Radially-Distorted Conjugate Translations [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns. Even with imagery from moderately distorted lenses, plane rectification using the pinhole camera model
Chum, Ondrej +3 more
core +2 more sources
Do GPTs Produce Less Literal Translations? [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Large Language Models (LLMs) such as GPT-3 have emerged as general-purpose language models capable of addressing many natural language generation or understanding tasks.
Vikas Raunak +3 more
semanticscholar +1 more source
Semantic and sentiment analysis of selected Bhagavad Gita translations using BERT-based language framework [PDF]
IEEE Access, 2022 It is well known that translations of songs and poems not only breaks rhythm and rhyming patterns, but also results in loss of semantic information. The Bhagavad Gita is an ancient Hindu philosophical text originally written in Sanskrit that features a ...
Rohitash Chandra, Venkatesh Kulkarni
semanticscholar +1 more source
Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities [PDF]
AAAI Conference on Artificial Intelligence, 2018 Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that can process and ...
Hai Pham +4 more
semanticscholar +1 more source
Boosting Neural Machine Translation with Similar Translations
Annual Meeting of the Association for Computational Linguistics, 2020 This paper explores data augmentation methods for training Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches.
Jitao Xu, J. Crego, Jean Senellart
semanticscholar +1 more source
The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2017 The Parallel Meaning Bank is a corpus of translations annotated with shared, formal meaning representations comprising over 11 million words divided over four languages (English, German, Italian, and Dutch).
Johan Bos +7 more
semanticscholar +1 more source
How Human is Machine Translationese? Comparing Human and Machine Translations of Text and Speech
International Workshop on Spoken Language Translation, 2020 Translationese is a phenomenon present in human translations, simultaneous interpreting, and even machine translations. Some translationese features tend to appear in simultaneous interpreting with higher frequency than in human text translation, but the
Yuri Bizzoni +5 more
semanticscholar +1 more source
Alignment-Enhanced Transformer for Constraining NMT with Pre-Specified Translations
AAAI Conference on Artificial Intelligence, 2020 We investigate the task of constraining NMT with pre-specified translations, which has practical significance for a number of research and industrial applications.
Kai Song +7 more
semanticscholar +1 more source
Translations and Boundaries in the Gap Between HCI Theory and Design Practice
ACM Trans. Comput. Hum. Interact., 2020 The gap between research and design practice has long been a concern for the HCI community. In this article, we explore how different translations of HCI knowledge might bridge this gap.
R. Velt, S. Benford, S. Reeves
semanticscholar +1 more source
Found in Translation: Reconstructing Phylogenetic Language Trees from Translations [PDF]
Annual Meeting of the Association for Computational Linguistics, 2017 Translation has played an important role in trade, law, commerce, politics, and literature for thousands of years. Translators have always tried to be invisible; ideal translations should look as if they were written originally in the target language. We
Ella Rabinovich, Noam Ordan, S. Wintner
semanticscholar +1 more source