scholarly journals Word Representation

2020 ◽  
pp. 13-41
Author(s):  
Zhiyuan Liu ◽  
Yankai Lin ◽  
Maosong Sun
Keyword(s):  
Word Representation

scholarly journals Context-dependent word representation for neural machine translation

2017 ◽  
Vol 45 ◽  
pp. 149-160 ◽  
Author(s):  
Heeyoul Choi ◽  
Kyunghyun Cho ◽  
Yoshua Bengio
Keyword(s):  
Machine Translation ◽  
Neural Machine Translation ◽  
Word Representation ◽  
Context Dependent

scholarly journals Problems of defining legal concepts in laws and other normative legal acts

Legal Ukraine ◽  
2020 ◽  
pp. 30-41
Author(s):  
Volodymyr Klochkov
Keyword(s):  
The State ◽  
Legal Concept ◽  
Legal Norms ◽  
Legal Nature ◽  
State And Society ◽  
Word Representation ◽  
The Law ◽  
Definition Of ◽  
Legal Concepts ◽  
Laws And Regulations

Each legal concept has not only content (content), but also a form. The form requires compliance with the rules for the definition and construction of concepts. Improving legal terminology is impossible without deep development and observance of the rules of analysis and the precise construction of the conceptual apparatus. Gaps in legislation and regulations are derived from inaccuracy, lack of clarity and simplicity of conceptual constructions. The inconsistency of certain legal norms found in various laws and regulatory legal acts, the inconsistency of norms with the prevailing realities of legal life in the state and society impede the fulfillment by state authorities, including law enforcement, of their functional responsibilities. Mistakes made in the preparation of draft laws and regulations, methodological recommendations mainly boil down to the violation of the requirements of the unified laws of logic: the law of identity, the law of contradiction, the law of the excluded third and the law of sufficient reason. The use of inappropriate terminology causes complications in the application of legal norms. The Constitution of Ukraine assigns to the prosecutor the function of representing the interests of a citizen or state in court in cases specified by law. The term representation is not exactly chosen. The word "representation" means: the performance of the duties of a representative; an institution representing the interests of someone; elections, as well as the law, the procedure for the election of representatives to any bodies; representation is a legal relationship in which one party (representative) is obligated or entitled to make a transaction on behalf of the other party that it represents; representation means activity on behalf of someone, on behalf of a person. By its legal nature, a representative can only be authorized for transactions that the person he represents is entitled to carry out. The representation of the prosecutor's office in court is specific, since this body does not need instructions, contracts or other documents. The prosecutor or his deputy should act not on behalf of someone, but on behalf of the state in favor of the person and citizen, state or society, within the limits established by law. In the legislation there is a conflict (conflict) in the law regarding the term «representation». To eliminate such a conflict, it is necessary to amend the Law of Ukraine «On the Prosecutor's Office». Key words: definition of concepts, laws and regulations, accuracy, clarity, brevity of terms.

scholarly journals Learning Task-Specific Representation for Novel Words in Sequence Labeling

2019 ◽  
Author(s):  
Minlong Peng ◽  
Qi Zhang ◽  
Xiaoyu Xing ◽  
Tao Gui ◽  
Jinlan Fu ◽  
...  
Keyword(s):  
Empirical Studies ◽  
Named Entity Recognition ◽  
Learning Task ◽  
Training Data ◽  
Entity Recognition ◽  
Named Entity ◽  
Part Of Speech Tagging ◽  
Sequence Labeling ◽  
Part Of Speech ◽  
Word Representation

Word representation is a key component in neural-network-based sequence labeling systems. However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance. This is commonly referred to as the out-of-vocabulary (OOV) problem. In this work, we address the OOV problem in sequence labeling using only training data of the task. To this end, we propose a novel method to predict representations for OOV words from their surface-forms (e.g., character sequence) and contexts. The method is specifically designed to avoid the error propagation problem suffered by existing approaches in the same paradigm. To evaluate its effectiveness, we performed extensive empirical studies on four part-of-speech tagging (POS) tasks and four named entity recognition (NER) tasks. Experimental results show that the proposed method can achieve better or competitive performance on the OOV problem compared with existing state-of-the-art methods.

scholarly journals Natural language description of images using hybrid recurrent neural network

2019 ◽  
Vol 9 (4) ◽  
pp. 2932
Author(s):  
Md. Asifuzzaman Jishan ◽  
Khan Raqib Mahmud ◽  
Abul Kalam Al Azad
Keyword(s):  
Neural Network ◽  
Natural Language ◽  
Recurrent Neural Network ◽  
Short Term Memory ◽  
Text Line ◽  
Short Term ◽  
Word Representation ◽  
Benchmark Datasets ◽  
Long Short Term Memory ◽  
Language Description

We presented a learning model that generated natural language description of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the intricacies of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional Recurrent Neural Network (BRNN) models. We conducted experiments on three benchmark datasets, e.g., Flickr8K, Flickr30K, and MS COCO. Our hybrid model utilized LSTM model to encode text line or sentences independent of the object location and BRNN for word representation, this reduced the computational complexities without compromising the accuracy of the descriptor. The model produced better accuracy in retrieving natural language based description on the dataset.

REGULARITIES AND SINGULARITIES IN LINE PICTURES

1991 ◽  
Vol 05 (01n02) ◽  
pp. 57-77 ◽  
Author(s):  
J. C. SIMON ◽  
O. BARET
Keyword(s):  
Pattern Recognition ◽  
Graph Representation ◽  
Main Difficulty ◽  
Feature Classification ◽  
Regular Feature ◽  
Substitution Rates ◽  
Preliminary Results ◽  
Word Representation ◽  
Definition Of

The main difficulty in pattern recognition is the interpretation of the iconic picture, which consists of pixels, into primitive features. The definition of a feature classification as regular or singular recalled and justified. These ideas are applied to line images, and particularly to handwritten words. A regular feature, the axis, is found on the graph representation of a word. It allows segmentation of the word representation and the obtaining of a descriptive chain. Examples of such symbolic descriptions are given with their interpretations as words from a list of 25. The results show 87% success and 3% substitution rates for the handwriting of one person. Preliminary results show that it may be extended to large categories of handwritings.

Sign in / Sign up

Export Citation Format

Share Document