Paraphrastic Reformulations in Spoken Corpora

Iris Eshkol-Taravella (1) , Natalia Grabar (2)

1 LLL - Laboratoire Ligérien de Linguistique
2 STL - Savoirs, Textes, Langage (STL) - UMR 8163

Our work addresses the automatic detection of paraphrastic reformulation in French spoken corpora. The proposed approach is syn-tagmatic. It is based on specific markers and the specificities of the spoken language. Manual multi-dimensional annotation performed by two annotators provides fine-grained reference data. An automatic method is proposed in order to decide whether sentences contain or not paraphras-tic relations. The obtained results show up to 66.4% precision. Analysis of the manual annotations indicates that few paraphrastic segments show morphological modifications (inflection, derivation or compounding) and that the syntactic equivalence between the segments is seldom respected, as these usually belong to different syntactic categories.

Mots clés: Reformulation; Paraphrase; Spoken corpora

Domaines: Linguistique; Informatique [cs]

Iris Eshkol-Taravella, Natalia Grabar. Paraphrastic Reformulations in Spoken Corpora. Lecture Notes in Computer Science, 2014, 9th International Conference on NLP, PolTAL2014, 8686, pp.425-437. ⟨10.1007/978-3-319-10888-9_42⟩. ⟨hal-01174657⟩