Nowadays, Web is characterized by a growing availability of multimedia data together with a strong need for integrating different media and modalities of interaction. Hence, the main goal is to bring into the Web data thought and produced for different media, such as TV or radio content. In this scenario, we focus on multimodal news aggregation retrieval and fusion. In particular, we present preliminary experiments aimed at automatically suggesting keywords to news and news aggregations. The proposed solution is based on the adoption of extraction-based text summarization techniques. Experiments are aimed at comparing the selected text summarization techniques with respect to a simple technique based on part-ofspeech tagging. Results show that the proposed solution performs better than the baseline solution in terms of precision, recall, and F1.
Experimenting text summarization on multimodal aggregation
ARMANO, GIULIANO;GIULIANI, ALESSANDRO;VARGIU, ELOISA
2011-01-01
Abstract
Nowadays, Web is characterized by a growing availability of multimedia data together with a strong need for integrating different media and modalities of interaction. Hence, the main goal is to bring into the Web data thought and produced for different media, such as TV or radio content. In this scenario, we focus on multimodal news aggregation retrieval and fusion. In particular, we present preliminary experiments aimed at automatically suggesting keywords to news and news aggregations. The proposed solution is based on the adoption of extraction-based text summarization techniques. Experiments are aimed at comparing the selected text summarization techniques with respect to a simple technique based on part-ofspeech tagging. Results show that the proposed solution performs better than the baseline solution in terms of precision, recall, and F1.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
