This chapter provides an overview of the technologies used for chatbots on the one hand and research dialog systems on the other hand. By comparing the two, the main disadvantage of chatbots is shown: its dependency on huge amounts of inflexible language data. Methods originating from Computational Linguistics, which are frequently used in dialog systems, can provide a solution by offering further flexibility to the language processing part of the system.
This paper presents an implemented hybrid approach to grammar and style checking, combining an industrial patternbased grammar and style checker with bidirectional, large-scale HPSG grammars for German and English. Under this approach, deep processing is applied selectively based on the error hypotheses of a shallow system. We have conducted a comparative evaluation of the two components, supporting an integration scenario where the shallow system is best used for error detection, whereas the HPSG grammars add error correction for both grammar and controlled language style errors.
The reading of text resources in scholarly settings can take various forms. Each form provides scholars with different insights that complement each other. The first findings from an ongoing series of interviews on scholarly annotation practices suggest that users are aware of the various forms of reading, but they are reluctant to use automatic annotations and still rely on conventional tools. In this paper, we introduce a prototype of annotation software that aims to interrelate different types of reading synergistically by employing a mixed-initiative approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.