paper-with-me

Papers

Learning Word Representations from Relational Graphs

2014-12-07 · Danushka Bollegala, Takanori Maehara, Yuichi Yoshida, Ken-ichi Kawarabayashi

Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes in common, they are connected by some semantic relations. On the other hand, if there are numerous semantic relations between two words, we can expect some of the attributes of one of the words to be inherited by the other. Motivated by this close connection between attributes and relations, given a relational graph in which words are inter- connected via numerous semantic relations, we propose a method to learn a latent representation for the individual words. The proposed method considers not only the co-occurrences of words as done by existing approaches for word representation learning, but also the semantic relations in which two words co-occur. To evaluate the accuracy of the word representations learnt using the proposed method, we use the learnt word representations to solve semantic word analogy problems. Our experimental results show that it is possible to learn better word representations by using semantic semantics between words.

📄 PDF Abstract BibTeX arXiv:1412.2378

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations

2018-06-14 · Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He 외

Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional featur…

image-classificationImage ClassificationNatural Language InferenceQuestion Answering+3

GLoMo: Unsupervised Learning of Transferable Relational Graphs

2018-12-01 · NeurIPS 2018 12 · Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He 외

Modern deep transfer learning approaches have mainly focused on learning generic feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional featur…

image-classificationImage ClassificationNatural Language InferenceQuestion Answering+3

Incorporating Both Distributional and Relational Semantics in Word Representations

2014-12-18 · Daniel Fried, Kevin Duh

We investigate the hypothesis that word representations ought to incorporate both distributional and relational semantics. To this end, we employ the Alternating Direction Method of Multipliers (ADMM), which flexibly opt…

Knowledge Base Completion

Incorporating Both Distributional and Relational Semantics in Word Representations

2014-12-14 · Daniel Fried, Kevin Duh

We investigate the hypothesis that word representations ought to incorporate both distributional and relational semantics. To this end, we employ the Alternating Direction Method of Multipliers (ADMM), which flexibly opt…

Knowledge Base Completion

Neural-Symbolic Relational Reasoning on Graph Models: Effective Link Inference and Computation from Knowledge Bases

2020-05-05 · Henrique Lemos, Pedro Avelar, Marcelo Prates, Luís Lamb 외

The recent developments and growing interest in neural-symbolic models has shown that hybrid approaches can offer richer models for Artificial Intelligence. The integration of effective relational learning and reasoning …

Graph Neural NetworkKnowledge GraphsLink PredictionRelational Reasoning+1