Automatic Generation of English Respellings

Proceedings of NAACL-HLT 2013, pages 634–643, Atlanta, Georgia, 9–14 June 2013. c⃝2013 Association for Computational Linguistics Automatic Generation of English Respellings Bradley Hauer and Grzegorz Kondrak Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G 2E8 {bmhauer,gkondrak}@ualberta.ca Abstract A respelling is an alternative spelling of a word in the same writing system, intended to clarify pronunciation. We introduce the task of automatic generation of a respelling from the word’s phonemic representation. Our ap- proach combines machine learning with lin- guistic constraints and electronic resources. We evaluate our system both intrinsically through a human judgment experiment, and extrinsically by passing its output to a letter- to-phoneme converter. The results show that the respellings generated by our system are better on average than those found on the Web, and approach the quality of respellings de- signed by an expert. 1 Introduction Respellings are a widely employed method of con- veying the pronunciation of English and foreign words, both in print and on the Web. For example, Huatulco, the name of a Mexican resort, is respelled as ‘wah-tool-koh’ in a travel guide (Noble, 2012). The advantage of using respellings lies in removing the need for a separately defined phonetic transcrip- tion system. Since they contain only the letters of the Latin alphabet, their phonetic interpretation re- lies exclusively on orthographic intuitions of read- ers. For this reason, respellings are widely used in travel phrase books, medical compendia, and drug name pronunciation guides, among others. Despite their utility, good respellings are not easy to create. Respellings found on the Web often con- tain errors or ambiguities. For example, Henoch- Schoenlein purpura, a skin disease, is respelled both as ‘heh-nok shoon-line purr-puh-ruh’ and ‘hen-awk sher-line purr-purr-ah’. Does ‘heh’ rhyme with eh [e] or with Nineveh [@], or is it the same vowel as in hen [E]? Clearly, if both respellings refer to the same pronunciation, at least one of them must be wrong. In addition, converting the pronunciation of a foreign name to English phonemes is in itself a non-trivial task. In this paper, we focus on the task of generating respellings from the intended pronunciation given as a sequence of phonemes. We develop a stand-alone system that combines linguistic knowledge and re- sources with machine learning models trained on data mined from the Web and electronic dictionar- ies. One of our ultimate objectives is to aid writ- ers by evaluating their respellings, improving them, or generating new candidates. Accordingly, we en- deavour to maintain the generation and the evalua- tion stages as separate modules in our system. The evaluation of respellings is a challenging problem. Since English spelling conventions are no- toriously inconsistent, there is no algorithm for ac- curately predicting the pronunciation of an out-of- vocabulary word. The current state-of-the-art letter- to-phoneme (L2P) converters are typically reported with 10-30% error rates on dictionary words (Bisani and Ney, 2008). On the other hand, human read- ers often disagree on the details of the pronunciation implied by a respelling. In this paper, we …

Content truncated to 500 words