Search

Syntactic parsing is a key task in natural language processing. This task has been dominated by symbolic, grammar-based parsers. Neural networks, with their distributed representations, are challenging these methods. In this article we show that existing symbolic parsing algorithms can cross the border and be entirely formulated over distributed representations. To this end we introduce a version of the traditional Cocke-Younger-Kasami (CYK) algorithm, called D-CYK, which is entirely defined over distributed representations. Our D-CYK uses matrix multiplication on real number matrices of size independent of the length of the input string. These operations are compatible with traditional neural networks. Experiments show that our D-CYK approximates the original CYK algorithm. By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layers of CYK-informed neural networks., Comment: The algorithm has been greatly improved. Experiments have been redesigned

We present a novel technique to remove spurious ambiguity from transition systems for dependency parsing. Our technique chooses a canonical sequence of transition operations (computation) for a given dependency tree. Our technique can be applied to a large class of bottom-up transition systems, including for instance Nivre (2004) and Attardi (2006).

This paper presents work in progress for the development of IFrameNet, a large-scale, computationally oriented, lexical resource based on Fillmore’s frame semantics for Italian. For the development of IFrameNet linguistic analysis, corpusprocessing and machine learning techniques are combined in order to support the semi-automatic development and annotation of the resource. Questo articolo presenta un work in progress per lo sviluppo di IFrameNet, una risorsa lessicale ad ampia copertura, computazionalmente orientata, basata sulle teorie di Semantica dei Frame proposte da Fillmore. Per lo sviluppo di IFrameNet sono combinate analisi linguistica, corpusprocessing e tecniche di machine learning al fine di semi-automatizzare lo sviluppo della risorsa e il processo di annotazione.

In this paper, we present a preliminary study on the style of headlines in order to evaluate the correlation between linguistic features and newsworthiness. Our hypothesis is that each particular linguistic form or stylistic variation can be motivated by the purpose of encoding a certain newsworthiness value. To discover the correlations between newsworthiness and linguistic features, we perform an analysis on the basis of characteristics considered indicative of a shared communicative function and of discriminating factors for headlines. Questo contributo descrive uno studio preliminare sullo stile dei titoli nelle notizie, al fine di valutare la correlazione tra gli aspetti linguistici e il valore delle notizie. La nostra ipotesi è che ogni particolare forma linguistica o variazione stilistica possa essere motivata dall’obiettivo di codificare un certo valore di notiziabilità. Al fine di analizzare la correlazione tra il valore delle notizie e gli aspetti linguistici, effettuiamo un‘analisi sulla base delle caratteristiche considerate indicative di una funzione comunicativa condivisa e di fattori discriminanti per i titoli.