Change search
ReferencesLink to record
Permanent link

Direct link
Evaluating learning language representations
KTH, School of Computer Science and Communication (CSC), Theoretical Computer Science, TCS. Gavagai, Sweden.ORCID iD: 0000-0003-4042-4919
Show others and affiliations
2015 (English)Conference paper (Refereed)Text
Abstract [en]

Machine learning offers significant benefits for systems that process and understand natural language: (a) lower maintenance and upkeep costs than when using manually-constructed resources, (b) easier portability to new domains, tasks, or languages, and (c) robust and timely adaptation to situation-specific settings. However, the behaviour of an adaptive system is less predictable than when using an edited, stable resource, which makes quality control a continuous issue. This paper proposes an evaluation benchmark for measuring the quality, coverage, and stability of a natural language system as it learns word meaning. Inspired by existing tests for human vocabulary learning, we outline measures for the quality of semantic word representations, such as when learning word embeddings or other distributed representations. These measures highlight differences between the types of underlying learning processes as systems ingest progressively more data.

Place, publisher, year, edition, pages
Springer, 2015. 254-260 p.
Series
Lecture Notes in Computer Science, ISSN 0302-9743
Keyword [en]
Evaluation, Language representations, Machine learning, Semantic spaces, Word embeddings, Adaptive control systems, Artificial intelligence, Association reactions, Benchmarking, C (programming language), Computational linguistics, Learning systems, Natural language processing systems, Semantics, Distributed representation, Embeddings, Natural language systems, Semantic Space, Vocabulary learning, Word representations, Quality control
National Category
Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:kth:diva-181546DOI: 10.1007/978-3-319-24027-5_25ISI: 000364677800028ScopusID: 2-s2.0-84945979173ISBN: 9783319240268OAI: oai:DiVA.org:kth-181546DiVA: diva2:910588
Conference
6th International Conference on Labs of the Evaluation Forum, CLEF 2015; Toulouse; France; 8-11 September 2015
Funder
European Science Foundation (ESF)
Note

QC 20160309

Available from: 2016-03-09 Created: 2016-02-02 Last updated: 2016-04-13Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Karlgren, Jussi
By organisation
Theoretical Computer Science, TCS
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 37 hits
ReferencesLink to record
Permanent link

Direct link