A Structured Distributional Model of Sentence Meaning and Processing - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Natural Language Engineering Année : 2019

A Structured Distributional Model of Sentence Meaning and Processing

Résumé

Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from Discourse Representation Theory and containing distri-butional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical items. Event knowledge is modeled as a graph extracted from parsed corpora and encoding roles and relationships between participants that are represented as distributional vectors. SDM is grounded on extensive psycholinguistic research showing that generalized knowledge about events stored in semantic memory plays a key role in sentence comprehension. We evaluate SDM on two recently introduced compositionality datasets, and our results show that combining a simple compositional model with event knowledge constantly improves performances, even with different types of word embeddings. 1 Sentence Meaning in Vector Spaces While for decades sentence meaning has been represented in terms of complex formal structures, the most recent trend in computational semantics is to model semantic representations with dense distributional vectors (aka embeddings). As a matter of fact, distributional semantics has become one of the most influential approaches to lexical meaning, because of the important theoretical and computational advantages of representing words with continuous vectors, such as automatically learning lexical representations from natural language corpora and multimodal data, assessing semantic similarity in terms of the distance between the vectors, and dealing with the inherently gradient and fuzzy nature of meaning (Erk 2012, Lenci 2018a).
Fichier principal
Vignette du fichier
A_Structured_Distributional_Model.pdf (393.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02151765 , version 1 (10-06-2019)

Identifiants

  • HAL Id : hal-02151765 , version 1

Citer

Emmanuele Chersoni, Enrico Santus, Ludovica Pannitto, Alessandro Lenci, Philippe Blache, et al.. A Structured Distributional Model of Sentence Meaning and Processing. Natural Language Engineering, 2019, 25, no. 4. ⟨hal-02151765⟩
87 Consultations
235 Téléchargements

Partager

Gmail Facebook X LinkedIn More