Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text
In contrast to the older writing system of the 19th century, modern Hawaiian orthography employs characters for long vowels and glottal stops. These extra characters account for about one-third of the phonemes in Hawaiian, so including them makes a big difference to reading comprehension and pronunciation. However, transliterating between older and newer texts is a laborious task when performed manually. We introduce two related methods to help solve this transliteration problem automatically, given that there were not enough data to train an end-to-end deep learning model. One method is implemented, end-to-end, using finite state transducers (FSTs). The other is a hybrid deep learning approach which approximately composes an FST with a recurrent neural network (RNN). We find that the hybrid approach outperforms the end-to-end FST by partitioning the original problem into one part that can be modelled by hand, using an FST, and into another part, which is easily solved by an RNN trained on the available data.
Code (0)
등록된 구현이 없습니다.
Tasks
Reading ComprehensionTransliterationSimilar Papers 제목 키워드 기반
Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text
In contrast to the older writing system of the 19th century, modern Hawaiian orthography employs characters for long vowels and glottal stops. These extra characters account for about one-third of the phonemes in Hawaiia…
Deep LearningReading ComprehensionTransliterationWord Class Based Language Modeling: A Case of Upper Sorbian
In this paper we show how word class based language modeling can support the integration of a small language in modern applications of speech technology. The methods described in this paper can be applied for any languag…
Language ModelingLanguage ModellingComposing Finite State Transducers on GPUs
Weighted finite-state transducers (FSTs) are frequently used in language processing to handle tasks such as part-of-speech tagging and speech recognition. There has been previous work using multiple CPU cores to accelera…
CPUGPUPart-Of-Speech Taggingspeech-recognition+1Modeling Reduplication with 2-way Finite-State Transducers
This article describes a novel approach to the computational modeling of reduplication. Reduplication is a well-studied linguistic phenomenon. However, it is often treated as a stumbling block within finite-state treatme…
A self-adaptive genetic algorithm for the flying sidekick travelling salesman problem
This paper presents a novel approach to solving the Flying Sidekick Travelling Salesman Problem (FSTSP) using a state-of-the-art self-adaptive genetic algorithm. The Flying Sidekick Travelling Salesman Problem is a combi…