H2020Индивидуална стипендия2016–2017

ARGUE_WEB · Probabilistic Argumentation on the Web

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2016-03-01 → 2017-12-31
Финансиране от ЕС: 168 167 €
Участници: 1
Схема: MSCA-IF-EF-CAR

Линиите свързват координатора с партньорите.

Накратко на български

Алгоритми за дълбоко обучение се тестват, за да разпознават автоматично аргументи в онлайн дискусии, като например в блогове. Това помага за по-доброто извличане и представяне на убеждаващи текстове в компютърни системи за логическо разсъждение.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Probabilistic Argumentation on the Web

A review of the current literature in the extraction of arguments and their components revealed that there were no existing tools that enabled the extraction of arguments and their components. Recent research in the classification of argumentative text using traditional machine learning algorithms focused on the recognition of arguing subjectivity (please see below a brief review of research) and showed that it is possible to identify subjectivity in arguing text found in online debates (blog posts and editorials). The methods employed in these cases, were similar to sentiment recognition in text. Although research on the subjectivity of arguing is a significant progress in the recognition of arguments, its is still not possible to extract, represent and use natural language arguments in KRR systems for reasoning. In order to overcome the above obstacle, the Researcher was asked to investigate Neural Network Deep Learning algorithms for the extraction of data. The lack of sufficiently large annotated data was a major problem in the experimental evaluation of different neural network architectures. The Researcher tried to overcome the problem by using NLP tools. Although NLP tools are widely used in the traditional machine learning tasks, their accuracy is very low when used for the extraction of types of text. The main goal of this project as can be defined as: to investigate algorithms and tools capable of identifying argumentation text on line textual resources. The term 'argumentation text' in this context refers to text intended to persuade the participants in a debate.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

The (World Wide) Web hosts a wide range of argumentative text from resources of multiple disciplines and online debates. Also, tools (such as Debadepedia and Twitter) encourage the communication of arguments in social and scientific settings. With the exponential growth of the Web and its users, a vast amount of argumentative text on the Web remains hidden. In order to query the Web for structured arguments included in web pages, it is necessary to address both of the following issues: (1) the deployment of technologies that enable an automatic extraction of the components of natural language arguments and the representation of their meaning and (2) the deployment of a pragmatic argumentation formalism that takes into account the uncertain and inconsistent nature of data on the Web to reason with structured arguments. State-of-the-art research in natural language processing (NLP) recently engaged in the deployment of technologies for learning the semantic similarity between statements and for the extraction of probabilistic beliefs and logic expressions from natural language text. This is a promising direction forward, toward the automatic extraction of the components of argumentative text online. Additionally, research on probabilistic formalisms supporting argumentation reasoning is at the heart of state-of-the-art research in knowledge representation and reasoning (KRR). The goal of the “ARGUE_WEB” project is to develop a scalable probabilistic argumentation system for the retrieval, for the principled management of points of view derived from argumentative text on web pages, and for query answering from such points of view. One of the central aspects of this scalable approach is the representation of structured arguments using an ontology language and the development of a formalism which is tolerant to uncertainty and inconsistency.

Оригинален текст от CORDIS (на английски).

Участници

THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD · OxfordКоординаторОбединеното кралство