We are pleased to present the Proceedings of the Eighth Meeting of the ACL Special Interest Group on Computational Phonology (SIGPHON) to be held on June 8 in New York City. This is the first time that the SIGPHON workshop has been collocated with the HLT-NAACL conference. Previous meetings were held in conjunction with ACL and COLING in Las Cruces (1994), Santa Cruz (1996), Madrid (1997), Quebec (1998), Luxembourg (2000), Philadelphia (2002), and Barcelona (2004).
One of the missions of SIGPHON is to encourage interaction between work in computational linguistics and work in theoretical phonology, in the hope that both fields will profit from the interaction. In addition, SIGPHON continues to promote work in computational morphology, seeking to fill in for the absence of an analogous SIGMORPH group. Our recent meetings have been successful in both regards, and we anticipate this will continue in 2006. Many mainstream phonologists are employing computational tools and models that are of considerable interest to computational linguists more generally, and our intention is that this workshop should be a forum to bring this work to the attention of a wider range of computational linguists.
Proceeding Downloads
A combined phonetic-phonological approach to estimating cross-language phoneme similarity in an ASR environment
This paper presents a fully automated linguistic approach to measuring distance between phonemes across languages. In this approach, a phoneme is represented by a feature matrix where feature categories are fixed, hierarchically related and binary-...
Improving syllabification models with phonotactic knowledge
We report on a series of experiments with probabilistic context-free grammars predicting English and German syllable structure. The treebank-trained grammars are evaluated on a syllabification task. The grammar used by Müller (2002) serves as point of ...
Learning quantity insensitive stress systems via local inference
This paper presents an unsupervised batch learner for the quantity-insensitive stress systems described in Gordon (2002). Unlike previous stress learning models, the learner presented here is neither cue based (Dresher and Kaye, 1990), nor reliant on a ...
Universal constraint rankings result from learning and evolution: invited talk
Optimality Theory has met with a bad press in the more emergentist (e.g. computational) literature for its reliance on innate constraints and even on innate constraint rankings (positional faithfulness, licensing by cue). In this talk I will show with ...
Exploring variant definitions of pointer length in MDL
Within the information-theoretical framework described by (Rissanen, 1989; de Marcken, 1996; Goldsmith, 2001), pointers are used to avoid repetition of phonological material. Work with which we are familiar has assumed that there is only one way in ...
Improved morpho-phonological sequence processing with constraint satisfaction inference
In performing morpho-phonological sequence processing tasks, such as letter-phoneme conversion or morphological analysis, it is typically not enough to base the output sequence on local decisions that map local-context input windows to single output ...
Richness of the base and probabilistic unsupervised learning in optimality theory
This paper proposes an unsupervised learning algorithm for Optimality Theoretic grammars, which learns a complete constraint ranking and a lexicon given only unstructured surface forms and morphological relations. The learning algorithm, which is based ...
Morphology induction from limited noisy data using approximate string matching
For a language with limited resources, a dictionary may be one of the few available electronic resources. To make effective use of the dictionary for translation, however, users must be able to access it using the root form of morphologically deformed ...
Learning probabilistic paradigms for morphology in a latent class model
This paper introduces the probabilistic paradigm, a probabilistic, declarative model of morphological structure. We describe an algorithm that recursively applies Latent Dirichlet Allocation with an orthogonality constraint to discover morphological ...
A naive theory of affixation and an algorithm for extraction
We present a novel approach to the unsupervised detection of affixes, that is, to extract a set of salient prefixes and suffixes from an unlabeled corpus of a language. The underlying theory makes no assumptions on whether the language uses a lot of ...