This paper proposes a chunking strategy to detect unknown words in Chinese word segmentation. First, a raw sentence is pre-segmented into a sequence of word atoms 1 using a maximum matching algorithm. Then a chunking model is applied to detect unknown words by chunking one or more word atoms together according to the word formation patterns of the word atoms. In this paper, a discriminative Mar...

Every year, traffic accidents are responsible for more than 1,000,000 fatalities worldwide. Understanding the causes of traffic accidents and increasing safety on the road are priority issues for both legislators and the automotive industry. Recently, in Europe, the US and Japan, significant public funding has been allocated for performing large-scale naturalistic driving studies to better unde...

We present a novel method for approximate inference in Bayesian models and regularized risk functionals. It is based on the propagation of mean and variance derived from the Laplace approximation of conditional probabilities in factorizing distributions, much akin to Minka’s Expectation Propagation. In the jointly normal case, it coincides with the latter and belief propagation, whereas in the ...

The power law of practice states that the time to perform a task decreases as a power-law function of the number of times the task has been performed. One possible explanation for this ubiquitous regularity is the chunking theory of learning. It proposes that the acquisition and use of chunks is the basis for these improvements. In this article we describe a first attempt at implementing a lear...

This is to present work on applying Inductive Logic Programming (ILP) to the task of BaseNP chunking. After ILP and NP Chunking are discussed, the experimental setup for using ILP to construct a BaseNP tagger in Prolog is described. Finally, the results are quantitatively as well as qualitatively analysed.

We present a novel method for improving parsing performance, using a stochastic islanddriven chart parser preceded by a chunking process for identifying initial islands. Two different stochastic models have been developed for the island-driven parsing. Some experiments with nominal chunking using broad-coverage grammars derived from the Penn Treebank have been performed with remarkable results.

In this paper, we focus on chunking including contiguous multiword expression recognition, namely super-chunking. In particular, we present different strategies to improve a superchunker based on Conditional Random Fields by combining it with a finite-state symbolic super-chunker driven by lexical and grammatical resources. We display a substantial gain of 7.6 points in terms of overall accuracy.

—The study investigated the effects of chunking and perceptual patterns that guide the drawings of Rey complex figure. Ten adult participants (M age = 22.2 yr., SD = 4.1) reproduced a single stimulus in four drawing modes including delayed recall, tracing, copying, and immediate recall across 10 sessions producing a total of 400 trials. It was hypothesized that the effect of chunking is most ob...

Research based on treebanks is ongoing for many natural language applications. However, the work involved in building a large-scale treebank is laborious and time-consuming. Thus, speeding up the process of building a treebank has become an important task. This paper proposes two versions of probabilistic chunkers to aid the development of a bracketed corpus. The basic version partitions part-o...