AimGiven a set of pre-defined medical categories used in Evidence Based Medicine, we aim to automatically annotate sentences in medical abstracts with these labels.MethodWe constructed a corpus of 1,000 medical abstracts annotated by hand with specified medical categories (e.g. Intervention, Outcome). We explored the use of various features based on lexical, semantic, structural, and sequential information in the data, using Conditional Random Fields (CRF) for classification.ResultsFor the classification tasks over all labels, our systems achieved micro-averaged f-scores of 80.9% and 66.9% over datasets of structured and unstructured abstracts respectively, using sequential features. In labeling only the key sentences, our systems produced f-scores of 89.3% and 74.0% over structured and unstructured abstracts respectively, using the same sequential features. The results over an external dataset were lower (f-scores of 63.1% for all labels, and 83.8% for key sentences).ConclusionsOf the features we used, the best for classifying any given sentence in an abstract were based on unigrams, section headings, and sequential information from preceding sentences. These features resulted in improved performance over a simple bag-of-words approach, and outperformed feature sets used in previous work.

In this paper we explore the results of a large-scale online game called ‘the Great Language Game’, in which people listen to an audio speech sample and make a forced-choice guess about the identity of the language from 2 or more alternatives. The data include 15 million guesses from 400 audio recordings of 78 languages. We investigate which languages are confused for which in the game, and if this correlates with the similarities that linguists identify between languages. This includes shared lexical items, similar sound inventories and established historical relationships. Our findings are, as expected, that players are more likely to confuse two languages that are objectively more similar. We also investigate factors that may affect players’ ability to accurately select the target language, such as how many people speak the language, how often the language is mentioned in written materials and the economic power of the target language community. We see that non-linguistic factors affect players’ ability to accurately identify the target. For example, languages with wider ‘global reach’ are more often identified correctly. This suggests that both linguistic and cultural knowledge influence the perception and recognition of languages and their similarity.

No abstract

No abstract