Home /
Research
Showing 571 - 576 / 904
Context-aware Stand-alone Neural Spelling Correction
XiangciLi, HairongLiu, LiangHuang....
Published date-11/12/2020
LanguageModelling, SpellingCorrection
Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. …
Incorporating a Local Translation Mechanism into Non-autoregressive Translation
XiangKong, ZhisongZhang, EduardHovy....
Published date-11/12/2020
MachineTranslation
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target …
Turning Transport Data to Comply with EU Standards while Enabling a Multimodal Transport Knowledge Graph
MarioScrocca, MarcoComerio, AlessioCarenini....
Published date-11/12/2020
Complying with the EU Regulation on multimodal transportation services requires sharing data on the National Access Points in one of the standards (e.g., NeTEx and SIRI) indicated by the European …
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
KarlSchmeckpeper, OlehRybkin, KostasDaniilidis....
Published date-11/12/2020
Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to …
Adversarial Robustness Against Image Color Transformation within Parametric Filter Space
ZhengyuZhao, ZhuoranLiu, MarthaLarson....
Published date-11/12/2020
We propose Adversarial Color Enhancement (ACE), a novel approach to generating non-suspicious adversarial images by optimizing a color transformation within a parametric filter space. The filter we use approximates human-understandable …
Analyzing Neural Discourse Coherence Models
YoumnaFarag, JosefValvoda, HelenYannakoudakis....
Published date-11/12/2020
In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that …