Study of Entity-Topic Models for OOV Proper Name Retrieval - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Study of Entity-Topic Models for OOV Proper Name Retrieval

Résumé

Retrieving Proper Names (PNs) relevant to an audio document can improve speech recognition and content based audio-video indexing. Latent Dirichlet Allocation (LDA) topic model has been used to retrieve Out-Of-Vocabulary (OOV) PNs relevant to an audio document with good recall rates. However, retrieval of OOV PNs using LDA is affected by two issues, which we study in this paper: (1)Word Frequency Bias (less frequent OOV PNs are ranked lower); (2) Loss of Specificity (the reduced topic space representation loses lexical context). Entity-Topic models have been proposed as extensions of LDA to specifically learn relations between words, entities (PNs) and topics. We study OOV PN retrieval with Entity-Topic models and show that they are also affected by word frequency bias and loss of specificity. We evaluate our proposed methods for rare OOV PN re-ranking and lexical context re-ranking for LDA as well as for Entity- Topic models. The results show an improvement in both Recall and the Mean Average Precision.
Fichier non déposé

Dates et versions

hal-01184955 , version 1 (18-08-2015)

Identifiants

  • HAL Id : hal-01184955 , version 1

Citer

Imran Sheikh, Irina Illina, Dominique Fohr. Study of Entity-Topic Models for OOV Proper Name Retrieval. Interspeech 2015, Sep 2015, Dresden, Germany. ⟨hal-01184955⟩
244 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More