Abstract Dense embedding-based semantic matching is widely used in e-commerce product search to address the shortcomings of lexical such as sensitivity spelling variants. The recent advances BERT-like language model encoders, have however, not found their way realtime due strict inference latency requirement imposed on websites. While bi-encoder BERT architectures enable fast approximate neares...

second-language (l2) acquisition is generally thought to be constrained by maturational factors that circumscribe a critical period for native-like attainment. consistent with the maturational view are age effects among learners who begin l2 acquisition prior to, but not after, closure of the putative critical period. some studies indicate that native-like acquisition of a second language by le...

Scale-space theory has been established primarily by the computer vision and signal processing communities as a well-founded and promising framework for multi-scale processing of signals (e.g., images). By embedding an original signal into a family of gradually coarsen signals parameterized with a continuous scale parameter, it provides a formal framework to capture the structure of a signal at...