Search
Now showing items 1-5 of 5
(Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment ...
(Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
This paper documents the creation of a large-scale dataset of evaluative sentences – i.e. both subjective and objective sentences that are found to be sentiment-bearing – based on mixed-domain professional reviews from ...
(Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
Neural methods for sentiment analysis have led to quantitative improvements over previous approaches, but these advances are not always accompanied with a thorough analysis of the qualitative differences. Therefore, it is ...
(Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades. This is done in order to test the hypothesis that evaluative adjectives are more prone to temporal ...
(Chapter / Bokkapittel / PublishedVersion; Peer reviewed, 2019)
We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists. The task is cast as a relation discovery problem and applied to historical armed conflicts ...