User Tools

Site Tools

Agence Nationale de la Recherche

2018-lifat-m2-1

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
2018-lifat-m2-1 [2018/09/21 14:40]
agata.savary
2018-lifat-m2-1 [2018/09/21 14:42]
agata.savary
Line 27: Line 27:
  
 The objectives of this internship are to exploit word embeddings for discovery of new MWEs based on their semantic proximity to the previously seen MWEs, contained in a lexicon or in an annotated corpus (resources of both types belong to the outcomes of the PARSEME-FR project). The discovery should lead to (semi-)automatic enrichment of these initial resources. Two stages are to be considered: The objectives of this internship are to exploit word embeddings for discovery of new MWEs based on their semantic proximity to the previously seen MWEs, contained in a lexicon or in an annotated corpus (resources of both types belong to the outcomes of the PARSEME-FR project). The discovery should lead to (semi-)automatic enrichment of these initial resources. Two stages are to be considered:
-  * (i) candidates for new MWEs are generated by replacing individual components of known MWEs by their semantically close words, established notably via word embeddings; +  * candidates for new MWEs are generated by replacing individual components of known MWEs by their semantically close words, established notably via word embeddings; 
-  * (ii) the candidates generated in this way are filtered based on their corpus frequency or contexts of occurrence; for instance, adjectives //chaud/froid// ‘hot/cold’ tend to co-occur more frequently with //*prendre* un **bain**/une **douche**// ‘to take a bath/shower’ than with //**prendre** une **baignoire**// (spacieuse/solide...) ‘take a (huge/solid) bathtub’.+  * the candidates generated in this way are filtered based on their corpus frequency or contexts of occurrence; for instance, adjectives //chaud/froid// ‘hot/cold’ tend to co-occur more frequently with //*prendre* un **bain**/une **douche**// ‘to take a bath/shower’ than with //**prendre** une **baignoire**// (spacieuse/solide...) ‘take a (huge/solid) bathtub’.
  
 Possible extensions of the objectives: Possible extensions of the objectives:
  
-  * (iii) integrating MWE discovery with MWE identification in //varIDE// +  * integrating MWE discovery with MWE identification in //varIDE// 
-  * (iv)  coupling word embedding-based lexical replacement with semantic resources such as WordNet.+  * coupling word embedding-based lexical replacement with semantic resources such as WordNet.
  
  
2018-lifat-m2-1.txt · Last modified: 2018/09/21 14:42 by agata.savary