Articles

AbstractOur ability to understand language often relies on common-sense knowledge ― background information the speaker can assume is known by the reader. Similarly, our comprehension of the language used in complex domains relies on access to domain-specific knowledge. Capturing common-sense and domain-specific knowledge can be achieved by taking advantage of …...

AbstractWe present a corpus of time-aligned spoken data of Wikipedia articles as well as the pipeline that allows to generate such corpora for many languages. There are initiatives to create and sustain spoken Wikipedia versions in many languages and hence the data is freely available, grows over time, and can …...

AbstractWe present a corpus and a knowledge database aiming at developing Question-Answering in a new context, the open world of a video game. We chose a popular game called ‘Minecraft’, and created a QA corpus with a knowledge database related to this game and the ontology of a meaning representation …...

We introduce possibilities of automatic evaluation of surface text coherence (cohesion) in texts written by learners of Czech during certified exams for non-native speakers. On the basis of a corpus analysis, we focus on finding and describing relevant distinctive features for automatic detection of A1–C1 levels (established by CEFR – …...

. Sentiment analysis is an emerging research field. One of the major tasks of sentiment analysis is building sentiment lexicons and calculating their scores, which is an essential job that provides “material” for all sentiment analysis problems. In this paper, we propose a fuzzy language computation by taking linguistic context …...

This paper presents the challenges and the methodology followed in the design of a new Input Method (IME) for the Taiwanese (Hokkien) language. We first describe the context, the motivations and some of the main issues related to the input of text in Taiwanese on modern computer systems and mobile …...

Literatures pertaining to English and Mandarin fricative/affricate productions by adults with cerebral palsy (CP) showed that acoustic measurements such as rise time contrast, initial burst rate contrast and friction noise duration contrast associated with fricative/affricate productions were highly correlated with overall speech intelligibility. However, the phonetic features of fricatives/affricates produced …...

In this paper, we use super-vectors in support vector machines for automatic speech emotion recognition. In our implementation, an utterance is converted to a super-vector formed by the mean vectors of a Gaussian mixture model adapted from a universal back- ground model. The proposed method is evaluated on FAU-Aibo database …...

This paper tries to demonstrate our exploratory efforts in tackling with the “high accuracy-low quantity” problem of human word sense annotation task in Chinese, and ultimately reach the goal of automatic word sense annotation. Our proposed annotation architecture consists of explicit and implicit aspects of of crowdsourcing approach. Explicit method …...

From the Internet slang “������(You’ll lose if being serious)” to a wide variety of collocations with the word “��(being serious)”, the Internet users in Taiwan show a preference to the word “��.” While the dictionary definitions of this word have included “being practical”, “being serious”, and “not being careless,” this …...

AbstractSpoken Language Translation is currently a hot topic in the research community. This task is very complex, involving automatic speech recognition, text-normalization and machine translation. We present our speech translation system, which was compared against the other systems participating in the IWSLT 2016 Shared Task. We introduce our ASR system …...

AbstractThis paper describes LIMSI’s submission to the MT track of IWSLT 2016. We report results for translation from English into Czech. Our submission is an attempt to address the difficulties of translating into a morphologically rich language by paying special attention to the morphology generation on target side. To this …...

AbstractThis paper describes QCRI’s machine translation systems for the IWSLT 2016 evaluation campaign. We participated in the Arabic→English and English→Arabic tracks. We built both Phrase-based and Neural machine translation models, in an effort to probe whether the newly emerged NMT framework surpasses the traditional phrase-based systems in Arabic-English language pairs. …...

AbstractIn this paper, we describe FBK’s neural machine translation (NMT) systems submitted at the International Workshop on Spoken Language Translation (IWSLT) 2016. The systems are based on the state-of-the-art NMT architecture that is equipped with a bi-directional encoder and an attention mechanism in the decoder. They leverage linguistic information such …...

AbstractIn this paper, we present the KIT systems of the IWSLT 2016 machine translation evaluation. We participated in the machine translation (MT) task as well as the spoken language language translation (SLT) track for English→German and German→English translation. We use attentional neural machine translation (NMT) for all our submissions. We …...

AbstractThis paper describes the speech recognition system of IOIT for IWSLT 2016. Four single DNN-based systems were developed to produce the 1st-pass lattices for the test sets using a baseline language model. The 2nd-pass lattices were further obtained by applying N-best list rescoring on topic adapted language models which were …...

AbstractThis paper aims to unravel the automatic quality assessment for spoken language translation (SLT). More precisely, we propose several effective estimators based on our estimation of transcription (ASR) quality, translation (MT) quality, or both (combined and joint features using ASR and MT information). Our experiments provide an important opportunity to …...

AbstractWe describe the Microsoft Speech Language Translation (MSLT) corpus, which was created in order to evaluate end-to-end conversational speech translation quality. The corpus was created from actual conversations over Skype, and we provide details on the recording setup and the different layers of associated text data. The corpus release includes …...

AbstractIn this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. State-of-the-art bidirectional long short-term memory (LSTM) and deep, multilingually boosted feed-forward neural network (FFNN) acoustic models are trained an …...

AbstractIn this paper, we investigate a multilingual approach for speech disfluency removal. A major challenge of this task comes from the costly nature of disfluency annotation. Motivated by the fact that speech disfluencies are commonly observed throughout different languages, we investigate the potential of multilingual disfluency modeling. We suggest that …...