In this paper I develop an LFG analysis of two noun phrase types in Hungarian that can be referred to as elliptical. In one of them, Type (A), the understood noun head is entirely missing from the construction and formally the head function is performed by the head of the final modifying constituent in the phrase. The major task here is to capture, in a lexicalist framework, the formal head pro...

A character corresponds roughly to a morpheme in Chinese, and it usually takes on multiple meanings. In this paper, we aimed at capturing the multiple meanings of a Chinese morpheme across polymorphemic words in a growing semantic micro-space. Using Latent Semantic Analysis (LSA), we created several nested LSA semantic micro-spaces of increasing size. The term-document matrix of the smallest se...

Morph-based spoken document retrieval uses morpheme-like subword units for both language modeling and as

After the release of the open sou rce softw are implementation of M orfessor alg orithm, a series of several open evalu ations has b een org aniz ed for u nsu pervised morpheme analy sis and morpheme-b ased speech recog nition and information retrieval. T he u nsu pervised morpheme analy sis is a particu larly attractive approach for speech and lang u ag e technolog y for the morpholog ically c...

In this article we evaluate our stochastic morphosyntactic language model (SMLM) on a Hungarian newspaper dictation task that requires modeling over 1 million different word forms. The proposed method is based on the use of morphemes as the basic recognition units and the combination of a morpheme gram model and a morphosyntactic language model. The architecture of the recognition system is bas...

The central notion of structural linguistics is that of contrast or opposition: The linguistic value and role of a unit cannot be reduced to its physical substance, but is crucially determined by the network of relations that it enters into with other units of a similar kind: phoneme to phoneme, morpheme to morpheme, etc. A mid front vowel /e/ in a five-vowel system is something quite different...

In this work, Morfessor, a morpheme segmentation model and algorithm developed by the organizers of the Morpho Challenge, is outlined and references are made to earlier work. Although Morfessor does not take part in the official Challenge competition, we report experimental results for the morpheme segmentation of English, Finnish and Turkish words. The obtained results are very good. Morfessor...

This work presents an algorithm for the unsupervised learning, or induction, of a simple morphology of a natural language. A probabilistic maximum a posteriori model is utilized, which builds hierarchical representations for a set of morphs, which are morpheme-like units discovered from unannotated text corpora. The induced morph lexicon stores parameters related to both the “meaning” and “form...

We built a pipeline to normalize Quechua texts through morphological analysis and disambiguation. Word forms are analyzed by a set of cascaded finite state transducers which split the words and rewrite the morphemes to a normalized form. However, some of these morphemes, or rather morpheme combinations, are ambiguous, which may affect the normalization. For this reason, we disambiguate the morp...