Семинар "Constructional syntactic analysis for information access tasks", Юсси Карлгрен

2 февраля 2011, 13:24

Сегодня мы открываем регистрацию на следующий семинар, который состоится 16 февраля 2011 года, в московском офисе Яндекса.

В рамках цикла семинаров «Информационный поиск и анализ данных» выступит Юсси Карлгрен из Swedish Institute of Computer Science.

Тема доклада: Constructional syntactic analysis for information access tasks.

О чем: In this talk, I will describe experiments to use non-terminological information to find attitudinal expressions in written English text. The experiments are based on an analysis of text with respect to not only the vocabulary of content terms present in it (which most other approaches use as a basis for analysis) but also with respect to presence of structural features of the text represented by *constructional features* (typically disregarded by most other analyses).

In our analysis, following a construction grammar framework, structural features are treated as occurrences, similarly to the treatment of vocabulary features. The constructional features in play are chosen to potentially signify opinion but are not specific to negative or positive expressions. The constructional framework is used to classify clauses, headlines, and sentences from three different shared collections of attitudinal data. We find that constructional features transfer well across different text collections and that the information couched in them integrates easily with a vocabulary based approach, yielding improvements in classification without complicating the application end of the processing framework.

О докладчике: Jussi Karlgren, Ph D in computational linguistics and adjoint professor of language technology, is a senior researcher at the Swedish Institute of Computer Science in Stockholm, Sweden. He has been a visiting researcher at Xerox PARC in Palo Alto, at New York University and at Yahoo! Research in Barcelona.

Jussi Karlgren studies usage of information and representation of language in digital information access. His interest is in gaining a closer understanding of the linguistic communication process between author and reader; his aim is to improve information access by designing systems based on 1) an informed analysis of usage, context, situation and domain 2) a deeper analysis of the content of the information flow, and 3) a flexible, dynamic, and scalable knowledge representation which captures what is essential for linguistic data. Current application areas he works with are authorship attribution and attitude analysis of text.

Задать вопросы докладчику и обсудить заявленную тему вы можете в Клубе. Трансляцию семинара можно будет посмотреть тут. Докладчик будет читать на английском языке.

Регистрация

Начало мероприятия в 19:00, а подтвердить регистрацию вы можете с 18.30 (лучше подойти к этому времени, чтобы успеть к началу лекции).

Группа по обучению и развитию