Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Chen, Liang; Berant, Jonathan; Le, Quoc V.; Forbus, Kenneth D.; Lao, Ni

doi:10.48550/arxiv.1611.00020

Cited by 47 publications

(44 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…c) Neural-Symbolic Models: To combine the advantages and circumvent the shortcomings of both symbolic and neural methods, neural-symbolic models which integrate symbolic logic and neural representation are widely studied [69,70,71,72,73]. Some work employs a neural module to parse the language into executable programs [74,18] and deterministically executing the programs to find the answer in a symbolic module. For example, the neural-symbolic models for numerical reasoning translate the input texts into expressions through a neural generation model and then discretely execute the expressions [43,46,47].…”

Section: B Advanced Methods Of Complex Reasoningmentioning

confidence: 99%

“…We design a set of trigger words to match potential functions [74] and extract arguments (i.e., participants, positions, and numbers) according to their relative positions to the trigger words. For uncertain sentences with no matched function, we also build a neural classification model based on RoBERTa to predict their corresponding function types.…”

Section: B Symbolic Model: Armmentioning

confidence: 99%

“…As the symbolic executor is non-differential, policy-gradient methods are usually employed to train the model [74,87]. However, analytical reasoning questions can only be answered after examining the satisfiability of all the constraints, which leads to extremely sparse rewards and makes the model hard to be optimized.…”

Section: Neural-symbolic Model: Nsarmentioning

confidence: 99%

See 2 more Smart Citations

From LSAT: The Progress and Challenges of Complex Reasoning

Wang¹,

Liu²,

Zhong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Complex reasoning aims to draw a correct inference based on complex rules. As a hallmark of human intelligence, it involves a degree of explicit reading comprehension, interpretation of logical knowledge and complex rule application. In this paper, we take a step forward in complex reasoning by systematically studying the three challenging and domain-general tasks of the Law School Admission Test (LSAT), including analytical reasoning, logical reasoning and reading comprehension. We propose a hybrid reasoning system to integrate these three tasks and achieve impressive overall performance on the LSAT tests. The experimental results demonstrate that our system endows itself a certain complex reasoning ability, especially the fundamental reading comprehension and challenging logical reasoning capacities. Further analysis also shows the effectiveness of combining the pre-trained models with the task-specific reasoning module, and integrating symbolic knowledge into discrete interpretable reasoning steps in complex reasoning. We further shed a light on the potential future directions, like unsupervised symbolic knowledge extraction, model interpretability, few-shot learning and comprehensive benchmark for complex reasoning.

show abstract

Section: B Advanced Methods Of Complex Reasoningmentioning

confidence: 99%

Section: B Symbolic Model: Armmentioning

confidence: 99%

See 1 more Smart Citation

From LSAT: The Progress and Challenges of Complex Reasoning

Wang¹,

Liu²,

Zhong³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…But how to combine it with embedding and deep learning techniques need to be concerned. Some studies [9,60,61] have discussed in this topic.…”

Section: Complementary Of Knowledgementioning

confidence: 99%

“…Symbolic reasoning [7] and deep learning [8] based inference are not compatible in early years. However, since the development of embedded representation methods and deep learning, it become more and more applicable [9]. In other words, that has established a bridge for the fusion of the above two technologies, and can make comprehensive use of the advantages of both sides.…”

Section: Introductionmentioning

confidence: 99%

Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field

Huang¹,

Chen²,

Tang³

2021

Preprint

View full text Add to dashboard Cite

We introduce a framework for AI-based medical consultation system with knowledge graph embedding and reinforcement learning components and its implement. Our implement of this framework leverages knowledge organized as a graph to have diagnosis according to evidence collected from patients recurrently and dynamically. According to experiment we designed for evaluating its performance, it archives a good result. More importantly, for getting better performance, researchers can implement it on this framework based on their innovative ideas, well designed experiments and even clinical trials.

show abstract

Knowledge Base Relation Detection via Multi-View Matching

Hasan

et al. 2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Relation detection is a core component for Knowledge Base Question Answering (KBQA). In this paper, we propose a knowledge base (KB) relation detection model based on multi-view matching, which utilizes useful information extracted from questions and KB.The matching inside each view is through multiple perspectives to compare two input texts thoroughly. All these components are trained in an end-to-end neural network model. Experiments on SimpleQuestions and We-bQSP yield state-of-the-art results on relation detection.

show abstract

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Cited by 47 publications

References 19 publications

From LSAT: The Progress and Challenges of Complex Reasoning

From LSAT: The Progress and Challenges of Complex Reasoning

Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field

Knowledge Base Relation Detection via Multi-View Matching

Contact Info

Product

Resources

About