论文信息 - Towards a Model Theory for Distributed Representations

Towards a Model Theory for Distributed Representations

Distributed representations (such as those based on embeddings) and discrete representations (such as those based on logic) have complementary strengths. We explore one possible approach to combining these two kinds of representations. We present a model theory/semantics for first order logic based on vectors of reals. We describe the model theory, discuss some interesting properties of such a system and present a simple approach to query answering.

Ramanathan V. Guha | R. Guha

[1] Praveen Paritosh,et al. Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[2] Zhen Wang,et al. Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[3] Ramanathan V. Guha,et al. Varieties of Contexts , 2003, CONTEXT.

[4] Christopher Potts,et al. Recursive Neural Networks for Learning Logical Semantics , 2014, ArXiv.

[5] John McCarthy,et al. Circumscription - A Form of Non-Monotonic Reasoning , 1980, Artif. Intell..

[6] Quoc V. Le,et al. Distributed Representations of Sentences and Documents , 2014, ICML.

[7] Jason Weston,et al. Learning Structured Embeddings of Knowledge Bases , 2011, AAAI.

[8] Christopher Potts,et al. Recursive Neural Networks Can Learn Logical Semantics , 2014, CVSC.

[9] Herbert B. Enderton,et al. A mathematical introduction to logic , 1972 .

[10] Ramanathan V. Guha,et al. Cyc: toward programs with common sense , 1990, CACM.

[11] R. Guha. Contexts: a formalization and some applications , 1992 .

[12] Andrew Y. Ng,et al. Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[13] Jason Weston,et al. A semantic matching energy function for learning with multi-relational data , 2013, Machine Learning.