Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts
نویسندگان
چکیده
منابع مشابه
Graph-Based Approach to Recognizing CST Relations in Polish Texts
This paper presents a supervised approach to the recognition of Cross-document Structure Theory (CST) relations in Polish texts. In the proposed, graph-based representation is constructed for sentences. Graphs are built on the basis of lexicalised syntactic-semantic relations extracted from text. Similarity between sentences is calculated on their graphs, and the values are used as features to ...
متن کاملAutomatic Term Recognition in Polish Texts
Although ATR has been in the research focus for over a decade now, most approaches have been developed for highly positional languages, whereas only a few efforts have been made for Slavic languages which have a richer morphological inflection and a more relaxed word order, e.g., Vintar (2004) (for Slovene) and Nenadic et al. (2003) (for Serbian). In this paper, we report on our experiments in ...
متن کاملPresupposition Role in the Compound-Complex Sentence
The article analyzes the role of presupposition in the compound-complex sentence. The authors examine the types of presuppositions and minimal compound-complex sentence as a field of presuppositions action. The analysis of these types of sentences by the material of the English language shows that several kinds of presuppositions are realized in them – contact or distant, - developing in the re...
متن کاملRecognition of Named Entities Boundaries in Polish Texts
In the paper we discuss the problem of low recall for the named entity (NE) recognition task for Polish. We discuss to what extent the recall of NE recognition can be improved by reducing the space of NE categories. We also present several extensions to the binary model which give an improvement of the recall. The extensions include: new features, application of external knowledge and post-proc...
متن کاملConstruction of Conceptual Graph Representation of Texts
This paper describes a system for constructing conceptual graph representation of text by using a combination of existing linguistic resources (VerbNet and WordNet). We use a twostep approach, by firstly identifying the semantic roles in a sentence, and then using these roles, together with semi-automatically compiled domain-specific knowledge to construct the conceptual graph representation.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cybernetics and Information Technologies
سال: 2018
ISSN: 1314-4081
DOI: 10.2478/cait-2018-0013