[Paper Review] Syntax and Semantics of Italian Poetry in the First Half of the 20th Century

Rodolfo Delmonte|arXiv (Cornell University)|Feb 11, 2018

Natural Language Processing Techniques10 references3 citations

TL;DR

This paper analyzes noncanonical syntactic and semantic structures in Italian poetry from the first half of the 20th century using Lexical Functional Grammar (LFG) to link syntactic discontinuities with informational and psycholinguistic complexity. It compares statistical parsers with a symbolic rule-based system (Getarun), demonstrating that the latter significantly outperforms the former in parsing and analyzing poetic structures due to its ability to handle discontinuous elements and perform full semantic and pragmatic analysis.

ABSTRACT

In this paper we study, analyse and comment rhetorical figures present in some of most interesting poetry of the first half of the twentieth century. These figures are at first traced back to some famous poet of the past and then compared to classical Latin prose. Linguistic theory is then called in to show how they can be represented in syntactic structures and classified as noncanonical structures, by positioning discontinuous or displaced linguistic elements in Spec XP projections at various levels of constituency. Then we introduce LFG (Lexical Functional Grammar) as the theory that allows us to connect syntactic noncanonical structures with informational structure and psycholinguistic theories for complexity evaluation. We end up with two computational linguistics experiments and then evaluate the results. The first one uses best online parsers of Italian to parse poetic structures; the second one uses Getarun, the system created at Ca Foscari Computational Linguistics Laboratory. As will be shown, the first approach is unable to cope with these structures due to the use of only statistical probabilistic information. On the contrary, the second one, being a symbolic rule based system, is by far superior and allows also to complete both semantic an pragmatic analysis.

Motivation & Objective

• To investigate rhetorical and syntactic noncanonical structures in Italian poetry from the first half of the 20th century.
• To compare the performance of statistical parsers versus symbolic rule-based systems in analyzing complex poetic syntax.
• To apply Lexical Functional Grammar (LFG) to model the connection between syntactic discontinuities and informational structure in poetry.
• To evaluate the effectiveness of computational systems in capturing semantic and pragmatic complexity in poetic texts.
• To demonstrate the limitations of probabilistic parsing in handling discontinuous, noncanonical structures common in modernist poetry.

Proposed method

• Tracing rhetorical figures in Italian poetry to classical Latin prose to identify syntactic deviations.
• Representing noncanonical structures as discontinuous or displaced elements in Spec XP projections across syntactic levels.
• Employing Lexical Functional Grammar (LFG) to link syntactic structures with informational and psycholinguistic complexity.
• Conducting two computational experiments: one using state-of-the-art statistical Italian parsers, and another using the symbolic Getarun system from Ca' Foscari Computational Linguistics Laboratory.
• Evaluating both systems based on syntactic parsing accuracy and the ability to perform semantic and pragmatic analysis.
• Using LFG to formalize the relationship between syntactic discontinuity and informational structure in poetic texts.

Experimental results

Research questions

• RQ1 How can noncanonical syntactic structures in early 20th-century Italian poetry be formally represented using syntactic theory?
• RQ2 To what extent do statistical parsers fail to handle discontinuous or displaced elements in poetic syntax?
• RQ3 Can a symbolic rule-based system like Getarun outperform statistical parsers in parsing complex poetic structures?
• RQ4 How does LFG facilitate the integration of syntactic, semantic, and psycholinguistic complexity in poetic analysis?
• RQ5 What is the role of rhetorical figures in shaping syntactic discontinuities in modernist Italian poetry?

Key findings

• Statistical parsers, relying solely on probabilistic information, fail to correctly parse discontinuous or noncanonical syntactic structures in Italian poetry.
• The symbolic rule-based system Getarun successfully parses complex poetic structures where statistical parsers fail.
• Getarun enables not only syntactic parsing but also full semantic and pragmatic analysis of poetic texts.
• LFG provides a robust theoretical framework for connecting syntactic discontinuities with informational structure and cognitive complexity.
• The study demonstrates that symbolic systems are better suited than statistical models for analyzing noncanonical poetic syntax.
• The results confirm that discontinuous elements in poetry are not random but follow systematic syntactic and semantic patterns amenable to formal modeling.