Yi-Cheng Pan

Learn More
Boulder, Colorado, June 2009. c ©2009 Association for Computational Linguistics Automatic Chinese Abbreviation Generation Using Conditional Random Field Dong Yang, Yi-cheng Pan, and Sadaoki Furui Department of Computer Science Tokyo Institute of Technology Tokyo 152-8552 Japan {raymond,thomas,furui}@furui.cs.titech.ac.jp Abstract This paper presents a new(More)
Position Specific Posterior Lattices (PSPL) have been recently proposed as very powerful, compact structures for indexing speech. In this paper, we take PSPL one step further to Subword-based Position Specific Posterior Lattices (S-PSPL). As with PSPL, we include posterior probabilities and proximity information, but we base this information on subword(More)
This paper describes our system for “NEWS 2009 Machine Transliteration Shared Task” (NEWS 2009). We only participated in the standard run, which is a direct orthographical mapping (DOP) between two languages without using any intermediate phonemic mapping. We propose a new two-step conditional random field (CRF) model for DOP machine transliteration, in(More)
Lattice-based speech indexing approaches are attractive for the combination of short spoken segments, short queries, and low automatic speech recognition (ASR) accuracies, as lattices provide recognition alternatives and therefore tend to compensate for recognition errors. Position-specific posterior lattices (PSPLs) and confusion networks (CNs), two of the(More)
In this paper we analytically compare the two widely accepted approaches of spoken document indexing, Position Specific Posterior Lattices (PSPL) and Confusion Network (CN), in terms of retrieval accuracy and index size. The fundamental distinctions between these two approaches in terms of construction units, posterior probabilities, number of clusters,(More)
We present a contextual spoken language understanding (contextual SLU) method using Recurrent Neural Networks (RNNs). Previous work has shown that context information, specifically the previously estimated domain assignment, is helpful for domain identification. We further show that other context information such as the previously estimated intent and slot(More)
Interaction with users is a powerful strategy that potentially yields better information retrieval for all types of media, including text, images, and videos. While spoken document retrieval (SDR) is a crucial technology for multimedia access in the network era, it is also more challenging than text information retrieval because of the inevitable(More)
In this paper, we propose two efficient approaches for Named Entity recognition (NER) from spoken documents. The first approach used a very efficient data structure, the PAT trees, to extract global evidences from the whole spoken documents, to be used with the well-known local (internal and external) evidences popularly used by conventional approaches. The(More)
This paper presents a new approach of latent semantic retrieval of spoken documents over Position Specific Posterior Lattices(PSPL). This approach performs concept matching instead of literal term matching during retrieval based on the Probabilistic Latent Semantic Analysis (PLSA), so as to solve the problem of term mismatch between the query and the(More)
Word-based consensus networks have been verified to be very useful in minimizing word error rates (WER) for large vocabulary continuous speech recognition for western languages. By considering the special structure of Chinese language, this paper points out that character-based rather then wordbased consensus networks should work better for Chinese(More)