Silvie Cinková

SemEval 2015 Task 18: Broad-Coverage Semantic Dependency Parsing

Task 18 at SemEval 2015 defines Broad-Coverage Semantic Dependency Parsing (SDP) as the problem of recovering sentence-internal predicate–argument relationships for all content words, i.e. the sema ...

Towards English-to-Czech MT via Tectogrammatical Layer

Towards English-to-Czech MT via Tectogrammatical Layer We present an overview of an English-to-Czech machine translation system. The system relies on transfer at the tectogrammatical (deep syntactic) layer of the language description. We report on the progress of linguistic annotation of English tectogrammatical layer and also on the first end-to-end evaluation of our syntax-based MT system.

Tectogrammatical Annotation of the Wall Street Journal

Tectogrammatical Annotation of the Wall Street Journal This paper gives an overview of the current state of the Prague English Dependency Treebank project. It is an updated version of a draft text that was released along with a CD presenting the first 25% of the PDT-like version of the Penn Treebank - WSJ section (PEDT 1.0). Before the January 2009 release, the conversion from the original phrase structure trees into dependency trees as well as the consistency checks were substantially enhanced to save manual work. The conversion is partly performed by scripted rules and partly by a statistical parser. To make the rules more powerful, the phrase-based Penn Treebank - WSJ was enriched with other publicly available language resources - the manual annotation of flat noun phrases and the named-entity and coreference tagging. At the moment, 50% of the 1 million corpus have been manually annotated and consistency-checked on the tectogrammatical layer.

PDTSL: An annotated resource for speech reconstruction

We present a description of a new resource (Prague Dependency Treebank of Spoken Language) being created for English and Czech to be used for the task of speech understanding, broad natural language analysis for dialog systems and other speech-related tasks, including speech editing. The resources we have created so far contain audio and a standard transcription of spontaneous speech, but as a novel layer, we add an edited (ldquoreconstructedrdquo) version of the spoken utterances. These edits go beyond the scope of current speech reconstruction efforts in that we allow, on top of the usual deletions of speech artifacts, fillers, etc. also for word modifications, insertions and word order changes. We have used both monologue and dialogue recordings in English and Czech to verify the feasibility of such transcription. We have also assessed the quality of the resulting annotation since the relative freedom of the editing raises an issue of what a ldquocorrectrdquo annotation is.

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2017, the task was devoted to learning dependency parsers for a large number of languages, in a real-world setting without any gold-standard annotation on input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. In this paper, we define the task and evaluation methodology, describe how the data sets were prepared, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems.

WordSim353 for Czech

Human judgments of lexical similarity/relatedness are used as evaluation data for Vector Space Models, helping to judge how the distributional similarity captured by a given Vector Space Model correlates with human intuitions. A well established data set for the evaluation of lexical similarity/relatedness is WordSim353, along with its translations into several other languages. This paper presents its Czech translation and annotation, which is publicly available via the LINDAT-CLARIN repository at hdl.handle.net/11234/1-1713.

SemEval-2015 Task 15: A CPA dictionary-entry-building task

This paper describes the first SemEval task to explore the use of Natural Language Processing systems for building dictionary entries, in the framework of Corpus Pattern Analysis. CPA is a corpus-driven technique which provides tools and resources to identify and represent unambiguously the main semantic patterns in which words are used. Task 15 draws on the Pattern Dictionary of English Verbs (www.pdev.org.uk), for the targeted lexical entries, and on the British National Corpus for the input text. Dictionary entry building is split into three subtasks which all start from the same concordance sample: 1) CPA parsing, where arguments and their syntactic and semantic categories have to be identified, 2) CPA clustering, in which sentences with similar patterns have to be clustered and 3) CPA automatic lexicography where the structure of patterns have to be constructed automatically. Subtask 1 attracted 3 teams, though none could beat the baseline (rule-based system). Subtask 2 attracted 2 teams, one of which beat the baseline (majority-class classifier). Subtask 3 did not attract any participant. The task has produced a major semantic multidataset resource which includes data for 121 verbs and about 17,000 annotated sentences, and which is freely accessible.

Two Languages - One Annotation Scenario? Experience from the Prague Dependency Treebank

Two Languages - One Annotation Scenario? Experience from the Prague Dependency Treebank This paper compares the two FGD-based annotation scenarios for Czech and for English, with the Czech as the basis. We discuss the secondary predication expressed by infinitive and its functions in Czech and English, respectively. We give a few examples of English constructions that do not have direct counterparts in Czech (e.g., tough movement and causative constructions with make, get, and have), as well as some phenomena central in English but much less employed in Czech (object raising or control in adjectives as nominal predicates), and, last, structures more or less parallel both in their function and distribution, whose respective annotation differs due to significant differences in the respective linguistic traditions (verbs of perception).

A Contrastive Lexical Description of Basic Verbs Examples from Swedish and Czech

A Contrastive Lexical Description of Basic Verbs This paper aims at a lexical description of frequent uses of frequent lexical verbs in Swedish on the background of Czech, with some implications for the lexical description of such verb uses verbs in general. It results in a draft of a production lexicon of Swedish frequent verbs for advanced Czech learners of Swedish, with focus on their uses as light verbs. The introductory sections (1 and 2) discuss semantic shifts in highly frequent lexical verbs, whose most literal or ‘primary’ uses express motion, location, or physical control; e.g. stand, put, go, hold. These verbs are called basic verbs, which is a term coined by Viberg (Viberg, 1990) that suggests that they typically denote events belonging to basic level categories described by Lakoff (Lakoff, 1987). The ‘literalness’ of verb uses is judged according to how much they are the ones speakers pick first to illustrate the meaning of that given verb (cognitive salience, a term coined by Hanks in (Hanks, forthcoming). Hanks pointed out an interesting discrepancy between the cognitive salience and the actual frequency of a given verb usage in large corpora. This discrepancy is extremely significant in basic verbs. Some of their uses exhibit such a low cognitive salience, that they are not even noticed by native speakers. This has consequences in second-language acquisition. Foreign learners, even the advanced ones, often lack competence in using the most frequent lexical verbs of the second language in their most frequent patterns. Basic verbs often act as light verbs. Sections 3 to 7 are dedicated to light verbs and light verb constructions. Section 8 discusses the morphosyntactic variability in predicate nouns (i.e. the nominal components of light verb constructions) and their possible semantic impact on the entire light verb construction. Different aspects of polysemy of basic verbs are dealt with by contrasting Swedish examples to Czech in Section 9. Special attention is paid to uses of basic verbs that denote relations between abstract entities. Section 10 focuses on grammaticalizing uses of lexical verbs. It gives a Swedish example of context-induced reinterpretation - an interesting semantic shift that often leads to grammaticalization. All the aspects of basic verbs discussed in Sections 1-10 are integrated in a structure of a Swedish-Czech lexicon, which captures verbs and predicate nouns in two respective interlinked parts. Sections 11-14 give its detailed decription.

Semantic Representation of Non-Sentential Utterances in Dialog

Being confronted with spontaneous speech, our current annotation scheme requires alterations that would reflect the abundant use of non-sentential fragments with clausal meaning tightly connected to their context, which do not systematically occur in written texts. The purpose of this paper is to list the common patterns of non-sentential fragments and their contexts and to find a smooth resolution of their semantic annotation.