We use a Dynamic Bayesian Network (dbn) to represent compactly a variety of sublexical and contextual features relevant to Part-ofSpeech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a benchmark corpus). We explore the effect of eliminating redundancy and radically reducing the size of feature vocabularies. We find that a small but li...

Dogon languages lexicalize action verbs with obligatory reference to manner and/or process. This contrasts with English and “Standard Average European,” which (in neutral contexts) profile result and/or function. Many common English verbs like carry and eat correspond to sets of Dogon verbs with senses like ‘carry on back’ and ‘munch’. The pattern cuts across many semantic domains and constitut...

The centralization of the low upgliding diphthong (typically called Canadian Raising, here just Raising), is frequently cited as an example of phonological opacity. Conditioned by a following voiceless segment, Raising continues to apply when an underlying unstressed /t/ is flapped on the surface. Dialects which have both Raising and Flapping, then, maintain the distinction between "writer" and...

Significant work in both lexicalized and unlexicalized parsing has been done in the past ten years. F1 measures of accuracy of over 90% have been achieved (Bikel, 2005), and linguistic notions of lexical dependencies and using head words have been harnessed to create significant improvements in probabilistic CFG note, however, that many of the techniques for improving lexicalized parsing create...

This paper explores the role of lexicalization and pruning of grammars for base noun phrase identification. We modify our original framework (Cardie & Pierce 1998) to extract lexicalized treebank grammars that assign a score to each potential noun phrase based upon both the part-of-speech tag sequence and the word sequence of the phrase. We evaluate the modified framework on the “simple” and “c...

The objective of this study is to investigate the types code-mixing found in Sri Mulyani Indrawati’s introductory lecture entitled Kuliah Pengantar Ekonomi FEB UI 2019- Indrawati, S. E., M.Sc., Ph. D (Introduction Economics), which was delivered Universitas Indonesia 2019. For analysis, writers used theory proposed by Muysken (2000). implemented qualitative approach complete study. findings res...

One of the claimed benefits of Tree Adjoining Grammars is that they have an extended domain of locality (EDOL). We consider how this can be exploited to limit the need for feature structure unification during parsing. We compare two wide-coverage lexicalized grammars of English, LEXSYS and XTAG, finding that the two grammars exploit EDOL in different ways. 1 Introduction One of the most basic p...

To understand how daily usages can shape the gradual changes of both hěn, a prototypical intensifier in Mandarin Chinese, and the construction hěn X, the study aims to investigate the syntactic and semantic behaviors of hěn X constructions in spoken corpora. The conversational data from the NCCU Corpus of Spoken Chinese and a Taiwan Public Television show Bring Up Parents are extracted and anal...

In this paper we propose a solution for the representation of a wide range of multiword expressions1 (lexicalized or not) in the Basque WordNet. We first argue in favor of including non-lexicalized multiword expressions, and propose very simple criteria based on existing dictionaries to mark those that are lexicalized from those that are not. We then motivate and propose a representation based ...