Can recursive neural tensor networks learn logical reasoning?

2013-12-21 · Samuel R. Bowman

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.

📄 PDF Abstract BibTeX arXiv:1312.6192

Code (1)

sleepinyourhat/vector-entailment

Tasks

Logical ReasoningTensor Networks

Neural Tensor Networks with Diagonal Slice Matrices

2018-06-01 · NAACL 2018 6 · Takahiro Ishihara, Katsuhiko Hayashi, Hitoshi Manabe, Masashi Shimbo 외

Although neural tensor networks (NTNs) have been successful in many NLP tasks, they require a large number of parameters to be estimated, which often leads to overfitting and a long training time. We address these issues…

Knowledge Graph Completion Logical Reasoning Sentiment Analysis Tensor Networks

Recursive Neural Networks Can Learn Logical Semantics

2014-06-06 · WS 2015 7 · Samuel R. Bowman, Christopher Potts, Christopher D. Manning

Tree-structured recursive neural networks (TreeRNNs) for sentence meaning have been successful for many applications, but it remains an open question whether the fixed-length representations that they learn can support t…

Open-Ended Question Answering Relational Reasoning Sentence Tensor Networks

TensorLog: A Differentiable Deductive Database

2016-05-20 · William W. Cohen

Large knowledge bases (KBs) are useful in many tasks, but it is unclear how to integrate this sort of knowledge into "deep" gradient-based learning systems. To address this problem, we describe a probabilistic deductive …

Implementing Tensor Logic: Unifying Datalog and Neural Reasoning via Tensor Contraction

2026-01-23 · Swapn Shah, Wlodek Zadrozny arxiv

The unification of symbolic reasoning and neural networks remains a central challenge in artificial intelligence. Symbolic systems offer reliability and interpretability but lack scalability, while neural networks provid…

Link Prediction

Improving the Expressiveness of Deep Learning Frameworks with Recursion

2018-09-04 · Eunji Jeong, Joo Seong Jeong, Soojeong Kim, Gyeong-In Yu 외

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano…

Deep Learning