scholarly journals Semantic relation classification through low-dimensional distributed representations of partial word sequences

2019 ◽  
Vol 10 (1) ◽  
pp. 28-44
Author(s):  
Zhan Jin ◽  
Chihiro Shibata ◽  
Kazuya Tago
Keyword(s):  
Semantic Relation ◽  
Distributed Representations ◽  
Partial Word ◽  
Relation Classification ◽  
Low Dimensional

scholarly journals Learning Concise Representations of Users' Influences through Online Behaviors

2017 ◽  
Author(s):  
Shenghua Liu ◽  
Houdong Zheng ◽  
Huawei Shen ◽  
Xueqi Cheng ◽  
Xiangwen Liao
Keyword(s):  
State Of The Art ◽  
Fundamental Problem ◽  
Viral Marketing ◽  
High Dimensional ◽  
Opinion Formation ◽  
Distributed Representations ◽  
Interpersonal Influences ◽  
Low Dimensional ◽  
Independent Model ◽  
Do So

Whereas it is well known that social network users influence each other, a fundamental problem in influence maximization, opinion formation and viral marketing is that users' influences are difficult to quantify. Previous work has directly defined an independent model parameter to capture the interpersonal influence between each pair of users. However, such models do not consider how influences depend on each other if they originate from the same user or if they act on the same user. To do so, these models need a parameter for each pair of users, which results in high-dimensional models becoming easily trapped into the overfitting problem. Given these problems, another way of defining the parameters is needed to consider the dependencies. Thus we propose a model that defines parameters for every user with a latent influence vector and a susceptibility vector. Such low-dimensional and distributed representations naturally cause the interpersonal influences involving the same user to be coupled with each other, thus reducing the model's complexity. Additionally, the model can easily consider the sentimental polarities of users' messages and how sentiment affects users' influences. In this study, we conduct extensive experiments on real Microblog data, showing that our model with distributed representations achieves better accuracy than the state-of-the-art and pair-wise models, and that learning influences on sentiments benefit performance.

Semantic Relation Classification by Bi-directional LSTM Architecture

2017 ◽  
Author(s):  
Menglong Wu ◽  
Lin Liu ◽  
Wenxi Yao ◽  
Chunyong Yin ◽  
Jin Wang
Keyword(s):  
Semantic Relation ◽  
Relation Classification

scholarly journals MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network

2018 ◽  
Author(s):  
Di Jin ◽  
Franck Dernoncourt ◽  
Elena Sergeeva ◽  
Matthew McDermott ◽  
Geeticka Chauhan
Keyword(s):  
Neural Network ◽  
Semantic Relation ◽  
Convolution Neural Network ◽  
Relation Classification

scholarly journals Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

2015 ◽  
Author(s):  
Kazuma Hashimoto ◽  
Pontus Stenetorp ◽  
Makoto Miwa ◽  
Yoshimasa Tsuruoka
Keyword(s):  
Semantic Relation ◽  
Word Embeddings ◽  
Relation Classification ◽  
Task Oriented

GRAPH BASED MULTI-VIEW LEARNING FOR SEMANTIC RELATION EXTRACTION

2010 ◽  
Vol 04 (03) ◽  
pp. 285-300 ◽  
Author(s):  
HAIBO LI ◽  
YUTAKA MATSUO ◽  
MITSURU ISHIZUKA
Keyword(s):  
Bipartite Graph ◽  
Complete Graph ◽  
Relation Extraction ◽  
Learning Task ◽  
Semantic Relation ◽  
Description Language ◽  
Concept Pair ◽  
Relation Classification ◽  
Combine Information

To understand text contents better, many research efforts have been made exploring detection and classification of the semantic relation between a concept pair. As described herein, we present our study of a semantic relation classification task as a graph-based multi-view learning task. Semantic relation can be naturally represented from two views: entity pair view and context view. Then we construct a weighted complete graph for each view and a bipartite graph to combine information of different views. An instance's label score is propagated on each intra-view graph and inter-view graph. The proposed algorithm is evaluated using the Concept Description Language for Natural Language (CDL) corpus and SemEval-2007 Task 04 dataset. The experimental results validate its effectiveness.

Sign in / Sign up

Export Citation Format

Share Document