Extractive Text-Based Summarization of Arabic Videos: Issues, Approaches and Evaluations

Abstract

In this paper, we present and evaluate a method for extractive textbased summarization of Arabic videos. The algorithm is proposed in the scope of the AMIS project that aims at helping a user to understand videos given in a foreign language (Arabic). For that, the project proposes several strategies to translate and summarize the videos. One of them consists in transcribing the Arabic videos, summarizing the transcriptions, and translating the summary. In this paper we describe the video corpus that was collected from YouTube and present and evaluate the transcription-summarization part of this strategy. Moreover, we present the Automatic Speech Recognition (ASR) system used to transcribe the videos, and show how we adapted this system to the Algerian dialect. Then, we describe how we automatically segment into sentences the sequence of words provided by the ASR system, and how we summarize the obtained sequence of sentences. We evaluate objectively and subjectively our approach. Results show that the ASR system performs well in terms of Word Error Rate on MSA, but needs to be adapted for dealing with Algerian dialect data. The subjective evaluation shows the same behaviour than ASR: transcriptions for videos containing dialectal data were better scored than videos containing only MSA data. However, summaries based on transcriptions are not as well rated, even when transcriptions are better rated. Last, the study shows that features, such as the lengths of transcriptions and summaries, and the subjective score of transcriptions, explain only 31% of the subjective score of summaries.

A Comparative Study for Speech Summarization Based on Machine Learning: A Survey

“…Users can first see a high-level summary of the information, then drill down into longer and more thorough summaries or listen to the raw audio itself using hierarchical summarization. PEGASUS the current state-of-the-art abstractive summarization model was used, which is capable of producing summaries of significantly higher human quality [14]. Kumar, B. D. (n.d.) used an Essence vector (EV) modeling which is an unsupervised paragraph embedding method aims to derive the most important information from a paragraph while also including general background information.…”

“…The total video corpus consists of roughly 300 hours of video, with approximately 100 hours in each of the languages (French, English and Arabic) in [14]. How-2 dataset includes 2000 hours of instructional videos, as well as text transcripts, speech, video, translations, and summaries was employed [18].…”