Multi-sense Embeddings through a Word Sense Disambiguation Process
dc.contributor.author | Ruas, Terry | |
dc.contributor.author | Grosky, William | |
dc.contributor.author | Aizawa, Akiko | |
dc.date.accessioned | 2018-08-28T16:23:40Z | |
dc.date.available | 2018-08-28T16:23:40Z | |
dc.date.issued | 2018-06-23 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/145475 | |
dc.description.abstract | Natural Language Understanding has seen an increasing number of publications in the last years, especially after robust word embedding models became popular. These models gained a special place in the spotlight when they proved themselves able to capture and represent semantic relations underneath huge amounts of data. Nevertheless, traditional models often fall short in intrinsic issues of linguistics, such as polysemy and homonymy. Multi-sense word embeddings were devised to alleviate these and other problems by representing each word-sense separately, but studies in this area are still in its infancy and much can be explored. We follow this scenario by proposing an unsupervised technique that disambiguates and annotates words by their specific sense, considering their context influence. These are later used to train a word embeddings model to produce a more accurate vector representation. We test our approach in 6 different benchmarks for the word similarity task, showing that our approach can sustain good results and often outperforms current state-of-the-art systems. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | wsd | en_US |
dc.subject | Word2vec | en_US |
dc.subject | wordnet | en_US |
dc.subject | word similarity | en_US |
dc.title | Multi-sense Embeddings through a Word Sense Disambiguation Process | en_US |
dc.type | Working Paper | en_US |
dc.subject.hlbsecondlevel | Computer Science | |
dc.subject.hlbtoplevel | Engineering | |
dc.contributor.affiliationum | University of Michigan Dearborn | en_US |
dc.contributor.affiliationum | University of Michigan Dearborn | en_US |
dc.contributor.affiliationother | National Institute of Informatics | en_US |
dc.contributor.affiliationumcampus | Dearborn | en_US |
dc.description.bitstreamurl | https://deepblue.lib.umich.edu/bitstream/2027.42/145475/3/tacl.pdf | |
dc.description.filedescription | Description of tacl.pdf : WorkingPaper | |
dc.owningcollname | Computer and Information Science, Department of (UM-Dearborn) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.