4 |
Measuring Brazilian Portuguese Product Titles Similarity using Embeddings ...
|
|
|
|
Abstract:
Textual similarity deals with determining how similar two pieces of texts are, considering the lexical (surface forms) or semantic (meaning) close-ness. In this paper we applied word embeddings for measuring e-commerce product title similarity in Brazilian Portuguese. We generated some domain-specific word embeddings (using Word2Vec, FastText and GloVe) and compared them with general-domain models (word embeddings and BERT models). We concluded that the cosine similarity calculated using the domain-specific word embeddings was a good approach to distinguish between similar and non-similar products, but the multilingual BERT pre-trained model proved to be thebest one. ...
|
|
URL: https://underline.io/lecture/41588-measuring-brazilian-portuguese-product-titles-similarity-using-embeddings https://dx.doi.org/10.48448/2b2t-ev09
|
|
BASE
|
|
Hide details
|
|
9 |
Universal Dependencies 2.2
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
|
|
BASE
|
|
Show details
|
|
12 |
Universal Dependencies 2.1
|
|
|
|
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
|
|
BASE
|
|
Show details
|
|
15 |
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A Case Study of Copredication over a Deverbal that Reconciles Empirical Data with Computational Semantics
|
|
|
|
In: 12th annual International Workshop on Logic and Engineering of Natural Language Semantics ; LENLS: Logic and Engineering of Natural Language Semantics ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-01311129 ; LENLS: Logic and Engineering of Natural Language Semantics, Nov 2015, Tokyo, Japan ; http://www.is.ocha.ac.jp/~bekki/lenls/lenls12/index.html (2015)
|
|
BASE
|
|
Show details
|
|
|
|