GeLexi project: Sentence Parsing Based on a GEnerative LEXIcon
نویسندگان
چکیده
The principal aim of our research team, called GeLexi, is to legitimate a new sort of generative grammar via verifying its computational implementability. This grammar is more radically “lexicalist” than any earlier one: no phrase structure trees are generated, but word order is accounted for by means of ranked parameters. Another novelty is the extension of “total lexicalism” to morphology: lexical items are assigned not to words but to morphemes. Our parser, in accordance with the basic task of every generative grammar, decides whether a sentence is grammatical, and if it is, then provides a morphophonological analysis, a compilation of grammatical relations, and two kinds of semantic representations. At the end we show some examples to demonstrate our procedures, among them a sentence containing the conjunction és ‘and’, which is our latest development.
منابع مشابه
The GeLexi MT Project
Our double Machine (-Aided) Translation project to be demonstrated here (sections 3-4) is based on the parsing project [5-9, 12] of our Pécs theoretical and computational linguistics research team, called GeLexi (‘Generative LEXIcon’), whose (knowledge-based) parsers (section 2) rely on “totally lexicalist” [21, 2, 4, 7] representative mini-grammars of English and the (morphologically very rich...
متن کاملFeature extraction in opinion mining through Persian reviews
Opinion mining deals with an analysis of user reviews for extracting their opinions, sentiments and demands in a specific area, which can play an important role in making major decisions in such area. In general, opinion mining extracts user reviews at three levels of document, sentence and feature. Opinion mining at the feature level is taken into consideration more than the other two levels d...
متن کاملA Single Generative Model for Joint Morphological Segmentation and Syntactic Parsing
Morphological processes in Semitic languages deliver space-delimited words which introduce multiple, distinct, syntactic units into the structure of the input sentence. These words are in turn highly ambiguous, breaking the assumption underlying most parsers that the yield of a tree for a given sentence is known in advance. Here we propose a single joint model for performing both morphological ...
متن کاملPosterior Decoding for Generative Constituent-Context Grammar Induction
In this project, we study the problem of natural language grammar induction from a database of sentence part-of-speech (POS) tags. We then present an implementation of the EM-based generative constituent-context model by Klein and Manning. We also present two posterior decoding approaches to be used in conjunction with the constituent-context model and evaluate their performance against regular...
متن کاملData Analysis Project: A Probabilistic Generative Grammar for Semantic Parsing
We present a generative model of natural language sentences and demonstrate its application to semantic parsing. In the generative process, a logical form sampled from a prior, and conditioned on this logical form, a grammar probabilistically generates the output sentence. Grammar induction using MCMC is applied to learn the grammar given a set of labeled sentences with corresponding logical fo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Acta Cybern.
دوره 16 شماره
صفحات -
تاریخ انتشار 2004