scholarly journals Systems of knowledge representation based on stratified graphs. Application in Natural Language Generation

2016 ◽  
Vol 32 (1) ◽  
pp. 49-62
Author(s):  
DANIELA DANCIULESCU ◽  
◽  
MIHAELA COLHON ◽  
◽  
Keyword(s):  
Knowledge Representation ◽  
Natural Language ◽  
Natural Language Generation ◽  
Inference Process ◽  
Knowledge Processing ◽  
Language Generation ◽  
Universal Algebras ◽  
Injective Mapping ◽  
Regular Path ◽  
Real Objects

The concept of stratified graph introduces some method of knowledge representation (see [T¸ and ˘ areanu, N., ˘ Knowledge representation by labeled stratified graphs, Proc. 8th World Multi-Conference on Systemics, Cybernetics and Informatics, 5 (2004), 345–350; T¸ and ˘ areanu, N., ˘ Proving the Existence of Labelled Stratified Graphs, An. Univ. Craiova Ser. Mat. Inform., 27 (2000), 81–92]) The inference process developed for this method uses the paths of the stratified graphs, an order between the elementary arcs of a path and some results of universal algebras. The order is defined by considering a structured path instead of a regular path. In this paper we define the concept of system of knowledge representation as a tuple of the following components: a stratified graph G, a partial algebra Y of real objects, an embedding mapping (an injective mapping that embeds the nodes of G into objects of Y ) and a set of algorithms such that each of them can combine two objects of Y to get some other object of Y . We define also the concept of inference process performed by a system of knowledge processing in which the interpretation of the symbolic elements is defined by means of natural language constructions. In this manner we obtained a mechanism for texts generation in a natural language (for this approach, Romanian).

scholarly journals Splitting the structured paths in stratified graphs. Application in Natural Language Generation

2014 ◽  
Vol 22 (2) ◽  
pp. 57-68 ◽  
Author(s):  
Dana Dănciulescu ◽  
Mihaela Colhon
Keyword(s):  
Knowledge Representation ◽  
Natural Language ◽  
Natural Language Generation ◽  
Graph Representation ◽  
Inference Process ◽  
Inference Mechanism ◽  
Language Generation ◽  
Universal Algebras ◽  
Regular Path

AbstractThe concept of labeled stratified graph (LSG) introduces some method of knowledge representation. The inference process developed for this structures uses the paths of the stratified graphs, an order between the elementary arcs of a path and some results of universal algebras. The order is defined by considering a structured path instead of a regular path. The application described in this paper interprets the symbolic elements of a LSG with natural language constructions. In this manner we obtained a mechanism for generation coherent texts in a natural language (for this approach, Romanian). The generation method is based on labeled stratified graph representation and the inference mechanism is guided by the structured paths of these representations.

Guru

2012 ◽  
pp. 156-171 ◽  
Author(s):  
Andrew M. Olney ◽  
Natalie K. Person ◽  
Arthur C. Graesser
Keyword(s):  
Natural Language Processing ◽  
Knowledge Representation ◽  
Natural Language ◽  
Language Processing ◽  
Natural Language Understanding ◽  
Natural Language Generation ◽  
Language Understanding ◽  
Language Generation ◽  
Processing Techniques

The authors discuss Guru, a conversational expert ITS. Guru is designed to mimic expert human tutors using advanced applied natural language processing techniques including natural language understanding, knowledge representation, and natural language generation.

scholarly journals The Rare Word Issue in Natural Language Generation: A Character-Based Solution

Informatics ◽  
2021 ◽  
Vol 8 (1) ◽  
pp. 20
Author(s):  
Giovanni Bonetta ◽  
Marco Roberti ◽  
Rossella Cancelliere ◽  
Patrick Gallinari
Keyword(s):  
Natural Language ◽  
Error Probability ◽  
Essential Feature ◽  
Proper Names ◽  
Neural Model ◽  
Natural Language Generation ◽  
Training Phase ◽  
Tabular Data ◽  
Rare Word ◽  
Language Generation

In this paper, we analyze the problem of generating fluent English utterances from tabular data, focusing on the development of a sequence-to-sequence neural model which shows two major features: the ability to read and generate character-wise, and the ability to switch between generating and copying characters from the input: an essential feature when inputs contain rare words like proper names, telephone numbers, or foreign words. Working with characters instead of words is a challenge that can bring problems such as increasing the difficulty of the training phase and a bigger error probability during inference. Nevertheless, our work shows that these issues can be solved and efforts are repaid by the creation of a fully end-to-end system, whose inputs and outputs are not constrained to be part of a predefined vocabulary, like in word-based models. Furthermore, our copying technique is integrated with an innovative shift mechanism, which enhances the ability to produce outputs directly from inputs. We assess performance on the E2E dataset, the benchmark used for the E2E NLG challenge, and on a modified version of it, created to highlight the rare word copying capabilities of our model. The results demonstrate clear improvements over the baseline and promising performance compared to recent techniques in the literature.

Sign in / Sign up

Export Citation Format

Share Document