Search

In this work we present the Talk of Norway (ToN) data set, a collection of Norwegian Parliament speeches from 1998 to 2016. Every speech is richly annotated with metadata harvested from different sources, and augmented with language type, sentence, token, lemma, part-of-speech, and morphological feature annotations. We also present a pilot study on party classification in the Norwegian Parliament, carried out in the context of a cross-faculty collaboration involving researchers from both Political Science and Computer Science. Our initial experiments demonstrate how the linguistic and institutional annotations in ToN can be used to gather insights on how different aspects of the political process affect classification. [ABSTRACT FROM AUTHOR]

This article explores a combination of deep and shallow approaches to the problem of resolving the scope of speculation and negation within a sentence, specifically in the domain of biomedical research literature. The first part of the article focuses on speculation. After first showing how speculation cues can be accurately identified using a very simple classifier informed only by local lexical context, we go on to explore two different syntactic approaches to resolving the in-sentence scopes of these cues. While one uses manually crafted rules operating over dependency structures, the other automatically learns a discriminative ranking function over nodes in constituent trees. We provide an in-depth error analysis and discussion of various linguistic properties characterizing the problem, and show that although both approaches perform well in isolation, even better results can be obtained by combining them, yielding the best published results to date on the CoNLL-2010 Shared Task data. The last part of the article describes how our speculation system is ported to also resolve the scope of negation. With only modest modifications to the initial design, the system obtains state-of-the-art results also on this task. [ABSTRACT FROM AUTHOR]

Background: This paper presents a novel approach to the problem of hedge detection, which involves identifying so-called hedge cues for labeling sentences as certain or uncertain. This is the classification problem for Task 1 of the CoNLL-2010 Shared Task, which focuses on hedging in the biomedical domain. We here propose to view hedge detection as a simple disambiguation problem, restricted to words that have previously been observed as hedge cues. As the feature space for the classifier is still very large, we also perform experiments with dimensionality reduction using the method of random indexing. Results: The SVM-based classifiers developed in this paper achieves the best published results so far for sentence-level uncertainty prediction on the CoNLL-2010 Shared Task test data. We also show that the technique of random indexing can be successfully applied for reducing the dimensionality of the original feature space by several orders of magnitude, without sacrificing classifier performance. Conclusions: This paper introduces a simplified approach to detecting speculation or uncertainty in text, focusing on the biomedical domain. Evaluated at the sentence-level, our SVM-based classifiers achieve the best published results so far. We also show that the feature space can be aggressively compressed using random indexing while still maintaining comparable classifier performance. [ABSTRACT FROM AUTHOR]