Lexical Features of Scientific Discourse

Relevance Prediction in Information Extraction using Discourse and Lexical Features

We present on-going work on estimating the relevance of the results of an Information Extraction (IE) system. Our aim is to build a user-oriented measure of utility of the extracted factual information. We describe experiments using discourse-level features, with classifiers that learn from users’ ratings of relevance of the results. Traditional criteria for evaluating the performance of IE foc...

Improved Information Structure Analysis of Scientific Documents Through Discourse and Lexical Constraints

Inferring the information structure of scientific documents is useful for many downstream applications. Existing feature-based machine learning approaches to this task require substantial training data and suffer from limited performance. Our idea is to guide feature-based models with declarative domain knowledge encoded as posterior distribution constraints. We explore a rich set of discourse ...

Modeling Scientific Discourse

We aim to build intelligent systems which can reason autonomously about the risk of carcinogenicity of chemicals, drawing on whatever theoretical or experimental evidence is available. In earlier work [14], reviewing the literature on methods of carcinogen risk assessment, we catalogued the different types of evidence adduced to support these claims, which may be in the form of: experimental re...

Language Features of Russian Texts of Engineering Discourse

The Article is devoted to the applied problem of identifying the linguistic features of engineering texts. The study of Russian-language texts of engineering discourse is usually of an applied nature, in our case, this applied research is caused by the need to teach foreigners who receive professional engineering education in Russia and in Russian language. The object of the research is the Rus...

Lexical cohesion and the organization of discourse