KRNL-18: Knowledge Representation in Natural Language Knowledge Representation 2018 Tempe, Arizona, AZ, United States, October 30-November 2, 2018 |
Conference website | https://sites.google.com/view/krnl-2018/home |
Submission link | https://easychair.org/conferences/?conf=krnl18 |
Submission deadline | July 21, 2018 |
Knowledge Representation in Natural Languages KRNL
Call for Papers
Motivation and Topics of Interest 1st Workshop on Knowledge Representation for Natural Languages (KRNL) will be organised as a satellite workshop at the 16-th International Conference on Principles of Knowledge Representation and Reasoning, Tempe, Arizona, 30 October–2 November 2018.
Natural languages spoken by humans are arguably the most natural medium for humans to express their knowledge about the world. Unfortunately, representing knowledge in the form of natural languages is a challenging task due to the ambiguities that exist in natural languages. Processing knowledge expressed in the form of natural languages, or performing logical inferences directly at the level of human spoken languages is further complicated by the lack of formal structure in human languages. To avoid these difficulties involved in KR directly at the level of natural languages, the KR community has resort to formal logical representations such as first-order logic or description logics. Once knowledge is extracted from human languages and represented in such abstract formats, a plethora of mathematical tools are at our disposal to perform inferences at scale.
NLP is the branch of AI that considers the problem of extracting and processing knowledge expressed in the form of human languages. Starting from the early work on corpus analysis using word-counting approaches, the NLP community has significantly advanced over the last few years on KR such as learning semantic representations for words and compositional approaches that can build semantic representations for larger lexical units such as phrases, sentences or documents. Moreover, tasks that require some form of logical inference at the level of languages such as recognising textual entailment (RTE), natural language inference in knowledge bases, argument mining, and semantic parsing have established as central research topics in the NLP community.
KR and NLP communities have so far worked independently and the inter-community communications have been intermittent and sparse. However, given the above-mentioned recent developments, we believe the two communities are at cross-roads, approaching an important junction. The two communities have much to learn from each other and share their experiences in related yet complementary topics. To provide one example, the KR community can benefit from the unsupervised knowledge extraction and representation methods developed in the NLP community to overcome the knowledge extraction bottleneck, whereas the NLP community can benefit from the efficient in- ference algorithms studied over the years in the KR community. The time is ripe to bring these two communities together, and this workshop aims to advance research in this new frontier by inviting papers from areas related, but not limited to, KR and NLP such as:
1. Formal methods for knowledge representation.
2. Knowledge extraction from unstructured texts.
3. Natural language inference.
4. Inference in knowledge bases and ontologies.
5. Textual entailment.
6. Representation learning for words or semantic relations.
Submissions We invite full papers of up to 9 pages in AAAI format including abstract, figures, and appendices (if any) but excluding references and acknowledgements, which may take up to one additional page; submission of additional material (e.g. proofs) as separate supplementary documents is allowed, but this material should not form an integral part of the submission and will only be consulted at the discretion of the reviewers.
Multiple submissions are welcome from the same authors. Moreover, we do accept papers that are currently under review in other conferences and journals, or in arxiv. A double-blind review policy will be used, and the authors are requested not to mention their names in the paper or provide self-citations in a format that reveals their identity. However, if a paper is accepted to KRNL, then the authors must withdraw it from the other venues to which it has been submitted. Papers that do not adhere to the submission requirements will be rejected without reviewing.
All submissions are accepted via the KR-2018 submission system.
Important Dates
• Workshops paper submission deadline: 21 July 2018.
• Workshops paper notification: 25 August 2018.
• Workshops registration deadline: TBD.
• Tutorial and workshop dates: 27-29 October 2018.
Organisers
• Danushka Bollegala, University of Liverpool
• Andre Hernich, University of Liverpool Programme Committee
PC
• Sebastian Riedel (University College London, UK)
• Edward Grefenstette (Google Deep Mind, UK)
• Jason Weston (Facebook AI Research, France)
• Naoaki Okazaki (Tokyo Institute of Technology, Japan)
• Kyunghyun Cho (New York University, US)
• Yuliya Lierler (University of Nebraska, US)
• Markus Kr¨otzsch (TU Dresden, Germany)
• Micha¨el Thomazo (INRIA, France)
• Pascal Hitzler (Wright State University, US)
• Guy van den Broek (UCLA, US)
• Vaishak Belle (University of Edinburgh, UK)
• Oliver Kutz (Free University Bozen-Bolzano, Italy)