Section: New Results

French FrameNet

Participants : Marie-Hélène Candito, Marianne Djemaa.

In 2016 we have continued the development of a French FrameNet, within the ASFALDA project. While the first phase of the project focused on the development of a French set of frames and corresponding lexicon (Candito et al., 2014), we have focused this year on the subsequent corpus annotation phase, which targeted four notional domains (commercial transactions, cognitive stances, causality and verbal communication). Given full coverage is not reachable for a relatively “new” FrameNet project such as ours, focusing on specific notional domains allowed us to obtain full lexical coverage for the frames of these domains, while partially reflecting word sense ambiguities. Furthermore, as frames and roles were annotated on two main French Treebanks (the French Treebank and the Sequoia Treebank), we were able to extract a syntactico-semantic lexicon from the annotated frames. In the resource's current status [28], there are 98 frames, 662 frame-evoking words or “triggers”, 872 senses, and about 13,000 annotated frames, with their semantic roles assigned to portions of text (The French FrameNet is freely available at http://asfalda.linguist.univ-paris-diderot.fr/frameIndex.xml.)

During this year's resource development efforts, we have put a specific emphasis on the causality domain (about 4000 instances of causal lexical items with their corresponding semantic frames are included in our resource). In the process of building the French lexicon and preparing the annotation of the corpus, we had to remodel some of the frames proposed in FrameNet based on English data, with hopefully more precise frame definitions to facilitate human annotation. This includes semantic clarifications of frames and frame elements, redundancy elimination, and added coverage. The result is arguably a significant improvement of the treatment of causality in FrameNet itself [34].