scholarly journals Improving Neural Relation Extraction with Positive and Unlabeled Learning

2020 ◽  
Vol 34 (05) ◽  
pp. 7927-7934
Author(s):  
Zhengqiu He ◽  
Wenliang Chen ◽  
Yuyi Wang ◽  
Wei Zhang ◽  
Guanchun Wang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Relation Extraction ◽  
Experimental Results ◽  
New Approach ◽  
Distant Supervision ◽  
Novel Approach ◽  
Pu Learning ◽  
Positive And Unlabeled Learning

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a given relation, and then positive and unlabeled bags are constructed. In contrast to most previous studies, which mainly use selected positive instances only, we make full use of unlabeled instances and propose two new representations for positive and unlabeled bags. These two representations are then combined in an appropriate way to make bag-level prediction. Experimental results on a widely used real-world dataset demonstrate that this new approach indeed achieves significant and consistent improvements as compared to several competitive baselines.

On Semantic Relation Extraction Over Enterprise Data

2018 ◽  
pp. 62-84 ◽  
Author(s):  
Wei Shen ◽  
Jianyong Wang ◽  
Ping Luo ◽  
Min Wang
Keyword(s):  
Statistical Method ◽  
Real World ◽  
Relation Extraction ◽  
Semantic Relation ◽  
Experimental Results ◽  
Web Data ◽  
Data Set ◽  
Redundancy Level ◽  
Hybrid Framework ◽  
The Web

Relation extraction from the Web data has attracted a lot of attention recently. However, little work has been done when it comes to the enterprise data regardless of the urgent needs to such work in real applications (e.g., E-discovery). One distinct characteristic of the enterprise data (in comparison with the Web data) is its low redundancy. Previous work on relation extraction from the Web data largely relies on the data's high redundancy level and thus cannot be applied to the enterprise data effectively. This chapter reviews related work on relation extraction and introduces an unsupervised hybrid framework REACTOR for semantic relation extraction over enterprise data. REACTOR combines a statistical method, classification, and clustering to identify various types of relations among entities appearing in the enterprise data automatically. REACTOR was evaluated over a real-world enterprise data set from HP that contains over three million pages and the experimental results show its effectiveness.

scholarly journals Learning to Transfer Relational Representations through Analogy

2019 ◽  
Vol 33 ◽  
pp. 10015-10016
Author(s):  
Gaetano Rossiello ◽  
Alfio Gliozzo ◽  
Michael Glass
Keyword(s):  
State Of The Art ◽  
Relation Extraction ◽  
Knowledge Bases ◽  
The State ◽  
Large Set ◽  
Relational Information ◽  
Siamese Network ◽  
Distant Supervision ◽  
Novel Approach ◽  
Art Methods

We propose a novel approach to learn representations of relations expressed by their textual mentions. In our assumption, if two pairs of entities belong to the same relation, then those two pairs are analogous. We collect a large set of analogous pairs by matching triples in knowledge bases with web-scale corpora through distant supervision. This dataset is adopted to train a hierarchical siamese network in order to learn entity-entity embeddings which encode relational information through the different linguistic paraphrasing expressing the same relation. The model can be used to generate pre-trained embeddings which provide a valuable signal when integrated into an existing neural-based model by outperforming the state-of-the-art methods on a relation extraction task.

scholarly journals Measuring the Significance of Policy Outputs with Positive Unlabeled Learning

2020 ◽  
pp. 1-8
Author(s):  
RADOSLAW ZUBEK ◽  
ABHISHEK DASGUPTA ◽  
DAVID DOYLE
Keyword(s):  
United Kingdom ◽  
Construct Validity ◽  
Government Regulations ◽  
New Approach ◽  
The United Kingdom ◽  
Novel Approach ◽  
Pu Learning ◽  
Finite Set ◽  
Small Set

Identifying important policy outputs has long been of interest to political scientists. In this work, we propose a novel approach to the classification of policies. Instead of obtaining and aggregating expert evaluations of significance for a finite set of policy outputs, we use experts to identify a small set of significant outputs and then employ positive unlabeled (PU) learning to search for other similar examples in a large unlabeled set. We further propose to automate the first step by harvesting “seed” sets of significant outputs from web data. We offer an application of the new approach by classifying over 9,000 government regulations in the United Kingdom. The obtained estimates are successfully validated against human experts, by forecasting web citations, and with a construct validity test.

Predicting the Signs of the Links in a Network

2020 ◽  
Vol 2 (2) ◽  
pp. 14-22
Author(s):  
Quang-Vinh Dang
Keyword(s):  
Real World ◽  
Machine Learning Techniques ◽  
Research Approach ◽  
New Approach ◽  
Online Systems ◽  
Novel Approach ◽  
Learning Techniques ◽  
The Future ◽  
Potential Improvement ◽  
New Research

It is hard to deny the importance of graph analysis techniques, particularly the problem of link and link-sign prediction, in many real-world applications. Predicting future sign of connections in a network is an important task for online systems such as social networks, e-commerce, scientific research, and others. Several research studies have been presented since the early days of this century to predict either the existence of a link in the future or the property of the link. In this study we present a novel approach that combine both families by using machine learning techniques. Instead of focusing on the established links, we follow a new research approach that focusing on no-link relationship. We aim to understand the move between two states of no-link and link. We evaluate our methods in popular real-world signed networks datasets. We believe that the new approach by understanding the no-link relation has a lot of potential improvement in the future.

