Proposes a model-agnostic diachronic entity embedding function to extend static KG embedding models for temporal knowledge graph completion, with a proof that the SimplE combination is fully expressive.
Temporal Analysis of Language through Neural Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We provide a method for automatically detecting change in language across time through a chronologically trained neural language model. We train the model on the Google Books Ngram corpus to obtain word vector representations specific to each year, and identify words that have changed significantly from 1900 to 2009. The model identifies words such as "cell" and "gay" as having changed during that time period. The model simultaneously identifies the specific years during which such words underwent change.
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diachronic Embedding for Temporal Knowledge Graph Completion
Proposes a model-agnostic diachronic entity embedding function to extend static KG embedding models for temporal knowledge graph completion, with a proof that the SimplE combination is fully expressive.