This paper presents a fine-grained test suite for the language pair German–English. The test suite is based on a number of linguistically motivated categories and phenomena and the semi-automatic evaluation is carried out with regular expressions. We describe the creation and implementation of the test suite in detail, providing a full list of all categories and phenomena. Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese–English. We describe how we tracked the development of the performance of various systems MT systems over the years with the help of the test suite and which categories and phenomena are prone to resulting in MT errors. For the first time, we also make a large part of our test suite publicly available to the research community.
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking. However, it is challenging to organize, structure, and navigate a vast number of diverse argumentations and comments collected from many participants over a long time period. In this paper we demonstrate Common Round, a next generation platform for large-scale web debates, which provides functions for eliciting the semantic content and structures from the contributions of participants. In particular, Common Round applies language technologies for the extraction of semantic essence from textual input, aggregation of the formulated opinions and arguments. The platform also provides a cross-lingual access to debates using machine translation.
A huge body of continuously growing written knowledge is available on the web in the form of social media posts, RSS feeds, and news articles. Real-time information extraction from such high velocity, high volume text streams requires scalable, distributed natural language processing pipelines. We introduce such a system for fine-grained event recognition within the big data framework Flink, and demonstrate its capabilities for extracting and geo-locating mobility- and industry-related events from heterogeneous text sources. Performance analyses conducted on several large datasets show that our system achieves high throughput and maintains low latency, which is crucial when events need to be detected and acted upon in real-time. We also present promising experimental results for the event extraction component of our system, which recognizes a novel set of event types. The demo system is available at http://dfki.de/sd4m-sta-demo/.
Modern language learning courses are no longer exclusively based on books or face-to-face lectures. More and more lessons make use of multimedia and personalized learning methods. Many of these are based on e-learning solutions. Learning via the Internet provides 7/24 services that require sizeable human resources. Therefore we witness a growing economic pressure to employ computer-assisted methods for improving language learning in quality, efficiency and scalability. In this paper, we will address three applications of language technologies for language learning: 1) Methods and strategies for pronunciation training in second language learning, e.g., multimodal feedback via visualization of sound features, speech verification and prosody transplantation; 2) Dialogue-based language learning games; 3) Application of parsing and generation technologies to the automatic generation of paraphrases for the semi-automatic production of learning material.
In the area of Computer Assisted Language Learning(CALL), second language (L2) learners spoken data is an important resource for analysing and annotating typical L2 pronunciation errors. The annotation of L2 pronunciation errors in spoken data is not an easy task though, normally it requires manual annotation from trained linguists or phoneticians. In order to facilitate this task, in this paper, we present the MAT tool, a web-based tool intended to facilitate the annotation of L2 learners’ pronunciation errors at various levels. The tool has been designed taking into account recent studies on error detection in pronunciation training. It also aims at providing an easy and fast annotation process via a comprehensive and friendly user interface. The tool is based on the MARY TTS open source platform, from which it uses the components: text analyser (tokeniser, syllabifier, phonemiser), phonetic aligner and speech signal processor. Annotation results at sentence, word, syllable and phoneme levels are stored in XML format. The tool is currently under evaluation with a L2 learners spoken corpus recorded in the SPRINTER (Language Technology for Interactive, Multi-Media Online Language Learning) project.