Are extractive text summarisation techniques portable to broadcast news?

Christensen, Heidi; Gotoh, Yoshihiko; Kolluru, BalaKrishna; Renals, Steve

doi:10.1109/asru.2003.1318489

Cited by 10 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work, the manual classifications into Spontaneous and Read were not available and instead we performed an automatic classification based on the length of the news story [9]. The results are rather similar for both cases.…”

Section: Resultsmentioning

confidence: 61%

See 1 more Smart Citation

From Text Summarisation to Style-Specific Summarisation for Broadcast News

Christensen

Kolluru

Gotoh

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we report on a series of experiments investigating the path from text-summarisation to style-specific summarisation of spoken news stories. We show that the portability of traditional text summarisation features to broadcast news is dependent on the diffusiveness of the information in the broadcast news story. An analysis of two categories of news stories (containing only read speech or some spontaneous speech) demonstrates the importance of the style and the quality of the transcript, when extracting the summary-worthy information content. Further experiments indicate the advantages of doing style-specific summarisation of broadcast news.

show abstract

Section: Resultsmentioning

confidence: 61%

“…These one-sentence summaries were all produced by the same human summariser, and validated in an evaluation experiment for their consistency and quality (see [9] for further details).…”

Section: Datamentioning

confidence: 99%

From Text Summarisation to Style-Specific Summarisation for Broadcast News

Christensen

Kolluru

Gotoh

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Christensen et al. () compared the effect of individual lexical and structural features on both English text and speech summarization. For newspapers, they observed that the most revealing information was provided by the position of sentences, but found no such dominant trait for broadcast news.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Frequently assigned video tags are related to named entities, such as people and object categories (Kim, ). Named entities, which are often related to topic‐oriented words, are more important in speech summarization than in text summarization (Christensen, Gotoh, Kolluru, & Renalset, ; Zhang, Cohn, & Ciravegna, ).…”

Section: Introductionmentioning

confidence: 99%

Generic speech summarization of transcribed lecture videos: Using tags and their semantic relations

Kim

2014

Asso for Info Science & Tech

View full text Add to dashboard Cite

We propose a tag-based framework that simulates human abstractors' ability to select significant sentences based on key concepts in a sentence as well as the semantic relations between key concepts to create generic summaries of transcribed lecture videos. The proposed extractive summarization method uses tags (viewer-and author-assigned terms) as key concepts. Our method employs Flickr tag clusters and WordNet synonyms to expand tags and detect the semantic relations between tags. This method helps select sentences that have a greater number of semantically related key concepts. To investigate the effectiveness and uniqueness of the proposed method, we compare it with an existing technique, latent semantic analysis (LSA), using intrinsic and extrinsic evaluations. The results of intrinsic evaluation show that the tag-based method is as or more effective than the LSA method. We also observe that in the extrinsic evaluation, the grand mean accuracy score of the tag-based method is higher than that of the LSA method, with a statistically significant difference. Elaborating on our results, we discuss the theoretical and practical implications of our findings for speech video summarization and retrieval.

show abstract

“…Applying text-based technologies (Mani and Maybury, 1999) to speech is not always viable and often the systems are not equipped to capture speech specific phenomena (Kolluru et al, 2003;Christensen et al, 2003). One fundamental problem with speech summarization is that it contains speech recognition errors and disfluencies (Valenza et al, 1999;Murray et al, 2005a,b).…”

Section: Introductionmentioning

confidence: 97%