This chapter focuses on computational approaches to the automatic extraction of terms from domain specific corpora. The different subtasks of Automatic Term Extraction are presented in detail, including corpus compilation, unithood, termhood and variant detection, and system evaluation.
We describe a system for the CWI-task that includes information on 5 aspects of the (complex) lexical item, namely distributional information of the item itself, morphological structure, psychological measures, corpus-counts and topical information. We constructed a deep learning architecture that combines those features and apply it to the probabilistic and binary classification task for all English sets and Spanish. We achieved reasonable performance on all sets with best performances seen on the probabilistic task, particularly on the English news set (MAE 0.054 and F1-score of 0.872). An analysis of the results shows that reasonable performance can be achieved with a single architecture without any domainspecific tweaking of the parameter settings and that distributional features capture almost all of the information also found in hand-crafted features.
Abstract. This paper reports on the potential of Oral Elicited Imitation (OEI) as a format for output practice, building on an analysis of picture-matching and spoken data collected from 36 university-level learners of German as a second language (L2) in a web-based assessment task inspired by Input Processing (VanPatten, 2004). The design and development of OEI for output practice faces two key challenges: learners must be engaged in meaningful language processing rather than in mere repetition of oral stimuli, and the task must eventually provide individualized and qualitative corrective feedback that helps learners to notice gaps between their interlanguage and the target language. Results show that learners attended to meaning and that a commercially available speech recognition tool was able to transcribe learner speech remarkably well.
This chapter focuses on computational approaches to the automatic extraction of terms from domain specific corpora. The different subtasks of Automatic Term Extraction are presented in detail, including corpus compilation, unithood, termhood and variant detection, and system evaluation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.