3 Search Results for "Gao, Tiantian"


Document
Knowledge Authoring and Question Answering via Controlled Natural Language

Authors: Tiantian Gao

Published in: OASIcs, Volume 64, Technical Communications of the 34th International Conference on Logic Programming (ICLP 2018)


Abstract
Knowledge acquisition from text is the process of automatically acquiring, organizing and structuring knowledge from text which can be used to perform question answering or complex reasoning. However, current state-of-the-art systems are limited by the fact that they are not able to construct the knowledge base with high quality as knowledge representation and reasoning (KRR) has a keen requirement for the accuracy of data. Controlled Natural Languages (CNLs) emerged as a technology to author knowledge using a restricted subset of English. However, they still fail to do so as sentences that express the same information may be represented by different forms. Current CNL systems have limited power to standardize sentences that express the same meaning into the same logical form. We solved this problem by building the Knowledge Authoring Logic Machine (KALM), which is a technology for domain experts who are not familiar with logic to author knowledge using CNL. The system performs semantic analysis of English sentences and achieves superior accuracy of standardizing sentences that express the same meaning to the same logical representation. Besides, we developed the query part of KALM to perform question answering, which also achieves very high accuracy in query understanding.

Cite as

Tiantian Gao. Knowledge Authoring and Question Answering via Controlled Natural Language. In Technical Communications of the 34th International Conference on Logic Programming (ICLP 2018). Open Access Series in Informatics (OASIcs), Volume 64, pp. 21:1-21:8, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{gao:OASIcs.ICLP.2018.21,
  author =	{Gao, Tiantian},
  title =	{{Knowledge Authoring and Question Answering via Controlled Natural Language}},
  booktitle =	{Technical Communications of the 34th International Conference on Logic Programming (ICLP 2018)},
  pages =	{21:1--21:8},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-090-3},
  ISSN =	{2190-6807},
  year =	{2018},
  volume =	{64},
  editor =	{Dal Palu', Alessandro and Tarau, Paul and Saeedloei, Neda and Fodor, Paul},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ICLP.2018.21},
  URN =		{urn:nbn:de:0030-drops-98870},
  doi =		{10.4230/OASIcs.ICLP.2018.21},
  annote =	{Keywords: Knowledge Authoring, Question Answering, Controlled Natural Language}
}
Document
Achieving High Quality Knowledge Acquisition using Controlled Natural Language

Authors: Tiantian Gao

Published in: OASIcs, Volume 58, Technical Communications of the 33rd International Conference on Logic Programming (ICLP 2017)


Abstract
Controlled Natural Languages (CNLs) are efficient languages for knowledge acquisition and reasoning. They are designed as a subset of natural languages with restricted grammar while being highly expressive. CNLs are designed to be automatically translated into logical representations, which can be fed into rule engines for query and reasoning. In this work, we build a knowledge acquisition machine, called KAM, that extends Attempto Controlled English (ACE) and achieves three goals. First, KAM can identify CNL sentences that correspond to the same logical representation but expressed in various syntactical forms. Second, KAM provides a graphical user interface (GUI) that allows users to disambiguate the knowledge acquired from text and incorporates user feedback to improve knowledge acquisition quality. Third, KAM uses a paraconsistent logical framework to encode CNL sentences in order to achieve reasoning in the presence of inconsistent knowledge.

Cite as

Tiantian Gao. Achieving High Quality Knowledge Acquisition using Controlled Natural Language. In Technical Communications of the 33rd International Conference on Logic Programming (ICLP 2017). Open Access Series in Informatics (OASIcs), Volume 58, pp. 13:1-13:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{gao:OASIcs.ICLP.2017.13,
  author =	{Gao, Tiantian},
  title =	{{Achieving High Quality Knowledge Acquisition using Controlled Natural Language}},
  booktitle =	{Technical Communications of the 33rd International Conference on Logic Programming (ICLP 2017)},
  pages =	{13:1--13:10},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-058-3},
  ISSN =	{2190-6807},
  year =	{2018},
  volume =	{58},
  editor =	{Rocha, Ricardo and Son, Tran Cao and Mears, Christopher and Saeedloei, Neda},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ICLP.2017.13},
  URN =		{urn:nbn:de:0030-drops-84645},
  doi =		{10.4230/OASIcs.ICLP.2017.13},
  annote =	{Keywords: Logic Programming, Controlled Natural Languages, Knowledge Acquisition}
}
Document
Controlled Natural Languages for Knowledge Representation and Reasoning

Authors: Tiantian Gao

Published in: OASIcs, Volume 52, Technical Communications of the 32nd International Conference on Logic Programming (ICLP 2016)


Abstract
Controlled natural languages (CNLs) are effective languages for knowledge representation and reasoning. They are designed based on certain natural languages with restricted lexicon and grammar. CNLs are unambiguous and simple as opposed to their base languages. They preserve the expressiveness and coherence of natural languages. In this paper, it mainly focuses on a class of CNLs, called machine-oriented CNLs, which have well-defined semantics that can be deterministically translated into formal languages to do logical reasoning. Although a number of machine-oriented CNLs emerged and have been used in many application domains for problem solving and question answering, there are still many limitations: First, CNLs cannot handle inconsistencies in the knowledge base. Second, CNLs are not powerful enough to identify different variations of a sentence and therefore might not return the expected inference results. Third, CNLs do not have a good mechanism for defeasible reasoning. This paper addresses these three problems and proposes a research plan for solving these problems. It also shows the current state of research: a paraconsistent logical framework from which six principles that guide the user to encode CNL sentences were created. Experiment results show this paraconsistent logical framework and these six principles can consistently and effectively solve word puzzles with injections of inconsistencies.

Cite as

Tiantian Gao. Controlled Natural Languages for Knowledge Representation and Reasoning. In Technical Communications of the 32nd International Conference on Logic Programming (ICLP 2016). Open Access Series in Informatics (OASIcs), Volume 52, pp. 19:1-19:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)


Copy BibTex To Clipboard

@InProceedings{gao:OASIcs.ICLP.2016.19,
  author =	{Gao, Tiantian},
  title =	{{Controlled Natural Languages for Knowledge Representation and Reasoning}},
  booktitle =	{Technical Communications of the 32nd International Conference on Logic Programming (ICLP 2016)},
  pages =	{19:1--19:10},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-007-1},
  ISSN =	{2190-6807},
  year =	{2016},
  volume =	{52},
  editor =	{Carro, Manuel and King, Andy and Saeedloei, Neda and De Vos, Marina},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.ICLP.2016.19},
  URN =		{urn:nbn:de:0030-drops-67487},
  doi =		{10.4230/OASIcs.ICLP.2016.19},
  annote =	{Keywords: Controlled Natural Languages, Paraconsistent Logics, Defeasible Reasoning}
}
  • Refine by Author
  • 3 Gao, Tiantian

  • Refine by Classification
  • 1 Computing methodologies → Knowledge representation and reasoning
  • 1 Computing methodologies → Natural language processing

  • Refine by Keyword
  • 2 Controlled Natural Languages
  • 1 Controlled Natural Language
  • 1 Defeasible Reasoning
  • 1 Knowledge Acquisition
  • 1 Knowledge Authoring
  • Show More...

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 2 2018
  • 1 2016

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail