Can recursive neural tensor networks learn logical reasoning?

By Samuel R. Bowman. 2013

44 citations recorded by the source corpus.

Recursive neural network models and their accompanying vector representations for words have seen success in an array of increasingly semantically sophisticated tasks, but almost nothing is known about their ability to accurately capture the aspects of linguistic meaning that are necessary for interpretation or reasoning. To evaluate this, I train a recursive model on a new corpus of constructed examples of logical reasoning in short sentences, like the inference of "some animal walks" from "some dog walks" or "some cat walks," given that dogs and cats are animals. This model learns representations that generalize well to new types of reasoning pattern in all but a few cases, a result which is promising for the ability of learned representation models to capture logical reasoning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical Learning Theory

Citations in the corpus

Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, background): “ (2012) builds a neural network that recursively combines word representations based on parse tree structures and shows that such neural network can simulate the behavior of conjunction and negation. Bowman (2014) further demonstrates that recursive neural network can capture certain aspects of natu”
Traversing Knowledge Graphs in Vector Space (2015, background): “Previous works have explored compositional vector space representations in the context of sentence interpretation (Socher et al., 2012; Socher et al., 2014; Grefenstette, 2013; Bowman et al., 2014).”
Deep Learning for Ontology Reasoning (2017, background): “However, these focus on rather restricted logics, like natural logic (Bowman, 2013) or real logic (Seraﬁni and d’Avila Garcez, 2016), and do not consider reasoning in its full generality.”
Simpler Context-Dependent Logical Forms via Model Projections (2016, background): “16) use recurrent neural networks attempt to perform logical operations. One could go one step further and bypass logical forms altogether, performing all the logical reasoning in a continuous space (Bowman et al., 2014; Weston et al., 2015; Guu et al., 2015; Reed and de Freitas, 2016). This certain”
Learning Program Embeddings to Propagate Feedback on Student Code (2015, methodology): “Our models are related to recent work from the NLP and deep learning communities on recursive neural networks, particularly for modeling semantics in sentences or symbolic expressions (Socher et al., 2013; 2011; Zaremba et al., 2014; Bowman, 2013).”
Dynamic Neural Program Embedding for Program Repair (2017, background): “As for learning representations, there are several related efforts in modeling semantics in sentence or symbolic expressions (Socher et al., 2013; Zaremba et al., 2014; Bowman, 2013).”