Proposes Adaptive Margin Loss (AML) for TransE-style KG embeddings that uses a correntropy objective to adaptively expand the margin during training, requiring only a single center value instead of upper/lower bounds.
Question Answering with Subgraph Embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few hand-crafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers. Training our system using pairs of questions and structured representations of their answers, and pairs of question paraphrases, yields competitive results on a competitive benchmark of the literature.
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function
Proposes Adaptive Margin Loss (AML) for TransE-style KG embeddings that uses a correntropy objective to adaptively expand the margin during training, requiring only a single center value instead of upper/lower bounds.