In this paper we explore an unsupervised approach to classify video content by analyzing the corresponding subtitles. The proposed method is based on the WordNet lexical database and the WordNet domains and applies natural language processing techniques on video subtitles. The method is divided into several steps. The first step includes subtitle text preprocessing. During the next steps, a key...

This paper describes our work on building and employing Statistical Machine Translation systems for TV subtitles in Scandinavia. We have built translation systems for Danish, English, Norwegian and Swedish. They are used in daily subtitle production and translate large volumes. As an example we report on our evaluation results for three TV genres. We discuss our lessons learned in the system de...

We propose a weakly supervised framework for domain adaptation in a multi-modal context for multi-label classification. This framework is applied to annotate objects such as animals in a target video with subtitles, in the absence of visual demarcators. We start from classifiers trained on external data (the source, in our setting ImageNet), and iteratively adapt them to the target dataset usin...

We describe the use of text data scraped from the web to augment language models for Automatic Speech Recognition and Keyword Search for Low Resource Languages. We scrape text from multiple genres including blogs, online news, translated TED talks, and subtitles. Using linearly interpolated language models, we find that blogs and movie subtitles are more relevant for language modeling of conver...

The subtitles on video are very useful for us to understand video's contents. If we can extract text information from the subtitles, it will be very helpful to establish a database of video’s content that includes annotations and indexes. To extract text from videos, most text detection and extraction methods use the text color, background contrast, and texture information. However, the limitat...

Even when the role of a conversational agent is well known users persist in confronting them with Out-of-Domain input. This often results in inappropriate feedback, leaving the user unsatisfied. In this paper we explore the automatic creation/enrichment of conversational agents’ knowledge bases by taking advantage of natural language interactions present in the Web, such as movies subtitles. Th...

This paper presents the AMARA corpus of on-line educational content: a new parallel corpus of educational video subtitles, multilingually aligned for 20 languages, i.e. 20 monolingual corpora and 190 parallel corpora. This corpus includes both resource-rich languages such as English and Arabic, and resource-poor languages such as Hindi and Thai. In this paper, we describe the gathering, validat...

Captioning of recorded videos is beneficial to many and a matter compliance with accessibility regulations guidelines. Like captions, real-time captions can also be means implement the Universal Design for Learning checkpoint offer text-based alternatives auditory information. A cost-effective solution live online presentations use speech recognition technologies generate automated captions. In...

This paper discusses the application of classical machine learning approaches to the task of Dialogue Act Recognition for text-based Sinhala. A study was carried out to identify a dialogue act tag set for Sinhala. A new corpus using Sinhala subtitles for English movies was created and was annotated with the selected dialogue acts. Evaluation of the dialogue act recognition system was performed ...

We present a framework that automatically and quickly learns a large number of signs from sign language-interpreted TV broadcasts by exploiting supervisory information available in the subtitles. Our contributions are: (i) we show that, somewhat counter-intuitively, mouth patterns are highly informative for distinguishing words in a language for the Deaf, and their co-occurrence with signing ca...