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.

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.

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 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.

ProBot – A Procedure Chatbot for Digital Procedural Adherence

2020 ◽  
Vol 64 (1) ◽  
pp. 224-228
Author(s):  
Nilesh Ade ◽  
Noor Quddus ◽  
Trent Parker ◽  
S.Camille Peres
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Natural Language ◽  
Industry 4.0 ◽  
Natural Language Generation ◽  
Conversational Agent ◽  
Safe Distance ◽  
Process Industries ◽  
Language Generation ◽  
Plastic Pellets

One of the major implications of Industry 4.0 will be the application of digital procedures in process industries. Digital procedures are procedures that are accessed through a smart gadget such as a tablet or a phone. However, like paper-based procedures their usability is limited by their access. The issue of accessibility is magnified in tasks such as loading a hopper car with plastic pellets wherein the operators typically place the procedure at a safe distance from the worksite. This drawback can be tackled in the case of digital procedures using artificial intelligence-based voice enabled conversational agent (chatbot). As a part of this study, we have developed a chatbot for assisting digital procedure adherence. The chatbot is trained using the possible set of queries from the operator and text from the digital procedures through deep learning and provides responses using natural language generation. The testing of the chatbot is performed using a simulated conversation with an operator performing the task of loading a hopper car.

Sign in / Sign up

Export Citation Format

Share Document