Contextualized Knowledge Base Sense Embeddings in Word Sense Disambiguation
| Autor: | Norbert Zeh, Evangelos E. Milios, Mozhgan Saeidi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
business.industry
Computer science Space (commercial competition) Base (topology) computer.software_genre Knowledge base Named-entity recognition Embedding Artificial intelligence business Representation (mathematics) computer Feature learning Word (computer architecture) Natural language processing |
| Zdroj: | Document Analysis and Recognition – ICDAR 2021 Workshops ISBN: 9783030861582 ICDAR Workshops (2) |
| DOI: | 10.1007/978-3-030-86159-9_12 |
| Popis: | Contextualized sense embedding has been shown to carry useful semantic information to improve the final results of various Natural Language Processing tasks. However, it is still challenging to integrate them with the information of the knowledge base, which is one lack in current state-of-the-art representations. This integration is helpful in NLP tasks, specifically in the lexical ambiguity problem. In this paper, we present C-KASE (Contextualized-Knowledge base Aware Sense Embedding), a novel approach to producing sense embeddings for the lexical meanings within a lexical knowledge base. The novel difference of our representation is the integration of the knowledge base information and the input text. This representation lies in a space that is comparable to that of contextualized word vectors. C-KASE representations enable a simple 1-Nearest-Neighbour algorithm to perform as well as state-of-the-art models in the English Word Sense Disambiguation task. Since this embedding is specified for each individual knowledge base, it also outperforms in other similar tasks, i.e., Wikification and Named Entity Recognition. The results of comparing our method with recent state-of-the-art methods show the efficiency of our method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|