Pith. sign in

REVIEW 4 cited by

Harnessing Deep Neural Networks with Logic Rules

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1603.06318 v6 pith:M6ADDRPG submitted 2016-03-21 cs.LG cs.AIcs.CLstat.ML

Zhiting Hu , Xuezhe Ma , Zhengzhong Liu , Eduard Hovy , Eric Xing This is my paper · ORCID
classification cs.LGcs.AIcs.CLstat.ML
keywords neuralruleslogicnetworksdeepframeworkstructuredachieve
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Embedding Symbolic Knowledge into Deep Networks

    cs.AI 2019-09 conditional novelty 6.0 of 10

    LENSR embeds propositional formulas, especially d-DNNF, with a modified graph convolutional network and uses the embeddings as a regularizer, improving entailment checking and visual relation prediction.

  2. Conditions for Unnecessary Logical Constraints in Kernel Machines

    cs.LO 2019-08 conditional novelty 5.0 of 10

    The paper defines an 'unnecessary constraint' in kernel-based learning from logical constraints and shows it can be detected by logical consequence or by finding alternative Lagrange multipliers that preserve the opti...

  3. Knowledge Enhanced Attention for Robust Natural Language Inference

    cs.CL 2019-08 conditional novelty 5.0 of 10

    Injecting WordNet lexical relations as bias terms into multi-head attention improves accuracy on the adversarial SNLI test set, with BERT reaching 94.1%, equal to estimated human performance.

  4. Tale of tails using rule augmented sequence labeling for event extraction

    cs.IR 2019-08 conditional novelty 4.0 of 10

    A new five-language disaster event extraction dataset shows that rule-based cues added to Bi-LSTM models improve rare tail event labels when training data is small.

Pith tools