INTERSPEECH 2015
16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

Leveraging Word Embeddings for Spoken Document Summarization

Kuan-Yu Chen (1), Shih-Hung Liu (1), Hsin-Min Wang (1), Berlin Chen (2), Hsin-Hsi Chen (3)

(1) Academia Sinica, Taiwan
(2) National Taiwan Normal University, Taiwan
(3) National Taiwan University, Taiwan

Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express the most important theme of the document, has been an active area of research and experimentation. On the other hand, word embedding has emerged as a newly favorite research subject because of its excellent performance in many natural language processing (NLP)-related tasks. However, as far as we are aware, there are relatively few studies investigating its use in extractive text or speech summarization. A common thread of leveraging word embeddings in the summarization process is to represent the document (or sentence) by averaging the word embeddings of the words occurring in the document (or sentence). Then, intuitively, the cosine similarity measure can be employed to determine the relevance degree between a pair of representations. Beyond the continued efforts made to improve the representation of words, this paper focuses on building novel and efficient ranking models based on the general word embedding methods for extractive speech summarization. Experimental results demonstrate the effectiveness of our proposed methods, compared to existing state-of-the-art methods.

Full Paper

Bibliographic reference.  Chen, Kuan-Yu / Liu, Shih-Hung / Wang, Hsin-Min / Chen, Berlin / Chen, Hsin-Hsi (2015): "Leveraging word embeddings for spoken document summarization", In INTERSPEECH-2015, 1383-1387.