1. 1 Sentence Extraction-based Presentation Summarization Techniques and Evaluation Metrics Makoto Hirohata, Yousuke Shinnaka, Koji Iwano and Sadaoki Furui ICASSP2005 Present ： Yao-Min Huang Date ： 04/07/2005

2. 2 Introduction One of the major applications of automatic speech recognition is to transcribe speech documents such as talks, presentations, lectures, and broadcast news. Spontaneous speech is ill-formed and very different from written text. –redundant information  repetitions, repairs... –Irrelevant or incorrect information  recognition errors

3. 3 Introduction Therefore, an approach in which all words are simply transcribed is not an effective one for spontaneous speech. Instead, speech summarization which extracts important information and removes redundant and incorrect information is ideal for recognizing spontaneous speech.

4. 4 Introduction (SAP2004)

5. 5 Sentence Extraction Methods Review SAP2004 –Important Sentence Extraction The score for important sentence extraction is calculated for each sentence. N : # of words in the sentence W L(w i ) 、 I(w i ) 、 C(w i ) are the linguistic score(trigram), the significance score(nouns, verbs, adjectives and out-of-vocabulary (OOV) ), and the confidence score of word w i, respectively. –The experiment shows that Significance score is more effective than L score and C score. This paper simply uses the significance score.

6. 6 Sentence Extraction Methods Review SAP2004 –Significance score measured by the amount of information for content words including nouns, verbs, adjectives and out-of- vocabulary (OOV) words, based on word occurrence in a corpus – –Important keywords are weighted and the words unrelated to the original content, such as recognition errors, are de- weighted by this score.

7. 7 Sentence Extraction Methods Extraction using latent semantic analysis –Equal to the “ Generic Text Summarization Using Relevance Measure and Latent Semantic Analysis SIGIR2001 “ – = ×∑××∑× Select the sentence which has the largest index value with the right singular vector (column vector of V)

8. 8 Sentence Extraction Methods Extraction using dimension reduction based on SVD –K=5

9. 9 Sentence Extraction Methods Extraction using sentence location –human subjects tend to extract sentences from the first and the last segments under the condition of 10% summarization ratio,whereas there is no such tendency at 50% summarization ratio.

10. 10 Sentence Extraction Methods Extraction using sentence location –The introduction and conclusion segments are estimated based on the Hearst method(1997) using sentence cohesiveness. which is measured by a cosine value between content word-frequency vectors consisting of more than a fixed number of content words.

11. 11 Sentence Extraction Methods Each segmentation boundary is the first sentence from the beginning or end of the presentation speech

12. 12 Objective Evaluation Metrics Summarization accuracy –SAP2004 measured in comparison with the closest word string extracted from the word network as the summarization accuracy. works reasonably well at relatively high summarization ratios such as 50%, but has problems at low summarization ratios such as 10% –since the variation between manual summaries is so large that the network accepts inappropriate summaries.

13. 13 Objective Evaluation Metrics Summarization accuracy –Therefore investigated word accuracy obtained by individually using the manual summaries (SumACCY-E). –(SumACCY-E/max) »the largest score among human summaries »which is equivalent to the NrstACCY proposed in [C. Hori..etc 2004,ACL]. –(SumACCY-E/ave) »average score

14. 14 Objective Evaluation Metrics Sentence recall / precision –Since sentence boundaries are not explicitly indicated in input speech Solution  T.Kitade.. etc,2004 –Extraction of a sentence in the recognition result is considered as extraction of one or multiple sentences in the manual summary with an overlap of 50% or more words. –In this metric, sentence recall/precision is measured by the largest score (F-measure/max) or the average score (F-measure/ave) of the F-measures.

15. 15 Objective Evaluation Metrics ROUGE-N

16. 16 Experiments Experimental conditions –30 presentations by 20 males and 10 females in the CSJ were automatically summarized at 10% summarization ratio. –Mean word recognition accuracy was 69%. –Sentence boundaries in the recognition results were automatically determined using language models, which achieved 72% recall and 75% precision. –The technique of extracting sentences significance score (SIG) latent semantic analysis (LSA) dimension reduction based on SVD (DIM); SIG combined with IC (sentence location) (SIG+IC); LSA combined with IC (LSA+IC); DIM combined with IC (DIM+IC).

17. 17 Experiments Subjective evaluation –180 automatic summaries (30 presentations x 6 summarization methods) were evaluated by 12 human subjects. –The summaries were evaluated in terms of ease of understanding and appropriateness as summaries in five levels 1-very bad; 2-bad; 3-normal;4-good; 5-very good. –The subjective evaluation results were converted into factor scores using factor analysis in order to normalize subjective differences.

18. 18 Experiments By combining the IC method using sentence location, every summarization method was significantly improved. SIG+IC achieved the best score, but the difference between SIG+IC and DIM+IC was not significant.

19. 19 Experiments Correlation between subjective and objective evaluation results –In order to investigate the relationship between subjective and objective evaluation results, the automatic summaries were evaluated by eight objective evaluation metrics SumACCY SumACCYE/max, SumACCY-E/ave, F-measure/max, F-measure/ave, ROUGE-1 (Uni-gram) ROUGE-2 (Bi-gram) ROUGE-3 (Tri-gram)

20. 20 Experiments max

21. 21 Experiments

22. 22 Experiments All the objective metrics yielded correlation with human judgment. If the effect of word recognition accuracy for each sentence is removed, all the metrics, except ROUGE-1, yield high correlations. –ROUGE-1 measures overlapping 1-grams, which probably causes the correlation between ROUGE-1 and the recognition accuracy.

23. 23 Experiments

24. 24 Experiments In contrast with the results averaged over all the presentations, no metric has strong correlation. –This is due to the large variation of scores over the whole set of presentations.

25. 25 CONCLUSION This paper has presented several sentence extraction methods for automatic presentation speech summarization and objective eval-uation metrics. We have proposed sentence extraction methods using dimension reduction based on SVD and sentence location. Under the condition of 10% summarization ratio, it was confirmed that the method using sentence location improves summarization results.

26. 26 CONCLUSION Among the objective evaluation metrics, SumACCY, SumACCY-E, F-measure, ROUGE-2 and 3 were found to be effective. Although the correlation between the subjective and objective scores averaged over presentations is high, the correlation for each individual presentation is not so high –due to the large variation of scores across presentations.

27. 27 Future Future research includes investigation of –other objective evaluation metrics –evaluation of summarization methods containing sentence compaction –producing optimum summarization techniques by employing objective evaluation metrics