scholarly journals Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding

2019 ◽  
Vol 33 ◽  
pp. 7418-7425 ◽  
Author(s):  
Changsen Yuan ◽  
Heyan Huang ◽  
Chong Feng ◽  
Xiao Liu ◽  
Xiaochi Wei
Keyword(s):  
Mutual Information ◽  
Efficient Method ◽  
Relation Extraction ◽  
Benchmark Dataset ◽  
Labor Costs ◽  
Distant Supervision ◽  
Complex Information ◽  
Novel Approach ◽  
Independent And Identically Distributed

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method.

scholarly journals Reinforcement Learning Based Artificial Immune Classifier

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Mehmet Karakose
Keyword(s):  
Reinforcement Learning ◽  
Artificial Immune Systems ◽  
Image Data ◽  
Memory Cell ◽  
Real Data ◽  
Experimental Results ◽  
Natural Immunity ◽  
Artificial Immune ◽  
New Approach ◽  
Immune Systems

One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

scholarly journals Fast and slow curiosity for high-level exploration in reinforcement learning

2020 ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Open Problem ◽  
Time Horizon ◽  
Experimental Results ◽  
Time Horizons ◽  
Designed Environment ◽  
Long Time ◽  
Efficient Exploration ◽  
High Level

Abstract Deep reinforcement learning (DRL) algorithms rely on carefully designed environment rewards that are extrinsic to the agent. However, in many real-world scenarios rewards are sparse or delayed, motivating the need for discovering efficient exploration strategies. While intrinsically motivated agents hold promise of better local exploration, solving problems that require coordinated decisions over long-time horizons remains an open problem. We postulate that to discover such strategies, a DRL agent should be able to combine local and high-level exploration behaviors. To this end, we introduce the concept of fast and slow curiosity that aims to incentivize long-time horizon exploration. Our method decomposes the curiosity bonus into a fast reward that deals with local exploration and a slow reward that encourages global exploration. We formulate this bonus as the error in an agent’s ability to reconstruct the observations given their contexts. We further propose to dynamically weight local and high-level strategies by measuring state diversity. We evaluate our method on a variety of benchmark environments, including Minigrid, Super Mario Bros, and Atari games. Experimental results show that our agent outperforms prior approaches in most tasks in terms of exploration efficiency and mean scores.

scholarly journals A Hierarchical Framework for Relation Extraction with Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 7072-7079 ◽  
Author(s):  
Ryuichi Takanobu ◽  
Tianyang Zhang ◽  
Jiexi Liu ◽  
Minlie Huang
Keyword(s):  
Reinforcement Learning ◽  
Relation Extraction ◽  
Extraction Process ◽  
Entity Extraction ◽  
Hierarchical Framework ◽  
Hierarchical Reinforcement Learning ◽  
Distant Supervision ◽  
Public Datasets ◽  
Determine Relation

Most existing methods determine relation types only after all the entities have been recognized, thus the interaction between relation types and entity mentions is not fully modeled. This paper presents a novel paradigm to deal with relation extraction by regarding the related entities as the arguments of a relation. We apply a hierarchical reinforcement learning (HRL) framework in this paradigm to enhance the interaction between entity mentions and relation types. The whole extraction process is decomposed into a hierarchy of two-level RL policies for relation detection and entity extraction respectively, so that it is more feasible and natural to deal with overlapping relations. Our model was evaluated on public datasets collected via distant supervision, and results show that it gains better performance than existing methods and is more powerful for extracting overlapping relations1.

scholarly journals Managing caching strategies for stream reasoning with reinforcement learning

2020 ◽  
Vol 20 (5) ◽  
pp. 625-640
Author(s):  
CARMINE DODARO ◽  
THOMAS EITER ◽  
PAUL OGRIS ◽  
KONSTANTIN SCHEKOTIHIN
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Performance Improvements ◽  
Novel Approach ◽  
Stream Reasoning ◽  
Significant Performance ◽  
Intelligent Management ◽  
Truth Maintenance ◽  
Constraint Learning ◽  
Real World Problems

AbstractEfficient decision-making over continuously changing data is essential for many application domains such as cyber-physical systems, industry digitalization, etc. Modern stream reasoning frameworks allow one to model and solve various real-world problems using incremental and continuous evaluation of programs as new data arrives in the stream. Applied techniques use, e.g., Datalog-like materialization or truth maintenance algorithms to avoid costly re-computations, thus ensuring low latency and high throughput of a stream reasoner. However, the expressiveness of existing approaches is quite limited and, e.g., they cannot be used to encode problems with constraints, which often appear in practice. In this paper, we suggest a novel approach that uses the Conflict-Driven Constraint Learning (CDCL) to efficiently update legacy solutions by using intelligent management of learned constraints. In particular, we study the applicability of reinforcement learning to continuously assess the utility of learned constraints computed in previous invocations of the solving algorithm for the current one. Evaluations conducted on real-world reconfiguration problems show that providing a CDCL algorithm with relevant learned constraints from previous iterations results in significant performance improvements of the algorithm in stream reasoning scenarios.

Sign in / Sign up

Export Citation Format

Share Document