Chinese word segmentation is a difficult, important and widely-studied sequence modeling problem. This paper demonstrates the ability of linear-chain conditional random fields (CRFs) to perform robust and accurate Chinese word segmentation by providing a principled framework that easily supports the integration of domain knowledge in the form of multiple lexicons of characters and words. We also present a probabilistic new word detection method, which further improves performance. Our system is evaluated on four datasets used in a recent comprehensive Chinese word segmentation competition. State-of-the-art performance is obtained.

No abstract

With the overwhelming volume of online news available today, there is an increasing need for automatic techniques to analyze and present news to the user in a meaningful and efficient manner. Previous research focused only on organizing news stories by their topics into a flat hierarchy. We believe viewing a news topic as a flat collection of stories is too restrictive and inefficient for a user to understand the topic quickly.In this work, we attempt to capture the rich structure of events and their dependencies in a news topic through our event models. We call the process of recognizing events and their dependencies event threading. We believe our perspective of modeling the structure of a topic is more effective in capturing its semantics than a flat list of on-topic stories.We formally define the novel problem, suggest evaluation metrics and present a few techniques for solving the problem. Besides the standard word based features, our approaches take into account novel features such as temporal locality of stories for event recognition and time-ordering for capturing dependencies. Our experiments on a manually labeled data sets show that our models effectively identify the events and capture dependencies among them.

We augment naive Bayes models with statistical n-gram language models to address shortcomings of the standard naive Bayes text classifier. The result is a generalized naive Bayes * Most research was conducted while the authors were at the School of Computer Science at University of Waterloo, Canada. 1classifier which allows for a local Markov dependence among observations; a model we refer to as the Chain Augmented Naive Bayes (CAN) Bayes classifier. CAN models have two advantages over standard naive Bayes classifiers. First, they relax some of the independence assumptions of naive Bayes-allowing a local Markov chain dependence in the observed variables-while still permitting efficient inference and learning. Second, they permit straightforward application of sophisticated smoothing techniques from statistical language modeling, which allows one to obtain better parameter estimates than the standard Laplace smoothing used in naive Bayes classification. In this paper, we introduce CAN models and apply them to various text classification problems. To demonstrate the language independent and task independent nature of these classifiers, we present experimental results on several text classification problems-authorship attribution, text genre classification, and topic detection-in several languages-Greek, English, Japanese and Chinese. We then systematically study the key factors in the CAN model that can influence the classification performance, and analyze the strengths and weaknesses of the model.

Grapheme-to-phoneme (G2P) models are key components in speech recognition and text-to-speech systems as they describe how words are pronounced. We propose a G2P model based on a Long Short-Term Memory (LSTM) recurrent neural network (RNN). In contrast to traditional joint-sequence based G2P approaches, LSTMs have the flexibility of taking into consideration the full context of graphemes and transform the problem from a series of grapheme-to-phoneme conversions to a word-to-pronunciation conversion. Training joint-sequence based G2P require explicit graphemeto-phoneme alignments which are not straightforward since graphemes and phonemes don't correspond one-to-one. The LSTM based approach forgoes the need for such explicit alignments.We experiment with unidirectional LSTM (ULSTM) with different kinds of output delays and deep bidirectional LSTM (DBLSTM) with a connectionist temporal classification (CTC) layer. The DBLSTM-CTC model achieves a word error rate (WER) of 25.8% on the public CMU dataset for US English. Combining the DBLSTM-CTC model with a joint n-gram model results in a WER of 21.3%, which is a 9% relative improvement compared to the previous best WER of 23.4% from a hybrid system.