본문 바로가기
  • Home

Comparing the Use of Semantic Relations between Tags Versus Latent Semantic Analysis for Speech Summarization

Kim, Hyun Hee 1

1명지대학교

Accredited

ABSTRACT

We proposed and evaluated a tag semantic analysis method in which original tags are expanded and the semantic relations between original or expanded tags are used to extract key sentences from lecture speech transcripts. To do that, we first investigated how useful Flickr tag clusters and WordNet synonyms are for expanding tags and for detecting the semantic relations between tags. Then, to evaluate our proposed method, we compared it with a latent semantic analysis (LSA) method. As a result, we found that Flick tag clusters are more effective than WordNet synonyms and that the F measure mean (0.27) of the tag semantic analysis method is higher than that of LSA method (0.22).

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.