Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource

Stéphan Tulkens, Chris Emmery, Walter Daelemans

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Abstract

    Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on a variety of corpora, in two language-specific tasks: relation evaluation, and dialect identification. For the latter, we compare unsupervised methods with a traditional, hand-crafted dictionary. With this research, we provide the embeddings themselves, the relation evaluation task benchmark for use in further research, and demonstrate how the benchmarked embeddings prove a useful unsupervised linguistic resource, effectively used in a downstream task.
    LanguageEnglish
    Title of host publication Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource
    PublisherAssociation for Computational Linguistics
    Publication statusPublished - 1 Jul 2016
    EventLanguage Resources and Evaluation Conference: 10th edition - Grand Hotel Bernardin Conference Center, Portorož, Slovenia
    Duration: 23 May 201628 May 2016
    http://lrec2016.lrec-conf.org/en/

    Conference

    ConferenceLanguage Resources and Evaluation Conference
    Abbreviated titleLREC-2016
    CountrySlovenia
    CityPortorož
    Period23/05/1628/05/16
    Internet address

    Fingerprint

    Linguistics
    Glossaries

    Keywords

    • Word Embeddings
    • Evaluation
    • Dutch

    Cite this

    Tulkens, S., Emmery, C., & Daelemans, W. (2016). Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. In Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource Association for Computational Linguistics.
    Tulkens, Stéphan ; Emmery, Chris ; Daelemans, Walter. / Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. Association for Computational Linguistics, 2016.
    @inproceedings{85d85154462b439eb488b55671d62ed2,
    title = "Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource",
    abstract = "Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on a variety of corpora, in two language-specific tasks: relation evaluation, and dialect identification. For the latter, we compare unsupervised methods with a traditional, hand-crafted dictionary. With this research, we provide the embeddings themselves, the relation evaluation task benchmark for use in further research, and demonstrate how the benchmarked embeddings prove a useful unsupervised linguistic resource, effectively used in a downstream task.",
    keywords = "Word Embeddings, Evaluation, Dutch",
    author = "St{\'e}phan Tulkens and Chris Emmery and Walter Daelemans",
    year = "2016",
    month = "7",
    day = "1",
    language = "English",
    booktitle = "Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource",
    publisher = "Association for Computational Linguistics",

    }

    Tulkens, S, Emmery, C & Daelemans, W 2016, Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. in Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. Association for Computational Linguistics, Language Resources and Evaluation Conference, Portorož, Slovenia, 23/05/16.

    Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. / Tulkens, Stéphan; Emmery, Chris; Daelemans, Walter.

    Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. Association for Computational Linguistics, 2016.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    TY - GEN

    T1 - Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource

    AU - Tulkens, Stéphan

    AU - Emmery, Chris

    AU - Daelemans, Walter

    PY - 2016/7/1

    Y1 - 2016/7/1

    N2 - Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on a variety of corpora, in two language-specific tasks: relation evaluation, and dialect identification. For the latter, we compare unsupervised methods with a traditional, hand-crafted dictionary. With this research, we provide the embeddings themselves, the relation evaluation task benchmark for use in further research, and demonstrate how the benchmarked embeddings prove a useful unsupervised linguistic resource, effectively used in a downstream task.

    AB - Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on a variety of corpora, in two language-specific tasks: relation evaluation, and dialect identification. For the latter, we compare unsupervised methods with a traditional, hand-crafted dictionary. With this research, we provide the embeddings themselves, the relation evaluation task benchmark for use in further research, and demonstrate how the benchmarked embeddings prove a useful unsupervised linguistic resource, effectively used in a downstream task.

    KW - Word Embeddings

    KW - Evaluation

    KW - Dutch

    M3 - Conference contribution

    BT - Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource

    PB - Association for Computational Linguistics

    ER -

    Tulkens S, Emmery C, Daelemans W. Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. In Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource. Association for Computational Linguistics. 2016