An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

https://www.cs.cornell.edu/home/halpern/papers/awareness.pdf

Belief, awareness, and limited reasoning

As part of an on-going project to understand the foundations of Knowledge Representation, we are attempting to characterize a kind of belief that forms a more appropriate basis for Knowledge Representation systems than that captured by the usual possible-world formalizations begun by Hintikka. In this paper, we point out deficiencies in current semantic treatments of knowledge and belief (including recent syntactic approaches) and suggest a new analysis in the form of a logic that avoids these shortcomings and is also more viable computationally.

/pdf/a-logic-of-implicit-and-explicit-belief-72fkkmw682.pdf

A logic of implicit and explicit belief

A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Using context information to facilitate processing of commands in a virtual assistant

TEAM: an experiment in the design of transportable natural-language interfaces

The problem addressed in this paper is how to enable a computer system to acquire facts about new domains from tutors who are experts in their respective fields, but who have little or no training in computer science. The information to be acquired is that needed to support question-answering activities. The basic acquisition approach is "learning by being told." We have been especially interested in exploring the notion of simultaneously learning not only new concepts, but also the linguistic constructions used to express those concepts. As a research vehicle we have developed a system that is preprogrammed with deductive algorithms and a fixed set of syntactic/semantic rules covering a small subset of English. It has been endowed with sufficient seed concepts and seed vocabulary to support effective tutorial interaction. Furthermore, the system is capable of learning new concepts and vocabulary, and can apply its acquired knowledge in a prescribed range of problem-solving situations.

/pdf/an-approach-to-acquiring-and-applying-knowledge-1w80tc5ce9.pdf

An approach to acquiring and applying knowledge

Natural-language (NL) interfaces built so far have primarily addressed the problem of accessing information stored in conventional data base systems. Among the proven capabilities exhibited by these systems are those that: • Provide reasonably good NL access to specific data bases • Access multiple, remote data bases. • Answer direct questions. ( \"What is Smith's salary?\") • Coordinate multiple files. ( \"Wha t is Smith's loca t ion?\" translates into \"W ha t is the location of the depar tment of Smith?.\") • Handle simple uses of pronouns. • Handle many elliptical inputs. ( \"Where is John? Sam?\") • Do basic report generation. ( \"By sex and age, list the salary and title of employees in New York.\") • Extend linguistic coverage at run time. (Define \" J D \" as \" Je f f e r son Davis Jones\" Le t \"Q1 Smith salary\" be like \"What is the salary of employee Smith? . . . . Q1 JD A G E ? \" ) • Analyze NULL answers. ( \" H o w many Japanese carriers have inoperative air search radar?\" Response: \"The re are no Japanese carriers.\") • Restate in English the system's in terpreta t ion of inputs. ~. Correct spelling errors. • Enhance the data in a data base with special-purpose functions. (E.g., calculate distances between cities.)

Natural-language interface

: Several computer systems have now been constructed that allow users to access databases by posing questions in natural languages, such as English. When used in the restricted domains for which they have been especially designed, these systems have achieved reasonably high levels of performance. However, these systems require the encoding of knowledge about the domain of application in complex data structures that typically can be created for a new database only with considerable effort on the part of a computer professional who has had special training in computational linguistics and the use of databases. This paper describes initial work on a methodology for creating natural-language processing capabilities for new databases without the need for intervention by specially trained experts. The approach is to acquire logical schemata and lexical information through simple interactive dialogues with someone who is familiar with the form and content of the database, but unfamiliar with the technology of natural-language interfaces. A prototype system using this methodology is described and an example transcript is presented.

Transportable natural-language interfaces to databases

This note describes LIFER, a practical facility for creating natural language interfaces to other computer software. Emphasizing human engineering, LIFER has bundled natural language specification and parsing technology into one convenient package.

Lifer: a natural language interface facility

The DIALOGIC system translates English sentences into representations of their literal meaning in the context of an utterance. These representations, or "logical forms," are intended to be a purely formal language that is as close as possible to the structure of natural language, while providing the semantic compositionality necessary for meaning-dependent computational processing. The design of DIALOGIC (and of its constituent modules) was influenced by the goal of using it as the core language-processing component in a variety of systems, some of which are transportable to new domains of application.

/pdf/dialogic-a-core-natural-language-processing-system-2kwqe142x8.pdf

Gary G. Hendrix

Papers

An approach to acquiring and applying knowledge

Natural-language interface

Transportable natural-language interfaces to databases

Lifer: a natural language interface facility

DIALOGIC: a core natural-language processing system