TEASPN: Framework and Protocol for Integrated Writing Assistance Environments

Abstract

Language technologies play a key role in assisting people with their writing. Although there has been steady progress in e.g., grammatical error correction (GEC), human writers are yet to benefit from this progress due to the high development cost of integrating with writing software. We propose TEASPN 1 , a protocol and an open-source framework for achieving integrated writing assistance environments. The protocol standardizes the way writing software communicates with servers that implement such technologies, allowing developers and researchers to integrate the latest developments in natural language processing (NLP) with low cost. As a result, users can enjoy the integrated experience in their favorite writing software. The results from experiments with human participants show that users use a wide range of technologies and rate their writing experience favorably, allowing them to write more fluent text.

A Design Space for Intelligent and Interactive Writing Assistants

“…A key compatibility issue to consider is usability consistency, i.e., the extent to which the writing assistant's user experience intentionally aligns with other systems in the writer's ecosystem. Examples in the corpus include integrating AI language technologies into everyday writing apps [96], extending Google Docs [247], and using familiar-looking BibTeX style codes to enable writers to invoke remote bibliographic searches [10]. This example also illustrates technical interoperability with external services, which designers may conceive in many ways.…”

On the Social and Technical Challenges of Web Search Autosuggestion Moderation

“…General Purpose Assistive Writing. More broadly, predictive text suggestions are used to assist users in any writing environment (Arnold, Gajos, and Kalai 2016;Hagiwara et al 2019), including by making re-writing suggestions that make writing more concise and inclusive (BBC 2019). Yet, due to the linguistic and social complexities of natural language that also affect the search query suggestions, such assistive writing systems can and have similarly failed to account for e.g., socio-cultural sensitivities (Scott 2019).…”

Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover

“…These advances already led to a more comprehensive use of language in a great number of research areas and consumer-oriented applications, as for example in the analysis of biomedical literature (Beltagy, Lo & Cohan, 2019), the generation of EEG reports (Biswal et al, 2019), the development of more advanced chatbots (Budzianowski & Vulić, 2019) and the improvement of grammar-and writing-assistance (Hagiwara et al, 2019). However, this newly-gained quality of generated language also increased the fear of its potential abuse by malicious actors (Solaiman et al, 2019).…”