Data-Driven Syllabification for Middle Dutch

TY - JOUR

T1 - Data-Driven Syllabification for Middle Dutch

AU - Haverals, Wouter

AU - Karsdorp, F.B.

AU - Kestemont, Mike

PY - 2019/11/4

Y1 - 2019/11/4

N2 - The task of automatically separating Middle Dutch words into syllables is a challenging one. A first method was presented by Bouma and Hermans (2012), who combined a rule-based finite-state component with data-driven error correction. Achieving an average word accuracy of 96.5%, their system surely is a satisfactory one, although it leaves room for improvement. Generally speaking, rule-based methods are less attractive for dealing with a medieval language like Middle Dutch, where not only each dialect has its own spelling preferences, but where there is also much idiosyncratic variation among scribes. This paper presents a different method for the task of automatically syllabifying Middle Dutch words, which does not rely on a set of pre-defined linguistic information. Using a Recurrent Neural Network (RNN) with Long-Short-Term Memory cells (LSTM), we obtain a system which outperforms the rule-based method both in robustness and in effort.

AB - The task of automatically separating Middle Dutch words into syllables is a challenging one. A first method was presented by Bouma and Hermans (2012), who combined a rule-based finite-state component with data-driven error correction. Achieving an average word accuracy of 96.5%, their system surely is a satisfactory one, although it leaves room for improvement. Generally speaking, rule-based methods are less attractive for dealing with a medieval language like Middle Dutch, where not only each dialect has its own spelling preferences, but where there is also much idiosyncratic variation among scribes. This paper presents a different method for the task of automatically syllabifying Middle Dutch words, which does not rely on a set of pre-defined linguistic information. Using a Recurrent Neural Network (RNN) with Long-Short-Term Memory cells (LSTM), we obtain a system which outperforms the rule-based method both in robustness and in effort.

U2 - https://doi.org/10.16995/dm.83

DO - https://doi.org/10.16995/dm.83

M3 - Article

SN - 1715-0736

VL - 1

SP - 1

EP - 23

JO - Digital Medievalist

JF - Digital Medievalist

IS - 2

ER -