Parsing Morphologically Complex Words
نویسندگان
چکیده
We present a method for probabilistic parsing of German words. Our approach uses a morphological analyzer based on weighted finitestate transducers to segment words into lexical units and a probabilistic context free grammar trained on a manually created set of word trees for the parsing step.
منابع مشابه
Changing morphological structures: The effect of sentence context on the interpretation of structurally ambiguous English trimorphemic words
Morphological parsing has often been studied with words in isolation. In this study we used sentence context to investigate how structural analyses of morphologically complex words are affected by the semantic content of their carrier sentences. Our main stimuli were trimorphemic ambiguous words such as unlockable (meaning either ‘‘not able to be locked’’ or ‘‘able to be unlocked’’). We treat t...
متن کاملImproved Transition-based Parsing by Modeling Characters instead of Words with LSTMs
We present extensions to a continuousstate dependency parsing method that makes it applicable to morphologically rich languages. Starting with a highperformance transition-based parser that uses long short-term memory (LSTM) recurrent neural networks to learn representations of the parser state, we replace lookup based word representations with representations constructed based on the orthograp...
متن کاملVerbs are where all the action lies: Experiences of Shallow Parsing of a Morphologically Rich Language
Verb suffixes and verb complexes of morphologically rich languages carry a lot of information. We show that this information if harnessed for the task of shallow parsing can lead to dramatic improvements in accuracy for a morphologically rich languageMarathi1. The crux of the approach is to use a powerful morphological analyzer backed by a high coverage lexicon to generate rich features for a C...
متن کاملCompound words and structure in the lexicon
The structure of lexical entries and the status of lexical decomposition remain controversial. In the psycholinguistic literature, one aspect of this debate concerns the psychological reality of the morphological complexity difference between compound words (teacup) and single words (crescent). The present study investigates morphological decomposition in compound words using visual lexical dec...
متن کاملThe AI-KU System at the SPMRL 2013 Shared Task : Unsupervised Features for Dependency Parsing
We propose the use of the word categories and embeddings induced from raw text as auxiliary features in dependency parsing. To induce word features, we make use of contextual, morphologic and orthographic properties of the words. To exploit the contextual information, we make use of substitute words, the most likely substitutes for target words, generated by using a statistical language model. ...
متن کامل