DeepAI AI Chat
Log In Sign Up

Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction

by   Diana Nicoleta Popa, et al.
Idiap Research Institute

Vector-space models, from word embeddings to neural network parsers, have many advantages for NLP. But how to generalise from fixed-length word vectors to a vector space for arbitrary linguistic structures is still unclear. In this paper we propose bag-of-vector embeddings of arbitrary linguistic graphs. A bag-of-vector space is the minimal nonparametric extension of a vector space, allowing the representation to grow with the size of the graph, but not tying the representation to any specific tree or graph structure. We propose efficient training and inference algorithms based on tensor factorisation for embedding arbitrary graphs in a bag-of-vector space. We demonstrate the usefulness of this representation by training bag-of-vector embeddings of dependency graphs and evaluating them on unsupervised semantic induction for the Semantic Textual Similarity and Natural Language Inference tasks.


page 1

page 2

page 3

page 4


Analyzing Structures in the Semantic Vector Space: A Framework for Decomposing Word Embeddings

Word embeddings are rich word representations, which in combination with...

Hierarchical Bag of Paths for Kernel Based Shape Classification

Graph kernels methods are based on an implicit embedding of graphs withi...

Learning Concept Embeddings for Efficient Bag-of-Concepts Densification

Explicit concept space models have proven efficacy for text representati...

Build2Vec: Building Representation in Vector Space

In this paper, we represent a methodology of a graph embeddings algorith...

Embedding Geographic Locations for Modelling the Natural Environment using Flickr Tags and Structured Data

Meta-data from photo-sharing websites such as Flickr can be used to obta...

Learning Universal Representations from Word to Sentence

Despite the well-developed cut-edge representation learning for language...