Weakly Supervised Reasoning by Neuro-Symbolic Approaches
Not on the map. Why?
Abstract (arXiv)
Deep learning has largely improved the performance of various natural language processing (NLP) tasks. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this chapter, we will introduce our recent progress on neuro-symbolic approaches to NLP, which combines different schools of AI, namely, symbolism and connectionism. Generally, we will design a neural system with symbolic latent structures for an NLP task, and apply reinforcement learning or its relaxation to perform weakly supervised reasoning in the downstream task. Our framework has been successfully applied to various tasks, including table query reasoning, syntactic structure reasoning, information extraction reasoning, and rule reasoning. For each application, we will introduce the background, our approach, and experimental results.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 73 references that are in the map. First posted on arXiv 19 Sep 2023.
Builds on
37 of 73 references.
References · 37
- 2017Attention Is All You Needcited by 59,932
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
- 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
- 2019Attention is not Explanationcited by 916
- 2014Neural Turing Machinescited by 630
- 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
25 more
- 2018Deep Learning: A Critical Appraisalcited by 214
- 2018Measuring abstract reasoning in neural networkscited by 165
- 2016Language to Logical Form with Neural Attentioncited by 158
- 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 101
- 2019Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoderscited by 60
- 2017Neural Language Modeling by Jointly Learning Syntax and Lexiconcited by 57
- 2017A Deep Generative Framework for Paraphrase Generationcited by 54
- 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
- 2017Learning to Compose Task-Specific Tree Structurescited by 48
- 2019Unsupervised Paraphrasing by Simulated Annealingcited by 37
- 2015Neural Programmer: Inducing Latent Programs with Gradient Descentcited by 32
- 2016Learning to Compose Words into Sentences with Reinforcement Learningcited by 30
- 2020Paraphrase Generation with Latent Bag of Wordscited by 27
- 2017Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMscited by 23
- 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
- 2017Towards String-to-Tree Neural Machine Translationcited by 19
- 2017Dynamic Entity Representations in Neural Language Modelscited by 19
- 2018A task in a suit and a tie: paraphrase generation with semantic augmentationcited by 15
- 2017Robust Incremental Neural Semantic Graph Parsingcited by 13
- 2015Multilingual Relation Extraction using Compositional Universal Schemacited by 11
- 2016Coupling Distributed and Symbolic Execution for Natural Language Queriescited by 9
- 2021Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logiccited by 9
- 2019An Imitation Learning Approach to Unsupervised Parsingcited by 7
- 2018JUMPER: Learning When to Make Classification Decisions in Readingcited by 6
- 2017Object-oriented Neural Programming (OONP) for Document Understandingcited by 3
Built on by
Citing papers per year: 2024: 3.
3 papers.