Natural Language Generation

Notes:

In a natural language generation (NLG) system, the morphological generator is a component that is responsible for post-processing the generated text to ensure that it is grammatically correct and conforms to the rules of the target language. This can involve tasks such as adding appropriate inflection and agreement to words, selecting the correct tense and aspect, and ensuring that the generated text is properly punctuated and formatted.

The morphological generator is an essential component of any NLG system, as it ensures that the generated text is fluent and natural-sounding. Without the post-processing performed by the morphological generator, the generated text may be difficult to understand or may contain errors that could make it appear unnatural or ungrammatical. By adding the appropriate inflection and agreement to the generated text, the morphological generator helps to make the NLG system more accurate and effective.

One of the key requirements for natural language generation (NLG) systems is that they should be application-independent, meaning that they should be able to operate as part of a generic dialog system platform. This is important because it allows NLG systems to be used in a wide range of applications, without the need for custom development or integration.

Being application-independent means that an NLG system should be able to operate without being specifically designed or tailored for a particular application or domain. Instead, the NLG system should be able to generate natural language text based on a generic set of input data, without requiring any specific knowledge or expertise about the application or domain. This allows the NLG system to be integrated into a variety of different dialog system platforms, and to be used in a wide range of applications, from virtual assistants and customer service bots, to educational tools and games.

The ACL Special Interest Group on Natural Language Generation (SIGGEN) is a group within the Association for Computational Linguistics (ACL) that focuses on the field of natural language generation (NLG). NLG is the technology that enables computers to produce text that is fluent, natural-sounding, and appropriate to the intended context. SIGGEN is dedicated to advancing the state of the art in NLG, and to promoting research and development in this field.

SIGGEN is a community of researchers, developers, and practitioners who are interested in NLG. The group hosts events, workshops, and conferences on NLG, and provides a forum for the exchange of ideas and information about NLG research and development. SIGGEN also publishes a newsletter and maintains a mailing list for members to stay up-to-date on the latest developments in the field.

Resources:

2txt.de .. automates the creation of advisory and promotional e-commerce texts
arria.com .. robust yet easy-to-use nlg design tool
articoolo.com .. create unique textual content in a flash
ax-semantics.com .. software that writes your texts
cogentex.com .. software that turns your data into fluent, readable text
conversica.com .. conversational ai software for marketing and sales
linguastat.com .. automatically manages optimized, unique product descriptions
narrativewave.com .. provides data-to-decision analytics for industrial iot
narrativa.com .. computer generated content
newsrx.com .. research and alerts on industries and sectors
phrasee.co .. ai that writes better subject lines
phrasetech.com .. automated text creation, control and optimization
phrazor.ai .. ai-powered data stories
retresco.de .. ai-driven content automation
textual.ai .. create, translate and optimize product descriptions
vphrase.com .. helps data tell it’s story, in words

Wikipedia:

References:

A Repository of Data and Evaluation Resources for Natural Language Generation (2012)
DEXTOR: Reduced Effort Authoring for Template-Based Natural Language Generation (2011)
How I automated my writing career (2011)
Incremental Semantics Driven Natural Language Generation With Self-Repairing Capability (2011)
Natural Language Generation from Class Diagrams (2011)
Optimising Natural Language Generation Decision Making for Situated Dialogue (2011)
Reinforcement Learning for Adaptive Dialogue Systems: A Data-Driven Methodology for Dialogue Management and Natural Language Generation (2011)
Text Modification Methods for Natural Language Generation (2011)
A Unifying View of Computational Discourse and Natural Language Generation (2010)
Data-driven Natural Language Generation: Making Machines Talk Like Humans Using Natural Corpora (2010)
Empirical Methods in Natural Language Generation (2010)
HYPERBUG: A Scalable Natural Language Generation Approach (2010)
INLG 2010: Proceedings of the Sixth International Natural Language Generation Conference, Trim, Ireland
Model driven development approach to natural language generation systems (2010)
NLGen2: a linguistically plausible, general purpose natural language generation system (2010)
A Hybrid Tree Framework for Semantic Parsing and Natural Language Generation (2009)
Engagement vs. Deceit: Virtual Humans with Human Autobiographies (2009)
MOUNTAIN: A translation-based approach to natural language generation for dialog systems (2009)
Statistical Natural Language Generation as Planning (2009)