Czech Verbs of Communication and the Extraction of Their Frames
نویسندگان
چکیده
We aim at a procedure of automatic generation of valency frames for verbs not covered in VALLEX, a lexicon of Czech verbs. We exploit the classification of verbs into syntactico-semantic classes. This article describes our first step to automatically identify verbs of communication and to assign the prototypical frame to them. The method of identification is evaluated against two versions of VALLEX and FrameNet 1.2. For the purpose of frame generation, a new metric based on the notion of frame edit distance is outlined.
منابع مشابه
Semantic Classes in Czech Valency Lexicon: Verbs of Communication and Verbs of Exchange
We introduce a project aimed at enhancing a valency lexicon of Czech verbs with coherent semantic classes. For this purpose, we make use of FrameNet, a semantically oriented lexical resource. At the present stage, semantic frames from FrameNet have been mapped to two groups of verbs with divergent semantic and morphosyntactic properties, verbs of communication and verbs of exchange. The feasibi...
متن کاملSemantic Roles in Valency Lexicon of Czech Verbs: Verbs of Communication and Exchange
We introduce a project to enhance a valency lexicon of Czech verbs with semantic roles. For this purpose, we make use of FrameNet. At the present stage, frame elements from FrameNet have been mapped to valency complementations of verbs of communication and verbs of exchange. The feasibility of this task has been proven by the achieved inter-annotator agreement – 95.6% for the verbs of communica...
متن کاملVerb Valency Frames in Czech Legal Texts
This paper deals with valency frames for selected group of Czech verbs belonging to the domain of law. Starting with the lexical database VerbaLex we propose semantic roles for these verbs and formulate their Complex Valency Frames. The lexical database VerbaLex has been developed recently at the NLP Centre FI MU and contains approximately 10 500 Czech verbs. We integrate the proposed ’law’ val...
متن کاملComparing Czech and Russian valency on the material of VALLEX
In this study we have compared Czech and Russian valency frames based on monolingual and bilingual data. We assume that Czech and Russian are close enough to have, for the majority of their verbs, similar valency structures . We have exploited Vallex as a source of valency frames and have used a Czech-Russian dictionary to automatically translate Czech verbs into Russian. Afterwards, we have ma...
متن کاملAutomatic Extraction of Subcategorization Frames for Czech
We present some novel machine learning techniques for the identification of subcategorization information for verbs in Czech. We compare three different statistical techniques applied to this problem. We show how the learning algorithm can be used to discover previously unknown subcategorization frames from the Czech Prague Dependency Treebank. The algorithm can then be used to label dependents...
متن کامل