Search Results

Documents authored by Bennett, Brandon


Document
Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning

Authors: Suk Joon Hong and Brandon Bennett

Published in: OASIcs, Volume 93, 3rd Conference on Language, Data and Knowledge (LDK 2021)


Abstract
The Winograd Schema Challenge (WSC) is a commonsense reasoning task that requires background knowledge. In this paper, we contribute to tackling WSC in four ways. Firstly, we suggest a keyword method to define a restricted domain where distinctive high-level semantic patterns can be found. A thanking domain was defined by keywords, and the data set in this domain is used in our experiments. Secondly, we develop a high-level knowledge-based reasoning method using semantic roles which is based on the method of Sharma [Sharma, 2019]. Thirdly, we propose an ensemble method to combine knowledge-based reasoning and machine learning which shows the best performance in our experiments. As a machine learning method, we used Bidirectional Encoder Representations from Transformers (BERT) [Jacob Devlin et al., 2018; Vid Kocijan et al., 2019]. Lastly, in terms of evaluation, we suggest a "robust" accuracy measurement by modifying that of Trichelair et al. [Trichelair et al., 2018]. As with their switching method, we evaluate a model by considering its performance on trivial variants of each sentence in the test set.

Cite as

Suk Joon Hong and Brandon Bennett. Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning. In 3rd Conference on Language, Data and Knowledge (LDK 2021). Open Access Series in Informatics (OASIcs), Volume 93, pp. 41:1-41:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)


Copy BibTex To Clipboard

@InProceedings{hong_et_al:OASIcs.LDK.2021.41,
  author =	{Hong, Suk Joon and Bennett, Brandon},
  title =	{{Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning}},
  booktitle =	{3rd Conference on Language, Data and Knowledge (LDK 2021)},
  pages =	{41:1--41:13},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-199-3},
  ISSN =	{2190-6807},
  year =	{2021},
  volume =	{93},
  editor =	{Gromann, Dagmar and S\'{e}rasset, Gilles and Declerck, Thierry and McCrae, John P. and Gracia, Jorge and Bosque-Gil, Julia and Bobillo, Fernando and Heinisch, Barbara},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.LDK.2021.41},
  URN =		{urn:nbn:de:0030-drops-145779},
  doi =		{10.4230/OASIcs.LDK.2021.41},
  annote =	{Keywords: Commonsense Reasoning, Winograd Schema Challenge, Knowledge-based Reasoning, Machine Learning, Semantics}
}
Document
Classification, Individuation and Demarcation of Forests: Formalising the Multi-Faceted Semantics of Geographic Terms

Authors: Lucía Gómez Álvarez and Brandon Bennett

Published in: LIPIcs, Volume 86, 13th International Conference on Spatial Information Theory (COSIT 2017)


Abstract
Many papers have considered the problem of how to define forest. However, as we shall illustrate, while most definitions capture some important aspects of what it means to be a forest, they almost invariably omit or are very vague regarding other aspects. In the current paper we address this issue, firstly by providing a definitional framework based on spatial and physical properties, within which one can make explicit the implicit variability of the natural language forest concept in terms of explicit parameters. Our framework explicitly differentiates between the functions of classification, individuation and demarcation that comprise the interpretation of predicative terms. Whereas ontologies have traditionally concentrated predominantly on classification, we argue that in many cases (especially in the case of geographic concepts) criteria for individuation (i.e. establishing how many distinct individual objects of a given type exist) and demarcation (establishing the boundary of an object) require separate attention, involve their own particular definitional issues and are affected by vagueness in different ways. We also describe a prototype Prolog system that illustrates how our framework can be implemented.

Cite as

Lucía Gómez Álvarez and Brandon Bennett. Classification, Individuation and Demarcation of Forests: Formalising the Multi-Faceted Semantics of Geographic Terms. In 13th International Conference on Spatial Information Theory (COSIT 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 86, pp. 8:1-8:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)


Copy BibTex To Clipboard

@InProceedings{gomezalvarez_et_al:LIPIcs.COSIT.2017.8,
  author =	{G\'{o}mez \'{A}lvarez, Luc{\'\i}a and Bennett, Brandon},
  title =	{{Classification, Individuation and Demarcation of Forests: Formalising the Multi-Faceted Semantics of Geographic Terms}},
  booktitle =	{13th International Conference on Spatial Information Theory (COSIT 2017)},
  pages =	{8:1--8:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-043-9},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{86},
  editor =	{Clementini, Eliseo and Donnelly, Maureen and Yuan, May and Kray, Christian and Fogliaroni, Paolo and Ballatore, Andrea},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2017.8},
  URN =		{urn:nbn:de:0030-drops-77676},
  doi =		{10.4230/LIPIcs.COSIT.2017.8},
  annote =	{Keywords: Forest, Definition, Vagueness, Ontology, GIS}
}
Document
Combining Logic and Probability in Tracking and Scene Interpretation

Authors: Brandon Bennett

Published in: Dagstuhl Seminar Proceedings, Volume 8091, Logic and Probability for Scene Interpretation (2008)


Abstract
The paper gives a high-level overview of some ways in which logical representations and reasoning can be used in computer vision applications, such as tracking and scene interpretation. The combination of logical and statistical approaches is also considered.

Cite as

Brandon Bennett. Combining Logic and Probability in Tracking and Scene Interpretation. In Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings, Volume 8091, pp. 1-7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{bennett:DagSemProc.08091.7,
  author =	{Bennett, Brandon},
  title =	{{Combining Logic and Probability in  Tracking and Scene Interpretation}},
  booktitle =	{Logic and Probability for Scene Interpretation},
  pages =	{1--7},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8091},
  editor =	{Anthony G. Cohn and David C. Hogg and Ralf M\"{o}ller and Bernd Neumann},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08091.7},
  URN =		{urn:nbn:de:0030-drops-16120},
  doi =		{10.4230/DagSemProc.08091.7},
  annote =	{Keywords: Vision, Tracking, Logic, Probability, Spatio-Temporal Continuity}
}
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