Many Latin inflectional endings share material constituting less than a whole morpheme. Conventional linguistic analysis must either ignore the shared material (treating it as historical relics) or make it into morphemes through abstract morphophonemics, poorly motivated in Latin. The shared material contributes to economy of representation when the inflectional system is stored as a transition...

We describe several experiments in computational modeling that require a system to infer the existence of inflectional classes, which are morphological classes that play a role in neither syntax nor semantics. A feed-forward connectionist model will utilize patterns of activation (rather than units) in its hidden layer to encode such abstract morphological patterns. We compare this with discuss...

Commonly used gralm~mrs which describe i~turai lan~uages /ex. ATN, Metamorphosis Grammars/ can be hardly applied in describing higly inflectional languages. So I propose a grammar called the grammar with natural context which takes into consideration properties of higly inflectional languages /ex. Polish / as well as structural languages /ex. English/. I introduce its normal form.

We describe a domain-specific method of adapting conditional random fields (CRFs) to morphosyntactic tagging of highly-inflectional languages. The solution involves extending CRFs with additional, position-wise restrictions on the output domain, which are used to impose consistency between the modeled label sequences and morphosyntactic analysis results both at the level of decoding and, more i...

In reading research, morphological processing and monomorphemic word identification have generally been treated separately. We describe a computational model that brings both kinds of reading together within a single framework. This model assumes that word knowledge—the orthography, phonology, and meaning of words—accumulates with experiences with individual words and that this knowledge is ref...

Encapsulation of morphology and syntax as separate domains of representation and processing causes many problems at the interfaces, such as rebracketing, reordering, and tampering with the representations of the information domains. These recomputations usually arise due to mismatches with the semantic bracketing. We propose a lexicalist framework based on Combinatory Categorial Grammar (CCG) t...

Grammars that expect words from the lexicon may be at odds with the transparent projection of syntactic and semantic scope relations of smaller units. We propose a morphosyntactic framework based on Combinatory Categorial Grammar that provides flexible constituency, flexible category consistency, and lexical projection of morphosyntactic properties and attachment to grammar in order to establis...