More than a century after the first linguistic definition of the notion of morpheme by Baudoin de Courtenay (1895) and Sweet (1876), an ever-lasting debate – which I shall refer here as the “Morpheme or Lexeme” (M or L) debate – on the nature of linguistic bricks is still going on. Since a by-product of this debate is terminological confusion in the use of the four notions of morpheme, lexeme, ...

This paper presents a statistical/symbolic hybrid morphological analysis, called V-morph, for large scale speech and natural language integration for Korean. In the V-morph approach, statistical Viterbi-based lexical decoding and symbolic morphological modeling are integrated together on top of connectionist phoneme recognition engine. Linguistic characteristics of Korean are appropriately cons...

The goal of Morpho Challenge 2009 was to evaluate unsupervised algorithms that provide morpheme analyses for words in different languages and in various practical applications. Morpheme analysis is particularly useful in speech recognition, information retrieval and machine translation for morphologically rich languages where the amount of different word forms is very large. The evaluations con...

Parsing texts into universal dependencies (UD) in realistic scenarios requires infrastructure for morphological analysis and disambiguation (MA&D) of typologically different languages as a first tier. MA&D is particularly challenging in morphologically rich languages (MRLs), where the ambiguous space-delimited tokens ought to be disambiguated with respect to their constituent morphemes. Here we...

This paper is concerned with the specifications and the implementation of a particular concept of word-based lexicon to be used for large natural language processing systems such as machine translation systems, and compares it with the morpheme-based conception of the lexicon traditionally assumed in computational linguistics. It will be argued that, although less concise, a relational word-bas...

Hansson (2001), Rose & Walker (2004), and Walker (2000a, 2000b) have recently proposed that long-distance consonant assimilation is accomplished via segmental correspondence rather than autosegmental linking. The phonology of the feature [anterior] in Chumash supports this idea: linking of the feature [anterior] is forbidden across morpheme boundaries, but long-distance [anterior] harmony is al...

This study focuses on the linear order of yes/no-question particle mI in Turkish. The distribution is intriguing, since it must reverse with immediately adjacent morpheme unless follows verb root. To account for such a distribution, attributed to interaction between two post-syntactic concatenation statements under adjacency (Local Dislocation Embick 2007). Assuming that question spells out C[+...

Morpho Challenge is an annual evaluation campaign for unsupervised morpheme analysis. In morpheme analysis, words are segmented into smaller meaningful units. This is an essential part in processing complex word forms in many large-scale natural language processing applications, such as speech recognition, information retrieval, and machine translation. The discovery of morphemes is particularl...

Morphemes often behave differently phonologically in ways that cannot be explained purely phonologically: one morpheme undergoes or triggers a process while another morpheme fails to undergo or trigger that process, even though the two are in all relevant respects indistinguishable. Piro syncope (Matteson 1965, Kisseberth 1970, Lin 1997) provides an example of such morpheme-specific phonology. ...