Assistant

Foreign language learners need to get cultural information during their learning process for their oral and written comprehension and expression activities. Current lexicographic products are not characterized by showing explicit, systematic, and organized cultural data about cultural words or expressions found in their vocabularies. Current lexicographic products are not characterized by showing explicit and/or systematically cultural data about cultural words or expressions found in their vocabularies. Consequently, learners’ communicative and cognitive needsare not satisfied when looking up any cultural word and/or expression. One of the challenges of lexicography is how to select and represent cultural data in various lexicographic products. Overcoming this double challenge will depend on how these lexicographic tools cope with the following actions: (1) personalization of the lexicographic product; (2) integration in other tools (e.g. writing assistants); and (3) development of the product as a learning tool and not only a consultation tool. In view of this issue, this paper discusses about how to select cultural data from different sources and how to represent them in Write Assistant, a tool created by the Danish language technology company Ordbogen and published in 2019, though still in progress. Special attention will be given to Spanish speakers learning the English language.

In this article, we propose a method-ology to automatically construct fuzzy rules in a Fuzzy Rule-Based System that detects emotions from an actor’s performance during a show. The idea is to collect video data from a lot of performances of the same show from which it should be possible to visualize all the emo-tions and intents or more precisely “intent graphs”. To do this, we analyze the collected data defining low-level descriptors that are con-verted into high-level characteriza-tions thanks to aggregations. The following step is to partition cor-rectly the universes in classes, de-pending on the retrieved data. Fi-nally the fuzzy rules built from the classes are used to label the detected emotions.