Realization of natural language interfaces using lazy functional programming

Frost, Richard A.

doi:10.1145/1177352.1177353

Cited by 12 publications

(3 citation statements)

References 93 publications

(75 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem has motivated studies in Natural Language Interfaces (NLI), those allow machine-processing of natural language "requests", without explicit need in part of the system users to transform the requests into system-language "queries". Frost (2006) provides a survey of the NLI techniques and recent developments in the field of NLI. The systemic aspect of improving precision involves improving the capabilities of the IR systems and is the subject matter of the field of Information Retrieval (IR) and its sub-field Information Filtering (Belkin and Croft 1992, Faloutsos and Oard 1995, Mostafa et al 1997, Greengrass 2000.…”

Section: Working Efficiently With Relevant Information: the Meta-requ...mentioning

confidence: 99%

On Challenges and Opportunities of Designing Integrated IT Platforms for Supporting Knowledge Works in Organizations

Laha¹

2011

Vikalpa

View full text Add to dashboard Cite

Designing and implementing comprehensive IT-based support environments for KM in organizations is fraught with many problems. Solving them requires intimate knowledge about the information usage in knowledge works and the scopes of technology intervention. In this paper, the Task-oriented Organizational Knowledge Management or TOKM, a design theory for building integrated IT platforms for supporting organizational KM, is proposed. TOKM brings together two apparently mutually exclusive practices of building KM systems, the task-based approach and the generic or universalistic approach. In developing the design, the information requirements of knowledge workers in light of an information usage model of knowledge works is studied. Then the model is extended to study possibilities of more advanced IT support and formulate them in form of a set of meta-requirements. Following the IS design theory paradigm, a set of artifacts are hypothesized to meet the requirements. Finally, a design method, as a possible approach of building an IT-based integrated platform, the Knowledge Work Support Platform (KWSP) to realize the artifacts in order to meet the requirements, is outlined. The KWSP is a powerful platform for building and maintaining a number of task-type specific Knowledge Work Support Systems (KWSS) on a common sharable platform. Each KWSS, for the task-type supported by it, can be easily designed to provide extensive and sophisticated support to individual as well as group of knowledge workers in performing their respective knowledge work instances. PRELIMINARIESThe theory, TOKM, deals at its core with the issues related to information usage in knowledge works, i.e., how does human knowledge workers use information and how the related processes can be supported effectively by technology interventions. The concepts I shall build upon, though might have originated in myriads of disciplines, I shall mostly draw upon them as available through the literature of the three fields of studies related in different ways to information, namely the information systems, the information science and the information technology. Readers interested in deeper exploration of the concepts/issues can use the "references" sections of the referred articles to further their quest. Handling InformationAll the three fields, information system, information science and information technology have "information" as their central themes. Nevertheless, despite significant overlaps, each of these fields has its own distinct perspective, goal and even lexicon, which render subtle but significantly different semantic to same or similar terms. In the following we shall discuss various aspects of each of them relevant to our discourse.

show abstract

Section: Working Efficiently With Relevant Information: the Meta-requ...mentioning

confidence: 99%

On Challenges and Opportunities of Designing Integrated IT Platforms for Supporting Knowledge Works in Organizations

Laha¹

2011

Vikalpa

View full text Add to dashboard Cite

show abstract

“…Functional programming languages have a strong foothold in compiler construction, because they are well adapted for manipulating linguistic structures such as syntax trees (Appel 1998). Haskell has also been acknowledged as a language suitable for natural language processing (Forsberg and Ranta 2004; Doets and van Eijck 2004; Frost 2006). The relation between Haskell and GF is to some extent similar to the relation between Prolog and unification grammar formalisms.…”

Section: Introductionmentioning

confidence: 99%

GF: A Multilingual Grammar Formalism

Ranta

2009

Language and Linguist. Compass

View full text Add to dashboard Cite

GF (Grammatical Framework) is a grammar formalism designed for dealing with many languages simultaneously. A multilingual GF grammar has a language‐independent abstract syntax that deals with pure tree structures, and a set of language‐dependent concrete syntaxes that specify how the trees are expressed in different languages. Multilingual grammars formalize the idea that the same grammatical categories (such as noun phrases and verb phrases) and syntax rules (such as predication) can appear in different languages. They are also a powerful tool for natural language engineering, used for applications ranging from a translator of mathematical exercises to a dialogue system usable for talking with devices in a car. As a programming language, GF has constructs inherited from functional programming languages, an optimizing grammar compiler and code generation into several other formats. The most ambitious multilingual grammar is the GF Resource Grammar Library, which implements the main grammar rules of 12 languages. This library enables non‐linguist programmers to build linguistically correct applications. It is at the same time a linguistic experiment showing how far one can go in sharing structure between languages.

show abstract

“…Finally, it will use the learned grammar to generate English sentences as responses. Instead of focusing on the formal language models [9] for English, we are more concerned with learning the various grammar terms in English: such as sentence, complete subject, verb, noun phrase, and preposition. There are four major components for each grammar term: structure, role, kind, and rule.…”

Section: Introductionmentioning

confidence: 99%

A multi-dimensional data organization for natural language processing

Cheng

Faris

2009

JCM

View full text Add to dashboard Cite

For knowledge systems that rely on teachings from an outside source to gain their knowledge, proper data organizations are instrumental in managing and applying what has been learned. This paper describes the development of a Multi-Dimensional Data Organization (MDDO). Our MDDO stores a collection of knowledge of the same category classified by multiple orthogonal dimensions. Each dimension has a number of indices reflecting the potential attribute values of that dimension. A knowledge object is identified by a unique combination of indices from multiple dimensions whose values signify the different properties of the object itself. Our solution allows the collection of knowledge to be learned dynamically in any order and in an incremental manner. This MDDO has been used to store part of the English grammar, and we describe in this paper how it assists a learning program in both the parsing and the production of an English sentence. We also define the functionalities of the data organization, describe its organization, describe how each function is implemented, and analyze their worst-case performances.

show abstract

Realization of natural language interfaces using lazy functional programming

Cited by 12 publications

References 93 publications

On Challenges and Opportunities of Designing Integrated IT Platforms for Supporting Knowledge Works in Organizations

On Challenges and Opportunities of Designing Integrated IT Platforms for Supporting Knowledge Works in Organizations

GF: A Multilingual Grammar Formalism

A multi-dimensional data organization for natural language processing

Contact Info

Product

Resources

About