Distilling Task-specific Logical Rules from Large Pre-trained Models
- URL: http://arxiv.org/abs/2210.02768v1
- Date: Thu, 6 Oct 2022 09:12:18 GMT
- Title: Distilling Task-specific Logical Rules from Large Pre-trained Models
- Authors: Tao Chen, Luxin Liu, Xuepeng Jia, Baoliang Cui, Haihong Tang, Siliang
Tang
- Abstract summary: We develop a novel framework to distill task-specific logical rules from large pre-trained models.
Specifically, we borrow recent prompt-based language models as the knowledge expert to yield initial seed rules.
Experiments on three public named entity tagging benchmarks demonstrate the effectiveness of our proposed framework.
- Score: 24.66436804853525
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Logical rules, both transferable and explainable, are widely used as weakly
supervised signals for many downstream tasks such as named entity tagging. To
reduce the human effort of writing rules, previous researchers adopt an
iterative approach to automatically learn logical rules from several seed
rules. However, obtaining more seed rules can only be accomplished by extra
human annotation with heavy costs. Limited by the size and quality of the seed
rules, the model performance of previous systems is bounded. In this paper, we
develop a novel framework STREAM to distill task-specific logical rules from
large pre-trained models. Specifically, we borrow recent prompt-based language
models as the knowledge expert to yield initial seed rules, and based on the
formed high-quality instance pool that acts as an intermediary role, we keep
teaching the expert to fit our task and learning task-specific logical rules.
Experiments on three public named entity tagging benchmarks demonstrate the
effectiveness of our proposed framework. With several predefined prompt
templates, our system has gained significant improvements over previous
state-of-the-art methods.
Related papers
- DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference.
We propose a novel decoding framework, DECIDER, which enables us to program rules on how we complete tasks to control a PLM.
arXiv Detail & Related papers (2024-03-04T11:49:08Z) - Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs [87.34281749422756]
Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks.
However, their mastery of underlying inferential rules still falls short of human capabilities.
We propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic.
arXiv Detail & Related papers (2024-02-18T03:38:51Z) - ChatRule: Mining Logical Rules with Large Language Models for Knowledge
Graph Reasoning [107.61997887260056]
We propose a novel framework, ChatRule, unleashing the power of large language models for mining logical rules over knowledge graphs.
Specifically, the framework is initiated with an LLM-based rule generator, leveraging both the semantic and structural information of KGs.
To refine the generated rules, a rule ranking module estimates the rule quality by incorporating facts from existing KGs.
arXiv Detail & Related papers (2023-09-04T11:38:02Z) - Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery [76.63807209414789]
We challenge the status quo in class-iNCD and propose a learning paradigm where class discovery occurs continuously and truly unsupervisedly.
We propose simple baselines, composed of a frozen PTM backbone and a learnable linear classifier, that are not only simple to implement but also resilient under longer learning scenarios.
arXiv Detail & Related papers (2023-03-28T13:47:16Z) - Effective and interpretable dispatching rules for dynamic job shops via
guided empirical learning [0.0]
This paper is the first major attempt at combining machine learning with domain problem reasoning for scheduling.
We test our approach in the classical dynamic job shop scheduling problem minimising tardiness.
Results suggest that our approach was able to find new state-of-the-art rules, which significantly outperform the existing literature.
arXiv Detail & Related papers (2021-09-07T20:46:45Z) - Weakly Supervised Named Entity Tagging with Learnable Logical Rules [20.90760075357411]
We study the problem of building entity tagging systems by using a few rules as weak supervision.
We propose a novel method TALLOR that bootstraps high-quality logical rules to train a neural tagger in a fully automated manner.
arXiv Detail & Related papers (2021-07-05T21:32:19Z) - Rewriting a Deep Generative Model [56.91974064348137]
We introduce a new problem setting: manipulation of specific rules encoded by a deep generative model.
We propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory.
We present a user interface to enable users to interactively change the rules of a generative model to achieve desired effects.
arXiv Detail & Related papers (2020-07-30T17:58:16Z) - Building Rule Hierarchies for Efficient Logical Rule Learning from
Knowledge Graphs [20.251630903853016]
We propose new methods for pruning unpromising rules using rule hierarchies.
We show that the application of HPMs is effective in removing unpromising rules.
arXiv Detail & Related papers (2020-06-29T16:33:30Z) - Pre-training Is (Almost) All You Need: An Application to Commonsense
Reasoning [61.32992639292889]
Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks.
We introduce a new scoring method that casts a plausibility ranking task in a full-text format.
We show that our method provides a much more stable training phase across random restarts.
arXiv Detail & Related papers (2020-04-29T10:54:40Z) - Towards Learning Instantiated Logical Rules from Knowledge Graphs [20.251630903853016]
We present GPFL, a probabilistic learner rule optimized to mine instantiated first-order logic rules from knowledge graphs.
GPFL utilizes a novel two-stage rule generation mechanism that first generalizes extracted paths into templates that are acyclic abstract rules.
We reveal the presence of overfitting rules, their impact on the predictive performance, and the effectiveness of a simple validation method filtering out overfitting rules.
arXiv Detail & Related papers (2020-03-13T00:32:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.