In this work, we showcase the Image2Text system, which is a real-time captioning system that can generate human-level natural language description for any input image. We formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from...

The paper presents the design concept of the VoiceTRAN Communicator that integrates speech recognition, machine translation and text-to-speech synthesis using the DARPA Galaxy architecture. The aim of the project is to build a robust multimodal speech-to-speech translation communicator able to translate simple domain-specific sentences in the Slovenian-English language pair. The project represe...

Among the formalisms for qualitative spatial reasoning, the Region Connection Calculus and its variant, the constraint algebra RCC8, have received particular attention recently. A translation of RCC8 constraints into a multimodal logic has been proposed by Bennett, but in his work a thorough semantical foundation of RCC8 and of the translation into modal logic is missing. In the present paper, ...

Statistical machine translation (SMT) systems depend on the availability of domain-specific bilingual parallel text. However parallel corpora are a limited resource and they are often not available for some domains or language pairs. We analyze the feasibility of extracting parallel sentences from multimodal comparable corpora. This work extends the use of comparable corpora by using audio sour...

How do English as a lingua franca (ELF) speakers achieve multimodal cohesion on the basis of their specific interests and cultural backgrounds? From a dialogic and collaborative view of communication, this study focuses on how verbal and nonverbal modes cohere together during intercultural conversations. The data include approximately 160-minute transcribed video recordings of ELF interactions ...

Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image a set of diverse images multiple target domains using pair generator and discriminator. Existing multimodal I2I methods adopt domain-specific content encoders for different domains, where each encoder is trained from the same doma...

Journey to the West is one of four famous Chinese classical works and it was reproduced into TV drama both at home abroad, which has aroused great concern. However, current studies mainly compare English translated versions with one, focusing on translation strategies for verbal texts or cultural level. Therefore, this study explores different kinds intersemiotic shifts in subtitle reasons that...

conclusions the combination of intravenous paracetamol 1 gr and ketamine 0.5 mg/kg resulted in an overall reduction in pain scores, decreased postoperative analgesic requirements, and lower agitation score compared with intravenous paracetamol 1 gr and tramadol 0.7 mg/kg for patients undergoing renal surgery. results postoperative pain scores were significantly lower in the pk group than in the...