Learn More
This paper proposes a new technique to enable Natural Language Understanding (NLU) systems to handle user queries beyond their original semantic schemas defined by intents and slots. Knowledge graph and search query logs are used to extend NLU system's coverage by transferring intents from other domains to a given domain. The transferred intents as well as(More)
In this paper, we introduce the task of selecting compact lexicon from large, noisy gazetteers. This scenario arises often in practice, in particular spoken language understanding (SLU). We propose a simple and effective solution based on matrix decomposition techniques: canonical correlation analysis (CCA) and rank-revealing QR (RRQR) factorization. CCA is(More)
Spoken language understanding (SLU) systems use various features to detect the domain, intent and semantic slots of a query. In addition to n-grams, features generated from entity dictionaries are often used in model training. Clean or properly weighted dictionaries are critical to improve model's coverage and accuracy for unseen entities during test time.(More)
Extending the technique of the perfectly matched layer ͑PML͒ to discrete lattice systems, a multiscale method was proposed by To and Li ͓Phys. Rev. B 72, 035414 ͑2005͔͒, which was termed the perfectly matched multiscale simulation ͑PMMS͒. In this paper, we shall revise the proposed PMMS formulation, and extend it to multiple dimensions. It is shown in(More)