2020 SensEmBERTContextEnhancedSenseE

(Scarlini et al., 2020) ⇒ Bianca Scarlini, Tommaso Pasini, and Roberto Navigli. (2020). “SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation.” In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020); Proceedings of the Thirty-Second Innovative Applications of Artificial Intelligence Conference (IAAI 2020); Proceedings of the Tenth AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI 2020).

Subject Headings: Sense Embedding System; SensEmBERT System; Word Sense Disambiguation System.

Notes

Online Resource(s):
- Website: http://sensembert.org

Cited By

Google Scholar: ~ 39 Citations.

Quotes

Abstract

Contextual representations of words derived by neural language models have proven to effectively encode the subtle distinctions that might occur between different meanings of the same word. However, these representations are not tied to a semantic network, hence they leave the word meanings implicit and thereby neglect the information that can be derived from the knowledge base itself. In this paper, we propose SensEmBERT, a knowledge-based approach that brings together the expressive power of language modelling and the vast amount of knowledge contained in a semantic network to produce high-quality latent semantic representations of word meanings in multiple languages. Our vectors lie in a space comparable with that of contextualized word embeddings, thus allowing a word occurrence to be easily linked to its meaning by applying a simple nearest neighbour approach. We show that, whilst not relying on manual semantic annotations, SensEmBERT is able to either achieve or surpass state-of-the-art results attained by most of the supervised neural approaches on the English Word Sense Disambiguation task. When scaling to other languages, our representations prove to be equally effective as their English counterpart and outperform the existing state of the art on all the Word Sense Disambiguation multilingual datasets. The embeddings are released in five different languages at http://sensembert.org.

References

BibTeX

@inproceedings{2020_SensEmBERTContextEnhancedSenseE,
  author    = {Bianca Scarlini and
               Tommaso Pasini and
               Roberto Navigli},
  title     = {SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word
               Sense Disambiguation},
  booktitle = {Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020);
               The Thirty-Second Innovative Applications of Artificial Intelligence
               Conference (IAAI 2020); The Tenth AAAI Symposium on Educational
               Advances in Artificial Intelligence (EAAI2020)},
  pages     = {8758--8765},
  publisher = {AAAI Press},
  year      = {2020},
  url       = {https://aaai.org/ojs/index.php/AAAI/article/view/6402},
}

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2020 SensEmBERTContextEnhancedSenseE	Bianca Scarlini Tommaso Pasini Roberto Navigli			SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation						2020