paper-with-me

홈 › Papers

NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning

2021-05-29 · Joint Conference on Lexical and Computational Semantics 2021 · Zeming Chen, Qiyue Gao, Lawrence S. Moss

Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have their advantages and weaknesses. However, currently, no method combines them in a system to solve the task of NLI. To merge symbolic and deep learning methods, we propose an inference framework called NeuralLog, which utilizes both a monotonicity-based logical inference engine and a neural network language model for phrase alignment. Our framework models the NLI task as a classic search problem and uses the beam search algorithm to search for optimal inference paths. Experiments show that our joint logic and neural inference system improves accuracy on the NLI task and can achieve state-of-art accuracy on the SICK and MED datasets.

📄 PDF Abstract BibTeX arXiv:2105.14167

Code (1)

eric11eca/NeuralLog 공식 구현

Tasks

Deep LearningLanguage ModelingLanguage ModellingLogical ReasoningNatural Language Inference

Methods 이 논문이 사용한 방법론

ALBERT 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…

Similar Papers 제목 키워드 기반

NeuralLog: a Neural Logic Language

2021-05-04 · Victor Guimarães, Vítor Santos Costa

Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important. In this paper we propose NeuralLog, a first-order logic language that is compil…

Link PredictionPrediction

Log-based Anomaly Detection Without Log Parsing

2021-08-04 · Van-Hoang Le, Hongyu Zhang

Software systems often record important runtime information in system logs for troubleshooting purposes. There have been many studies that use log data to construct machine learning models for detecting system anomalies.…

Anomaly DetectionLog Parsing

Learning to Reason via Mixture-of-Thought for Logical Reasoning

2025-05-21 · Tong Zheng, Lichang Chen, Simeng Han, R. Thomas McCoy 외

Human beings naturally utilize multiple reasoning modalities to learn and solve logical problems, i.e., different representational formats such as natural language, code, and symbolic logic. In contrast, most existing LL…

Logical ReasoningNatural Language Inference

Neural Logistic Bandits

2025-05-04 · Seoungbin Bae, Dabeen Lee

We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a neural network. Existing approaches either exhibit unfavorable dependenc…

Type Inference as Optimization

2021-10-08 · NeurIPS Workshop AIPLANS 2021 12 · Eirene V. Pandi, Earl T. Barr, Andrew D. Gordon, Charles Sutton

Optionally typed dynamic languages can permit multiple valid type assignments. When this happens, developers can prefer one valid type assignment over another because it better reflects how they think about the program a…

validVocal Bursts Type Prediction