Human computer interaction (HCI) is an important aspect that should concern every computer system. Ubiquitous computing applications and many other complex applications calls for an interface that have more than simple selection of couple of options. Consequently we need computer interfaces which can, if not eliminate; at least reduce the need of resources for training i.e. natural language interface (NLI) is required. Natural language processing (NLP) can prove helpful in natural language interfaces. Since such applications' interface designs do not call for deep natural language processing; such interfaces can benefit from the layered natural language processing architecture that we would present for designing natural language interfaces.
Keywords: Human Computer Interfaces, Ubiquitous Computing, Natural Language Interfaces, Natural Language Processing, NLP stack
[...] the 34th Annual Meeting of the Association for Computational Linguistics G Perlman, Natural artificial languages: low level processes, International Journal of Man-Machine Studies 373- References K Samuel, Dialogue Act Tagging with Transformation-Based Learning, In Proc of the 17th International Conference on Computational Linguistics J Allen, Natural Language Understanding, Benjamin Cummings A W Biermann, B W Ballard, and A H Sigmon, An experimental study of natural language programming. International Journal of Man-Machine Studies F J Damerau, Operating statistics for the transformational question answering system. [...]
[...] Spoken dialogue allows another channel of communication with the computer Hands-free, eyes-free: Spoken language may be the only available mode in operational environments because it may be desirable to have the hands and eyes free Reduction in training cost: NLI can dramatically reduce the cost of delivering training by decreasing learning time and the need for expensive and dedicated training equipments Increased computer literacy: Lack of computer literacy can be overcome by the use of natural language interfaces. A. Automatic Speech Recognition (ASR) The front-end to the NLI is a speech recognizer. [...]
[...] Natural language processing can benefit from a reliable, long-range-context-dependent representation of the meaning of each lexeme that appears in a given sentence. This layer should use a technique that produces a context-dependent ‘meaning' representation for a lexeme in a specific surrounding context. This layer is also responsible for considering constraints about what can be expressed within the language without elaboration, and determines the processing details that users may leave out of their expressions. While higher layer determines what can be expressed, this layer determines how it can be expressed. [...]
[...] Natural language processing (NLP) holds great promise for making computer interfaces that are easier to use for people because people can communicate in natural language rather than learning a specialized language of computer commands. But compressive or deep NLP is not demanded by the human computer interface (HCI) because NLI is the dialogue based exchange of information rather than complex conversation in natural language and thus NLI are designed to use constrained language in the particular domain. The area of NLI is a great filed for using NLP because the goal of being able to process natural languages has always been a bit of siren's call and has a certain note of purity about it and many researchers believe that understanding and processing natural language perfectly is not possible. [...]
Online readingwith our online reader
Content validatedby our reading committee