Investigating the Role of Prior Disambiguation in Deep-learning Compositional Models of Meaning

2014/11/15 by Jianpeng Cheng, Cheng, Jianpeng, Dimitri Kartsaklis +3 · 1 citation
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1411.4116

openalex publication_date 2014/11/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper aims to explore the effect of prior disambiguation on neural network- based compositional models, with the hope that better semantic representations for text compounds can be produced. We disambiguate the input word vectors before they are fed into a compositional deep net. A series of evaluations shows the positive effect of prior disambiguation for such deep models.

Citations

• Category-Theoretic Quantitative Compositional Distributional Models of Natural Language Semantics

Cited by

• Compositional Vector Space Models for Knowledge Base Completion

Related

• Compositionality as Lexical Symmetry
• One Representation per Word - Does it make Sense for Composition?
• A Deep Network with Visual Text Composition Behavior
• Compositionality decomposed: how do neural networks generalise?
• Semantic Composition and Decomposition: From Recognition to Generation