- 论文摘要 （6000字符，含标点）
Target languages of the conference - Russian\English\Chineese
Thesis must be only in Russian or English
One author may submit no more than two abstracts, of which no more than one can be written individually.
NB: we have double-blind peer review
Your thesis must contain:
- Abstract in English (150-250 words)
- Keywords in English (4-8 words)
- Main text must not exceed 6 000 character (including whitespaces) in length
- 格式：.doc, .docx, .rtf 格式
- 正文中的参考文献用[ ]标记，例如[Garbovsky，2007，p5]
- Text files must be in the DOC, DOCX or RTF format.
- page orientation: portrait
- if you use unusual fonts, send them in addition to your thesis
- do not use page numbering or automatic hyphenation
- examples in Chinese must be followed by reading, glosses and translation
- bibliographic references in text - in the Arabian figures in square brackets (ex. [Garbovsky 2007, p. 5])
- footnotes must be numbered and placed at the bottom of the page
- other settings such as font size, interval, intent, colour etc. does not matter
- 使用第三人称参考作者之前发表的作品。 例如，写“Black and Hart（2015）已经证明”而不是“我们/作者之前已经证明过[Black＆Hart，2015]”。
- 谨慎选择文件名，并确保文件的“属性”也是匿名的。如果您使用的是Microsoft Office 2007或更高版本，请在提交之前考虑使用文档检查器工具
DOUBLE-BLIND REVIEW GUIDLINES
- Do not use any identifying information, such as authors' names or affiliations, from your manuscript before submission.
- Use the third person to refer to work the authors have previously published. For example, write “Black and Hart (2015) have demonstrated” rather than “we/the authors have previously demonstrated (Black & Hart, 2015)”.
- Make sure that figures and tables do not contain any reference to author affiliations
- Exclude acknowledgements and any references to funding sources.
- Choose file names with care, and ensure that the file’s “properties” are also anonymised. If you are using Microsoft Office 2007 or later, consider using the Document Inspector Tool prior to submission.
- Take care to ensure that you do not inadvertently upload identifying information within any of the files that will be shared with reviewers.
SYNTAX PARSING FOR TEXTS WITH MISSPELLINGS IN DICTASCOPE SYNTAX
The paper deals with syntax parsing of natural language texts with misspellings and misprints in DictaScope Syntax. We propose a method for integration of a spellchecker and parser, which allows us on the one hand to correct typographical errors considering the context and on the other hand to increase the robustness of the parser. To correct the misspellings and misprints we propose to use a modified Levenshtein algorithm, in which each pair of characters involved in calculation of the Levenshtein distance is assigned a specific weight from the interval. The paper states the need to take into account the Syntax parsing for texts with misspellings in dictascope syntax lexical context of the words to be corrected in order to achieve the maximum accuracy of correction, which helps correct words used in an unusual context. The final choice is made by the DictaScope parser Basing on the modified Eisner algorithm, the parser builds a dependency tree for the sentence. In our model several vertices of interpretations correspond to one word, and variants of spellcorrection could be processed in the same way as morphological interpretations. The proposed method of integration of the parser and the spellchecker modules was implemented in the DictaScope Syntax system. This made it possible to considerably increase the stability of the parser and provided an opportunity to use it as a component of the opinion mining system for monitoring of blogs and forums.
Key words: syntax parsing, syntax parser, parsing, misspellings, misprints