We propose sentence chunking as a way to reduce the time and memory costs of realization of long sentences. During chunking we divide the semantic representation of a sentence into smaller components which can be processed and recombined without loss of information. Our meaning representation of choice is Dependency Minimal Recursion Semantics (DMRS). We show that realizing chunks of a sentence...

This paper proposes an approach of processing Japanese compound functional expressions by identifying them and analyzing their dependency relations through a machine learning technique. First, we formalize the task of identifying Japanese compound functional expressions in a text as a machine learning based chunking problem. Next, against the results of identifying compound functional expressio...

The Low Bandwidth Network File System (LBFS) was designed to minimize the bandwidth requirements for running interactive applications and accessing remote files over bandwidthconstrained network links. We present a simplified implementation of the original LBFS in which we concentrate on the analysis of the chunking algorithm used to exploit similarities across files. We propose an optimized ve...

Text-to-speech synthesis can be an empowering communication tool in the hands of the print-disabled or augmentative and alternative communication user. In an effort to improve the naturalness of synthesised speech – and thus enhance the communication experience – we apply the natural language processing tasks of part-of-speech tagging and chunking to the text in the synthesis process. We cover ...

We introduce a character-based chunking for unknown word identification in Japanese text. A major advantage of our method is an ability to detect low frequency unknown words of unrestricted character type patterns. The method is built upon SVM-based chunking, by use of character n-gram and surrounding context of n-best word segmentation candidates from statistical morphological analysis as feat...

We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking. Our segment-level CRF can consider higher-order label dependencies compared with conventional word-level CRF. Since it is difficult to consider all possible variable length segments, our method uses s...