A Generative Model of Words and Relationships from Multiple Sources

10/01/2015
by   Stephanie L. Hyland, et al.
0

Neural language models are a powerful tool to embed words into semantic vector spaces. However, learning such models generally relies on the availability of abundant and diverse training examples. In highly specialised domains this requirement may not be met due to difficulties in obtaining a large corpus, or the limited range of expression in average use. Such domains may encode prior knowledge about entities in a knowledge base or ontology. We propose a generative model which integrates evidence from diverse data sources, enabling the sharing of semantic information. We achieve this by generalising the concept of co-occurrence from distributional semantics to include other relationships between entities or words, which we model as affine transformations on the embedding space. We demonstrate the effectiveness of this approach by outperforming recent models on a link prediction task and demonstrating its ability to profit from partially or fully unobserved data training labels. We further demonstrate the usefulness of learning from different data sources with overlapping vocabularies.

READ FULL TEXT
research
06/27/2016

STransE: a novel embedding model of entities and relationships in knowledge bases

Knowledge bases of real-world facts about entities and their relationshi...
research
12/21/2022

Automatic Semantic Modeling for Structural Data Source with the Prior Knowledge from Knowledge Base

A critical step in sharing semantic content online is to map the structu...
research
01/16/2016

Learning the Semantics of Structured Data Sources

Information sources such as relational databases, spreadsheets, XML, JSO...
research
08/02/2021

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Can a generative model be trained to produce images from a specific doma...
research
12/07/2021

Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings

With an increase of dataset availability, the potential for learning fro...
research
06/03/2021

A Systematic Investigation of KB-Text Embedding Alignment at Scale

Knowledge bases (KBs) and text often contain complementary knowledge: KB...
research
07/19/2011

Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings

Open-text (or open-domain) semantic parsers are designed to interpret an...

Please sign up or login with your details

Forgot password? Click here to reset