure, and this corpus is the result of completely automatic conversion using the program. UD Japanese-BCCWJ is the largest-scale UD Japanese corpus and the second-largest of all UD corpora, including 1,980 documents, 57,109 sentences, and 1,273k words across six distinct domains.

The First Komi-Zyrian Universal Dependencies Treebanks
Niko Partanen | Rogier Blokland | KyungTae Lim | Thierry Poibeau | Michael Rießler

Two Komi-Zyrian treebanks were included in the Universal Dependencies 2.2 release. This article contextualizes the treebanks, discusses the process through which they were created, and outlines the future plans and timeline for the next improvements. Special attention is paid to the possibilities of using UD in the documentation and description of endangered languages.

The Hebrew Universal Dependency Treebank: Past Present and Future
Shoval Sade | Amit Seker | Reut Tsarfaty

The Hebrew treebank (HTB), consisting of 6221 morpho-syntactically annotated newspaper sentences, has been the only resource for training and validating statistical parsers and taggers for Hebrew, for almost two decades now. During these decades, the HTB has gone through a trajectory of automatic and semi-automatic conversions, until arriving at its UDv2 form. In this work we manually validate the UDv2 version of the HTB, and, according to our findings, we apply scheme changes that bring the UD HTB to the same theoretical grounds as the rest of UD. Our experimental parsing results with UDv2New confirm that improving the coherence and internal consistency of the UD HTB indeed leads to improved parsing performance. At the same time, our analysis demonstrates that there is more to be done at the point of intersection of UD with other linguistic processing layers, in particular, at the points where UD interfaces external morphological and lexical resources.

Multi-source synthetic treebank creation for improved cross-lingual dependency parsing
Francis Tyers | Mariya Sheyanova | Aleksandra Martynova | Pavel Stepachev | Konstantin Vinogorodskiy

This paper describes a method of creating synthetic treebanks for cross-lingual dependency parsing using a combination of machine translation (including pivot translation), annotation projection and the spanning tree algorithm. Sentences are first automatically translated from a lesser-resourced language to a number of related highly-resourced languages, parsed and then the annotations are projected back to the lesser-resourced language, leading to multiple trees for each sentence from the lesser-resourced language. The final treebank is created by merging the possible trees into a graph and running the spanning tree algorithm to vote for the best tree for each sentence. We present experiments aimed at parsing Faroese using a combination of Danish, Swedish and Norwegian. In a similar experimental setup to the CoNLL 2018 shared task on dependency parsing we report state-of-the-art results on dependency parsing for Faroese using an off-the-shelf parser.

Toward Universal Dependencies for Shipibo-Konibo
Alonso Vasquez | Renzo Ego Aguirre | Candy Angulo | John Miller | Claudia Villanueva | Željko Agić | Roberto Zariquiey | Arturo Oncevay

We present an initial version of the Universal Dependencies (UD) treebank for Shipibo-Konibo, the first South American, Amazonian, Panoan and Peruvian language with a resource built under UD. We describe the linguistic aspects of how the tagset was defined and the treebank was annotated; in addition we present our specific treatment of linguistic units called clitics. Although the treebank is still under development, it allowed us to perform a typological comparison against Spanish, the predominant language in Peru, and dependency syntax parsing experiments in both monolingual and cross-lingual approaches.

Transition-based Parsing with Lighter Feed-Forward Networks
David Vilares | Carlos Gómez-Rodríguez

We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.

Extended and Enhanced Polish Dependency Bank in Universal Dependencies Format
Alina Wróblewska

The paper presents the largest Polish Dependency Bank in Universal Dependencies format – PDBUD – with 22K trees and 352K tokens. PDBUD builds on its previous version, i.e. the Polish UD treebank (PL-SZ), and contains all 8K PL-SZ trees. The PL-SZ trees are checked and possibly corrected in the current edition of PDBUD. Further 14K trees are automatically converted from a new version of Polish Dependency Bank. The PDBUD trees are expanded with the enhanced edges encoding the shared dependents and the shared governors of the coordinated conjuncts and with the semantic roles of some dependents. The conducted evaluation experiments show that PDBUD is large enough for training a high-quality graph-based dependency parser for Polish.

Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning
Xiang Yu | Ngoc Thang Vu | Jonas Kuhn

We present a general approach with reinforcement learning (RL) to approximate dynamic oracles for transition systems where exact dynamic oracles are difficult to derive. We treat oracle parsing as a reinforcement learning problem, design the reward function inspired by the classical dynamic oracle, and use Deep Q-Learning (DQN) techniques to train the oracle with gold trees as features. The combination of a priori knowledge and data-driven methods enables an efficient dynamic oracle, which improves the parser performance over static oracles in several transition systems.

The Coptic Universal Dependency Treebank
Amir Zeldes | Mitchell Abrams

This paper presents the Coptic Universal Dependency Treebank, the first dependency treebank within the Egyptian subfamily of the Afro-Asiatic languages. We discuss the composition of the corpus, challenges in adapting the UD annotation scheme to existing conventions for annotating Coptic, and evaluate inter-annotator agreement on UD annotation for the language. Some specific constructions are taken as a starting point for discussing several more general UD annotation guidelines, in particular for appositions, ambiguous passivization, incorporation and object-doubling.