Grapheme-to-Phoneme Conversion using Multiple Unbounded Overlapping Chunks

TL;DR

This paper extends data-driven algorithms for grapheme-to-phoneme conversion, improving their performance and proposing a more general framework, but highlights limitations in modeling lexical neighborhoods and analogical reading processes.

Contribution

The paper introduces an improved extension of the Dedina and Nusbaum algorithm for better G2P conversion and a generalized framework for analogy-based models.

Findings

Extended algorithm outperforms original in realistic tests

Proposed framework allows for future useful extensions

Models still lack proper lexical neighborhood representation

Abstract

We present in this paper an original extension of two data-driven algorithms for the transcription of a sequence of graphemes into the corresponding sequence of phonemes. In particular, our approach generalizes the algorithm originally proposed by Dedina and Nusbaum (D&N) (1991), which had originally been promoted as a model of the human ability to pronounce unknown words by analogy to familiar lexical items. We will show that DN's algorithm performs comparatively poorly when evaluated on a realistic test set, and that our extension allows us to improve substantially the performance of the analogy-based model. We will also suggest that both algorithms can be reformulated in a much more general framework, which allows us to anticipate other useful extensions. However, considering the inability to define in these models important notions like lexical neighborhood, we conclude that both approaches fail to offer a proper model of the analogical processes involved in reading aloud.