Summarization Assistant for News Brief Services on Cellular Phones
7504Authors
nan
Abstract
A Chinese news summarization method is proposed in order to help humans deal with the message services of news briefs broadcast over cell phones. The problem to be solved here is unique because a strict length limit (69 or 45 characters) is imposed on the summaries for the message service. This requires some sort of automatic sentence fusion, rather than sentence selection alone. In the proposed method, important sentences were first identified based on the news content. They were matched against the news headline to determine a suitable position for concatenation with the headline to become candidates. These candidates were then ranked by their length and fitness for manual selection. In our evaluation, among 40 short news updates in the inside testing set, over 75% (80%) of the best candidates yield acceptable summaries without manual editing for the length limit of 69 (45) characters. These numbers, however, reduce to 70.7% (53.3%) for the outside testing set of 75 news stories of ordinary length. It seems that the shorter the length limit, the more difficult the problem of getting the summary from long stories. Nevertheless, the proposed method has the potential not only to reduce the cost of manual operation, but also to integrate and synchronize with other media in such services in the future. Keywords: Cell Phone Service, News Brief Message, Automated Summarization, Chinese News 1.
Keywords
Full Content
Computational Linguistics and Chinese Language Processing Vol. 14, No. 1, March 2009, pp. 85-104 85 © The Association for Computational Linguistics and Chinese Language Processing [Received February 13, 2009; Revised July 16, 2009; Accepted July 17, 2009] Summarization Assistant for News Brief Services on Cellular Phones Yuen-Hsien Tseng∗ Abstract A Chinese news summarization method is proposed in order to help humans deal with the message services of news briefs broadcast over cell phones. The problem to be solved here is unique because a strict length limit (69 or 45 characters) is imposed on the summaries for the message service. This requires some sort of automatic sentence fusion, rather than sentence selection alone. In the proposed method, important sentences were first identified based on the news content. They were matched against the news headline to determine a suitable position for concatenation with the headline to become candidates. These candidates were then ranked by their length and fitness for manual selection. In our evaluation, among 40 short news updates in the inside testing set, over 75% (80%) of the best candidates yield acceptable summaries without manual editing for the length limit of 69 (45) characters. These numbers, however, reduce to 70.7% (53.3%) for the outside testing set of 75 news stories of ordinary length. It seems that the shorter the length limit, the more difficult the problem of getting the summary from long stories. Nevertheless, the proposed method has the potential not only to reduce the cost of manual operation, but also to integrate and synchronize with other media in such services in the future. Keywords: Cell Phone Service, News Brief Message, Automated Summarization, Chinese News 1. Introduction The popularity of cell phones in the Taiwan area has reached the highest rate in the world during the last few years. Over 23 million cell phone numbers were used as of June 2002, which is slightly more than the population of Taiwan (Wang, 2002). To better utilize this ubiquitous communication device, a number of content providers have provided Chinese news ∗ National Taiwan Normal University, No.162, Sec. 1, Heping East Road., Taipei City, Taiwan (R.O.C.), 106, Tel: 886-2-77345535 E-mail: samtseng@ntnu.edu.tw 86 Yuen-Hsien Tseng brief services over the cell phone, such as United Daily News (United Daily News, n.d.), Central News Agency (Central News Agency, n.d.), and PC Home in Taiwan. The Asahi Shimbun in Japan (the second largest news agency in the world) has provided such news message services at an inexpensive rate since 1999, in the hope that the increase in the number of the readers of their content could lead to an increase in the subscriptions to their newspaper (China Times, n.d.). As multimedia technologies continue to improve, future news service over the cell phone may not only include text, but also speech, images, or video, integrated and synchronized. To reach this vision, however, the operation cost should be low enough to sustain such services. Therefore, automated methods of cost containment would be of great help. The news brief shown on …
Content truncated to 500 words
Labeled Text
A Chinese news summarization method is proposed in order to help humans deal with the message services of news briefs broadcast over cell phones. The problem to be solved here is unique because a strict length limit (69 or 45 characters) is imposed on the summaries for the message service. This requires some sort of automatic sentence fusion, rather than sentence selection alone. In the proposed method, important sentences were first identified based on the news content. They were matched against the news headline to determine a suitable position for concatenation with the headline to become candidates. These candidates were then ranked by their length and fitness for manual selection. In our evaluation, among 40 short news updates in the inside testing set, over 75% (80%) of the best candidates yield acceptable summaries without manual editing for the length limit of 69 (45) characters. These numbers, however, reduce to 70.7% (53.3%) for the outside testing set of 75 news stories of ordinary length. It seems that the shorter the length limit, the more difficult the problem of getting the summary from long stories. Nevertheless, the proposed method has the potential not only to reduce the cost of manual operation, but also to integrate and synchronize with other media in such services in the future. Keywords: Cell Phone Service, News Brief Message, Automated Summarization, Chinese News 1.
Publication Details
- Paper ID:
- 7504
- Year:
- 2009
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan