We present two connectionist architectures for chunking of symbolic rewrite rules. One uses backpropagation learning, the other competitive learning. Although they were developed for chunking the same sorts of rules, the two differ in their representational abilities and learning behaviors.

Sequential organization is central to much of human intelligent behavior ranging from everyday skills such as lacing shoes to using a computer. It is well known that such sequential skills involve chaining a number of primitive actions together.. A robust representation of skills can be formed by chunking together several elements of a sequence. We demonstrate, using a 2x6 finger movement task,...

In data deduplication systems, chunking has a significant impact on the ratio and throughput. Existing Content-Defined Chunking (CDC) approaches exploit sliding window to calculate rolling hashes of input stream byte-by-byte, then determine chunk cut-points if hash satisfies given cut-condition...

This paper describes a complete syntactic analysis system based on multi-level chunking. On the basis of the correct sequences of Chinese words provided by CLP2010, the system firstly has a Part-ofspeech (POS) tagging with Conditional Random Fields (CRFs), and then does the base chunking and complex chunking with Maximum Entropy (ME), and finally generates a complete syntactic analysis tree. Th...

We present a method of chunking in Korean texts using conditional random fields (CRFs), a recently introduced probabilistic model for labeling and segmenting sequence of data. In agglutinative languages such as Korean and Japanese, a rule-based chunking method is predominantly used for its simplicity and efficiency. A hybrid of a rule-based and machine learning method was also proposed to handl...

Dividing sentences in chunks of words is a useful preprocessing step for parsing, information extraction and information retrieval. (Ramshaw and Marcus, 1995) have introduced a "convenient" data representation for chunking by converting it to a tagging task. In this paper we will examine seven di erent data representations for the problem of recognizing noun phrase chunks. We will show that the...

New methods for the assessment of drawing strategies are examined that focus on analysis perceptual chunking. The demonstrated with four diverse participants as they copied a line-graph and bar-chart. Video recordings transcriptions were analysed stroke by stroke. Diverse global used line graph whereas all similar approach bar-chart, but local differences. Performance fluency varied substantial...

Phrase chunking remains an important natural language processing (NLP) technique for intermediate syntactic processing. This paper describes the development of protocols, annotated phrase chunking data sets and automatic phrase chunkers for ten South African languages. Various problems with adapting the existing annotation protocols of English are discussed as well as an overview of the annotat...

This study evaluates the chunking hypothesis in the context of two-element, reciprocal aiming movements. The chunking hypothesis assumes that movements toward small targets require a movement stop while movements toward large targets require a movement reuersal. According to the chunking hypothesis, a movement reversal allows for a functional coupling or linkage between the forward and backward...

We present new statistical models for jointly labeling multiple sequences and apply them to the combined task of partof-speech tagging and noun phrase chunking. The model is based on the Factorial Hidden Markov Model (FHMM) with distributed hidden states representing partof-speech and noun phrase sequences. We demonstrate that this joint labeling approach, by enabling information sharing betwee...