Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations (original) (raw)

Semantic Graph from English Sentences

2008

In this paper we describe our progress towards building an Interlingua based machine transla- tion system, by capturing the semantics of the source language sentences in the form of Uni- versal Networking Language (UNL) graphs from which the target language sentences can be produced. There are two stages to the UNL graph generation: first, the conceptual argu- ments of a situation are identified in the form of semantically relatable sequences (SRS) which are potential candidates for linking with semantic relations; next, the conceptual rela- tions such as instrument, source, goal, reason or agent are recognized, irrespective of their different syntactic configurations. The system has been tested against gold standard UNL expressions collected from various sources like Oxford Advanced Learners' Dictionary, XTAG corpus and Framenet corpus. Results indicate the promise and effectiveness of our approach on the difficult task of interlingua generation from text.

Large Scale Semantic Construction for Tree Adjoining Grammars

2005

Although Tree Adjoining Grammars (TAG) are widely used for syntactic processing, there is to date no large scale TAG available which also supports semantic construction. In this paper, we present a highly factorised way of implementing a syntax/semantic interface in TAG. We then show how the resulting resource can be used to perform semantic construction either during or after derivation.

Generating language from conceptual graphs

Computers & Mathematics with Applications, 1983

Conceptual graphs are a semantic representation that has a direct mapping to natural language. This article presents a universal algorithm for scanning the graphs, together with a version of augmented phrase-structure grammar for specifying the syntax of particular languages. When combined with a specific grammar, the universal algorithm determines a mapping from graphs to language with several important properties: multiple surface structures may be generated from a common underlying structure, constraints on the mapping result from the connectivity of the graphs rather than ad hoc assumptions, and the graphs combined with phrase-structure rules enforce context-sensitive conditions.

Representing Syntax and Composition with Geometric Transformations

ArXiv, 2021

The exploitation of syntactic graphs (SyGs) as a word’s context has been shown to be beneficial for distributional semantic models (DSMs), both at the level of individual word representations and in deriving phrasal representations via composition. However, notwithstanding the potential performance benefit, the syntactically-aware DSMs proposed to date have huge numbers of parameters (compared to conventional DSMs) and suffer from data sparsity. Furthermore, the encoding of the SyG links (i.e., the syntactic relations) has been largely limited to linear maps. The knowledge graphs’ literature, on the other hand, has proposed light-weight models employing different geometric transformations (GTs) to encode edges in a knowledge graph (KG). Our work explores the possibility of adopting this family of models to encode SyGs. Furthermore, we investigate which GT better encodes syntactic relations, so that these representations can be used to enhance phrase-level composition via syntactic c...

Graph-Based Meaning Representations: Design and Processing

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

This tutorial is on representing and processing sentence meaning in the form of labeled directed graphs. The tutorial will (a) briefly review relevant background in formal and linguistic semantics; (b) semi-formally define a unified abstract view on different flavors of semantic graphs and associated terminology; (c) survey common frameworks for graph-based meaning representation and available graph banks; and (d) offer a technical overview of a representative selection of different parsing approaches.

Resources for Building Applications with Dependency Minimal Recursion Semantics

We describe resources aimed at increasing the usability of the semantic representations utilized within the DELPH-IN (Deep Linguistic Processing with HPSG) consortium. We concentrate in particular on the Dependency Minimal Recursion Semantics (DMRS) formalism, a graph-based representation designed for compositional semantic representation with deep grammars. Our main focus is on English, and specifically English Resource Semantics (ERS) as used in the English Resource Grammar. We first give an introduction to ERS and DMRS and a brief overview of some existing resources and then describe in detail a new repository which has been developed to simplify the use of ERS/DMRS. We explain a number of operations on DMRS graphs which our repository supports, with sketches of the algorithms, and illustrate how these operations can be exploited in application building. We believe that this work will aid researchers to exploit the rich and effective but complex DELPH-IN resources.

Minimal Recursion Semantics: An Introduction

Research on Language and Computation, 2005

Minimal recursion semantics (MRS) is a framework for computational semantics that is suitable for parsing and generation and that can be implemented in typed feature structure formalisms. We discuss why, in general, a semantic representation with minimal structure is desirable and illustrate how a descriptively adequate representation with a nonrecursive structure may be achieved. MRS enables a simple formulation of the grammatical constraints on lexical and phrasal semantics, including the principles of semantic composition. We have integrated MRS with a broad-coverage HPSG grammar.

Bottom-Up Unranked Tree-to-Graph Transducers for Translation into Semantic Graphs

Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing

We propose a formal model for translating unranked syntactic trees, such as dependency trees, into semantic graphs. These tree-tograph transducers can serve as a formal basis of transition systems for semantic parsing which recently have been shown to perform very well, yet hitherto lack formalization. Our model features "extended" rules and an arcfactored normal form, comes with an efficient translation algorithm, and can be equipped with weights in a straightforward manner.