Study of entity-topic models for OOV proper name retrieval

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 EntityTopic models. The results show an improvement in both Recall and the Mean Average Precision.