Regulating Orthography-Phonology Relationship for English to Thai
            Transliteration

Nguyen, Binh Minh; Ngo, Gia H.; Chen, Nancy F.

doi:10.18653/v1/w16-2712

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the most effective ordering of input and output in machine learning is may not align with human intuition. For example, reversing the order of the input sentence boosted the performance of machine translation [35], while swapping the order of onsets and nuclei in Thai syllables boosted the performance of English-to-Thai transliteration [36]. We adopted the Coda-Nucleus-Onset prediction order in this paper as shown in Section III-C.…”

Section: Prediction Order Of Output Phonemesmentioning

confidence: 99%

Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin Using Recursive Neural Networks

Nguyen

Ngo

Chen

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Logographs (Chinese characters) have recursive structures (i.e. hierarchies of sub-units in logographs) that contain phonological and semantic information, as developmental psychology literature suggests that native speakers leverage on the structures to learn how to read. Exploiting these structures could potentially lead to better embeddings that can benefit many downstream tasks. We propose building hierarchical logograph (character) embeddings from logograph recursive structures using treeLSTM, a recursive neural network. Using recursive neural network imposes a prior on the mapping from logographs to embeddings since the network must read in the sub-units in logographs according to the order specified by the recursive structures. Based on human behavior in language learning and reading, we hypothesize that modeling logographs' structures using recursive neural network should be beneficial. To verify this claim, we consider two tasks (1) predicting logographs' Cantonese pronunciation from logographic structures and (2) language modeling. Empirical results show that the proposed hierarchical embeddings outperform baseline approaches. Diagnostic analysis suggests that hierarchical embeddings constructed using treeLSTM is less sensitive to distractors, thus is more robust, especially on complex logographs.

show abstract

Section: Prediction Order Of Output Phonemesmentioning

confidence: 99%

Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin Using Recursive Neural Networks

Nguyen

Ngo

Chen

2020

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The joint source-channel model has been shown to improve the transliteration performance in various tasks (e.g. [57] [58]) and is used as the baseline for statistical transliteration in this work.…”

Section: B Machine Transliterationmentioning

confidence: 99%

Phonology-Augmented Statistical Framework for Machine Transliteration Using Limited Linguistic Resources

Ngo

Nguyen

Chen

2019

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Transliteration converts words in a source language (e.g., English) into words in a target language (e.g., Vietnamese). This conversion considers the phonological structure of the target language, as the transliterated output needs to be pronounceable in the target language. For example, a word in Vietnamese that begins with a consonant cluster is phonologically invalid and thus would be an incorrect output of a transliteration system. Most statistical transliteration approaches, albeit being widely adopted, do not explicitly model the target language's phonology, which often results in invalid outputs. The problem is compounded by the limited linguistic resources available when converting foreign words to transliterated words in the target language. In this work, we present a phonology-augmented statistical framework suitable for transliteration, especially when only limited linguistic resources are available. We propose the concept of pseudosyllables as structures representing how segments of a foreign word are organized according to the syllables of the target language's phonology. We performed transliteration experiments on Vietnamese and Cantonese. We show that the proposed framework outperforms the statistical baseline by up to 44.68% relative, when there are limited training examples (587 entries).

show abstract

Delineating Indic Transliteration: Developing A Robust Model for Accurate Cross-Script Conversion

Shukla,

Agrawal,

Jain

2024

2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS)

View full text Add to dashboard Cite

Regulating Orthography-Phonology Relationship for English to Thai Transliteration

Cited by 4 publications

References 17 publications

Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin Using Recursive Neural Networks

Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin Using Recursive Neural Networks

Phonology-Augmented Statistical Framework for Machine Transliteration Using Limited Linguistic Resources

Delineating Indic Transliteration: Developing A Robust Model for Accurate Cross-Script Conversion

Contact Info

Product

Resources

About