TED выступления

In this paper, we address statistical ma- chine translation of public conference talks. Modeling the style of this genre can be very challenging given the shortage of available in-domain training …...

AbstractWe present ParCor, a parallel corpus of texts in which pronoun coreference ― reduced coreference in which pronouns are used as referring expressions ― has been annotated. The corpus is …...

Domain adaptation boosts translation quality on in-domain data, but translation quality for domain adapted systems on out-of-domain data tends to suffer. Users of web-based translation services expect high quality translation …...

. This paper proposes a new discriminative framework to train continuous-space trans- lation models based. This framework relies on the definition of a new objective function that al- lows us …...

AbstractThis paper describes metaTED ― a freely available corpus of metadiscursive acts in spoken language collected via crowdsourcing. Metadiscursive acts were annotated on a set of 180 randomly chosen TED …...

Previous simultaneous translation approaches either use a separate segmentation step followed by a machine translation decoder or rely on the decoder to segment and translate without training the segmenter to …...

AbstractThough people rarely speak in complete sentences, punctuation confers many benefits to the readers of transcribed speech. Unfortunately, most ASR systems do not produce punctuated output. To address this, we …...

AbstractWe present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. Our architecture features neural machine translation generating output of preferred length, prosodic alignment of the translation …...

AbstractWe propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific …...

AbstractMultilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, …...

AbstractOne key ingredient of neural machine translation is the use of large datasets from different domains and resources (e.g. Europarl, TED talks). These datasets contain documents translated by professional translators …...

AbstractMultilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination …...

AbstractIn this paper, we explore the relation between gestures and language. Using a multimodal dataset, consisting of Ted talks where the language is aligned with the gestures made by the …...