Embedding Senses via Dictionary Bootstrapping

Byungkon Kang, Kyung-Ah Sohn
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, PMLR R15:331-340, 2017.

Abstract

This paper addresses the problem of embedding senses of a plain word according to its context. Natural language is inherently ambiguous, due to the presence of many multi-sensed words. Such ambiguity might have undesirable influence over many text-mining tools, including word embed- ding. Traditional word embedding techniques have focused on identifying which words tend to co-occur with one another in order to derive close embeddings for such words. However, the effectiveness of this approach is largely suscep- tible to the validity and neutrality of the train- ing corpus. To address this problem, we propose to use the dictionary as the authoritative corpus for computing the word embeddings. The ba- sic idea is to simultaneously embed the defini- tion sentence while disambiguating words. Since dictionaries list a set of disambiguated senses, the proposed procedure yields sense embeddings which exhibit semantic characteristics compara- ble to plain word embeddings.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR15-kang17a, title = {Embedding Senses via Dictionary Bootstrapping}, author = {Kang, Byungkon and Sohn, Kyung-Ah}, booktitle = {Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence}, pages = {331--340}, year = {2017}, editor = {Elidan, Gal and Kersting, Kristian}, volume = {R15}, series = {Proceedings of Machine Learning Research}, month = {11--15 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r15/main/assets/kang17a/kang17a.pdf}, url = {https://proceedings.mlr.press/r15/kang17a.html}, abstract = {This paper addresses the problem of embedding senses of a plain word according to its context. Natural language is inherently ambiguous, due to the presence of many multi-sensed words. Such ambiguity might have undesirable influence over many text-mining tools, including word embed- ding. Traditional word embedding techniques have focused on identifying which words tend to co-occur with one another in order to derive close embeddings for such words. However, the effectiveness of this approach is largely suscep- tible to the validity and neutrality of the train- ing corpus. To address this problem, we propose to use the dictionary as the authoritative corpus for computing the word embeddings. The ba- sic idea is to simultaneously embed the defini- tion sentence while disambiguating words. Since dictionaries list a set of disambiguated senses, the proposed procedure yields sense embeddings which exhibit semantic characteristics compara- ble to plain word embeddings.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Embedding Senses via Dictionary Bootstrapping %A Byungkon Kang %A Kyung-Ah Sohn %B Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2017 %E Gal Elidan %E Kristian Kersting %F pmlr-vR15-kang17a %I PMLR %P 331--340 %U https://proceedings.mlr.press/r15/kang17a.html %V R15 %X This paper addresses the problem of embedding senses of a plain word according to its context. Natural language is inherently ambiguous, due to the presence of many multi-sensed words. Such ambiguity might have undesirable influence over many text-mining tools, including word embed- ding. Traditional word embedding techniques have focused on identifying which words tend to co-occur with one another in order to derive close embeddings for such words. However, the effectiveness of this approach is largely suscep- tible to the validity and neutrality of the train- ing corpus. To address this problem, we propose to use the dictionary as the authoritative corpus for computing the word embeddings. The ba- sic idea is to simultaneously embed the defini- tion sentence while disambiguating words. Since dictionaries list a set of disambiguated senses, the proposed procedure yields sense embeddings which exhibit semantic characteristics compara- ble to plain word embeddings. %Z Reissued by PMLR on 04 October 2026.
APA
Kang, B. & Sohn, K.. (2017). Embedding Senses via Dictionary Bootstrapping. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R15:331-340 Available from https://proceedings.mlr.press/r15/kang17a.html. Reissued by PMLR on 04 October 2026.

Related Material