scholarly journals Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

2018 ◽  
Vol 61 ◽  
pp. 65-170 ◽  
Author(s):  
Albert Gatt ◽  
Emiel Krahmer
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Data Driven ◽  
Research Topics ◽  
Language Generation ◽  
The Past ◽  
Current State ◽  
Linguistic Input ◽  
New Applications

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artificial intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of NLP, with an emphasis on different evaluation methods and the relationships between them.

scholarly journals SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

2018 ◽  
Author(s):  
Ke Wang ◽  
Xiaojun Wan
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Poor Quality ◽  
Experimental Results ◽  
Text Generation ◽  
Language Generation ◽  
Adversarial Networks

Generating texts of different sentiment labels is getting more and more attention in the area of natural language generation. Recently, Generative Adversarial Net (GAN) has shown promising results in text generation. However, the texts generated by GAN usually suffer from the problems of poor quality, lack of diversity and mode collapse. In this paper, we propose a novel framework - SentiGAN, which has multiple generators and one multi-class discriminator, to address the above problems. In our framework, multiple generators are trained simultaneously, aiming at generating texts of different sentiment labels without supervision. We propose a penalty based objective in the generators to force each of them to generate diversified examples of a specific sentiment label. Moreover, the use of multiple generators and one multi-class discriminator can make each generator focus on generating its own examples of a specific sentiment label accurately. Experimental results on four datasets demonstrate that our model consistently outperforms several state-of-the-art text generation methods in the sentiment accuracy and quality of generated texts.

scholarly journals Acquiring Correct Knowledge for Natural Language Generation

2003 ◽  
Vol 18 ◽  
pp. 491-516 ◽  
Author(s):  
E. Reiter ◽  
S. G. Sripada ◽  
R. Robertson
Keyword(s):  
Natural Language ◽  
Computer Software ◽  
Natural Language Generation ◽  
Software Systems ◽  
Language Generation ◽  
Correct Knowledge ◽  
General Terms ◽  
Linguistic Input ◽  
Robust Systems

Natural language generation (NLG) systems are computer software systems that produce texts in English and other human languages, often from non-linguistic input data. NLG systems, like most AI systems, need substantial amounts of knowledge. However, our experience in two NLG projects suggests that it is difficult to acquire correct knowledge for NLG systems; indeed, every knowledge acquisition (KA) technique we tried had significant problems. In general terms, these problems were due to the complexity, novelty, and poorly understood nature of the tasks our systems attempted, and were worsened by the fact that people write so differently. This meant in particular that corpus-based KA approaches suffered because it was impossible to assemble a sizable corpus of high-quality consistent manually written texts in our domains; and structured expert-oriented KA techniques suffered because experts disagreed and because we could not get enough information about special and unusual cases to build robust systems. We believe that such problems are likely to affect many other NLG systems as well. In the long term, we hope that new KA techniques may emerge to help NLG system builders. In the shorter term, we believe that understanding how individual KA techniques can fail, and using a mixture of different KA techniques with different strengths and weaknesses, can help developers acquire NLG knowledge that is mostly correct.

Suggesting Error Corrections of Path Expressions and Categories for Tree-Mapping Grammars

2007 ◽  
Vol 26 (2) ◽  
Author(s):  
Tim Vor Der Brück ◽  
Stephan Busemann
Keyword(s):  
Natural Language ◽  
Natural Language Generation ◽  
Derivation Tree ◽  
Grammar Rule ◽  
Language Generation ◽  
Error Corrections ◽  
Grammar Rules ◽  
Linguistic Input ◽  
The Given ◽  
Grammar Development

AbstractTree mapping grammars are used in natural language generation (NLG) to map non-linguistic input onto a derivation tree from which the target text can be trivially read off as the terminal yield. Such grammars may consist of a large number of rules. Finding errors is quite tedious and sometimes very time-consuming. Often the generation fails because the relevant input subtree is not specified correctly. This work describes a method to detect and correct wrong assignments of input subtrees to grammar categories by cross-validating grammar rules with the given input structures. The method also detects and corrects the usage of a category in a grammar rule. The result is implemented in a grammar development workbench and accelerates the grammar writer's work considerably. The paper suggests the algorithms can be ported to other areas in which tree mapping is required.

scholarly journals Natural language generation: The commercial state of the art in 2020

2020 ◽  
Vol 26 (4) ◽  
pp. 481-487
Author(s):  
Robert Dale
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Commercial Software ◽  
Language Generation ◽  
The Future ◽  
Mainstream Press

AbstractIt took a while, but natural language generation is now an established commercial software category. It’s commented upon frequently in both industry media and the mainstream press, and businesses are willing to pay hard cash to take advantage of the technology. We look at who’s active in the space, the nature of the technology that’s available today and where things might go in the future.

scholarly journals Hierarchical Attention Networks for Sentence Ordering

2019 ◽  
Vol 33 ◽  
pp. 7184-7191
Author(s):  
Tianming Wang ◽  
Xiaojun Wan
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Attention Network ◽  
Attention Networks ◽  
Language Generation ◽  
Visualization Analysis ◽  
Discourse Coherence ◽  
Model Visualization

Modeling discourse coherence is an important problem in natural language generation and understanding. Sentence ordering, the goal of which is to organize a set of sentences into a coherent text, is a commonly used task to learn and evaluate the model. In this paper, we propose a novel hierarchical attention network that captures word clues and dependencies between sentences to address this problem. Our model outperforms prior methods and achieves state-of-the-art performance on several datasets in different domains. Furthermore, our experiments demonstrate that the model performs very well even though adding noisy sentences into the set, which shows the robustness and effectiveness of the model. Visualization analysis and case study show that our model captures the structure and pattern of coherent texts not only by simple word clues but also by consecution in context.

Sign in / Sign up

Export Citation Format

Share Document