Jiazhong Nie

Learn More
As an important component in many speech and language processing applications, statistical language model has been widely investigated. The bigram topic model, which combines advantages of both the traditional n-gram model and the topic model, turns out to be a promising language modeling approach. However, the original bigram topic model assigns the same(More)
The potential benefit of integrating contextual information for recommendation has received much research attention recently, especially with the ever-increasing interest in mobile-based recommendation services. However, context based recommendation research is limited due to the lack of standard evaluation data with contextual information and reliable(More)
Many recommender systems might be part of an e-commerce or multi functional system (or portal) where various information about users, products/documents, social networks, and different types of user feedback about products/documents are available. This paper exploits the heterogeneous information a recommender system might collect to make the most(More)
This paper introduces an approach which jointly performs a cascade of segmentation and labeling subtasks for Chinese lexical analysis, including word segmentation, named entity recognition and partof-speech tagging. Unlike the traditional pipeline manner, the cascaded subtasks are conducted in a single step simultaneously, therefore error propagation could(More)
〈μ,D〉 = ∑ i=1 wi 〈ui,uiu T i 〉 Gradient descent Mill maintains the two moments 〈μt,Dt〉 ∈ U as parameter At trial t = 1 . . . T, the Mill 1. Decomposes parameter 〈μt,Dt〉 into a mixture of directions and draws ut from mixture 2. Receives Wind direction xt and gain E [ (ut xt + c) 2] 3. Updates 〈μt,Dt〉 to 〈μ̂t+1, D̂t+1〉 with the gradient of the expected gain(More)
To improve the Mandarin large vocabulary continuous speech recognition (LVCSR), a unified framework based approach is introduced to exploit multi-level linguistic knowledge. In this framework, each knowledge source is represented by a Weighted Finite State Transducer (WFST), and then they are combined to obtain a so-called analyzer for integrating(More)
Deep neural networks (DNNs) had great success on NLP tasks such as language modeling, machine translation and certain question answering (QA) tasks. However, the success is limited at more knowledge intensive tasks such as QA from a big corpus. Existing end-to-end deep QA models (Miller et al., 2016; Weston et al., 2014) need to read the entire text after(More)
Boosting algorithms can be viewed as a zero-sum game. At each iteration a new column / hypothesis is chosen from a game matrix representing the entire hypotheses class. There are algorithms for which the gap between the value of the sub-matrix (the t columns chosen so far) and the value of the entire game matrix is O( √ logn t ). A matching lower bound has(More)