Enhanced word embeddings using multi-semantic representation through lexical chains
dc.contributor.author | Ruas, Terry | |
dc.contributor.author | Ferreira, Charles Henrique Porto | |
dc.contributor.author | Grosky, William | |
dc.contributor.author | Olivetti de Franca, Fabrıcio | |
dc.contributor.author | Rossi de Medeiros, Debora Maria | |
dc.date.accessioned | 2020-05-13T17:36:38Z | |
dc.date.available | 2020-05-13T17:36:38Z | |
dc.date.issued | 2020-09 | |
dc.identifier.citation | Terry Ruas, Charles Henrique Porto Ferreira, William Grosky, Fabrício Olivetti de França, Débora Maria Rossi de Medeiros, "Enhanced word embeddings using multi-semantic representation through lexical chains," Information Sciences, Volume 532, 2020, Pages 16-32, https://doi.org/10.1016/j.ins.2020.04.048 | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/155353 | |
dc.description.abstract | The relationship between words in a sentence often tells us more about the underlying semantic content of a document than its actual words, individually. In this work, we propose two novel algorithms, called Flexible Lexical Chain II and Fixed Lexical Chain II. These algorithms combine the semantic relations derived from lexical chains, prior knowledge from lexical databases, and the robustness of the distributional hypothesis in word embeddings as building blocks forming a single system. In short, our approach has three main contributions: (i) a set of techniques that fully integrate word embeddings and lexical chains; (ii) a more robust semantic representation that considers the latent relation between words in a document; and (iii) lightweight word embeddings models that can be extended to any natural language task. We intend to assess the knowledge of pre-trained models to evaluate their robustness in document classification task. The proposed techniques are tested against seven word embeddings algorithms using five different machine learning classifiers over six scenarios in the document classification task. Our results show the integration between lexical chains and word embeddings representations sustain state-of-the-art results, even against more complex systems. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | Elsevier | en_US |
dc.subject | Lexical chains | en_US |
dc.subject | Natural language processing | en_US |
dc.subject | Word embeddings | en_US |
dc.subject | Document classification | en_US |
dc.subject | Synsets | en_US |
dc.title | Enhanced word embeddings using multi-semantic representation through lexical chains | en_US |
dc.type | Article | en_US |
dc.subject.hlbsecondlevel | Computer Science | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.peerreviewed | Peer Reviewed | en_US |
dc.contributor.affiliationum | Computer and Information Science, Department of (UM-Dearborn) | en_US |
dc.contributor.affiliationother | Federal University of ABC, Brazil | en_US |
dc.contributor.affiliationother | University of Wuppertal | en_US |
dc.contributor.affiliationumcampus | Dearborn | en_US |
dc.description.bitstreamurl | https://deepblue.lib.umich.edu/bitstream/2027.42/155353/1/Ruas_EtAl_Enhanced word embeddings_preprint_2020.pdf | |
dc.identifier.doi | https://doi.org/10.1016/j.ins.2020.04.048 | |
dc.identifier.source | Information Sciences | en_US |
dc.description.filedescription | Description of Ruas_EtAl_Enhanced word embeddings_preprint_2020.pdf : preprint of article published in the journal Information Sciences | |
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.