On-chip optical communications are growingly aiming at multimode operation together with mode-division multiplexing to further increase the transmission capacity. Optical switches, which are capable of optical signals switching at the nodes, play a key role in optical networks. We demonstrate a 2 × 2 electro-optic Mach–Zehnder interferometer-based mode- and polarization-selective switch fabricated by standard complementary metal–oxide–semiconductor process. An electro optic tuner based on a PN-doped junction in one of the Mach–Zehnder interferometer arms enables dynamic switching in 11 ns. For all the channels, the overall insertion losses and inter-modal crosstalk values are below 9.03 and –15.86 dB at 1550 nm, respectively.
Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query. Under the setup of cross-domain, traditional semantic parsing models struggle to adapt to unseen database schemas. To improve the model generalization capability for rare and unseen schemas, we propose a new architecture, ShadowGNN, which processes schemas at abstract and semantic levels. By ignoring names of semantic items in databases, abstract schemas are exploited in a well-designed graph projection neural network to obtain delexicalized representation of question and schema. Based on the domain-independent representations, a relation-aware transformer is utilized to further extract logical linking between question and schema. Finally, a SQL decoder with context-free grammar is applied. On the challenging Text-to-SQL benchmark Spider, empirical results show that ShadowGNN outperforms state-of-the-art models. When the annotated data is extremely limited (only 10% training set), ShadowGNN gets over absolute 5% performance gain, which shows its powerful generalization ability. Our implementation will be open-sourced at https://github. com/WowCZ/shadowgnn.
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of separate triples (domain-slotvalue), in this paper, we employ a structured state representation and cast dialogue state tracking as a sequence generation problem. Based on this new formulation, we propose a CoaRsE-to-fine DIalogue state Tracking (CREDIT) approach. Taking advantage of the structured state representation, which is a marked language sequence, we can further fine-tune the pre-trained model (by supervised learning) by optimizing natural language metrics with the policy gradient method. Like all generative state tracking methods, CREDIT does not rely on pre-defined dialogue ontology enumerating all possible slot values. Experiments demonstrate our tracker achieves encouraging joint goal accuracy for the five domains in MultiWOZ 2.0 and MultiWOZ 2.1 datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.