Comparing Semantic Relatedness between Word Pairs in Portuguese Using Wikipedia

Abstract

Open Archive Toulouse Archive OuverteOATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible To cite this version: Leitzke Granada, Roger and Trojahn, Cassia and Vieira, Renata Comparing Semantic Relatedness between Word Abstract. The growth of available data in digital format has been facil-itating the development of new models to automatically infer the seman-tic similarity between word pairs. However, there are still many natural languages without sufficient resources to evaluate measures of semantic relatedness. In this paper we translated word pairs from a well-known baseline for evaluating semantic relatedness measures into Portuguese and performed a manual evaluation of each pair. We compared the correlation with similar datasets in other languages and generated LSA models from Wikipedia articles in order to verify the pertinence of each dataset and how semantic similarity conveys across languages.

Distributional and Knowledge-Based Approaches for Computing Portuguese Word Similarity

“…On the other hand, our results for PT-65 clearly outperform experimental results by Granada et al [15], who used a LSA distributional model based on the Portuguese Wikipedia and achieved ρ = 0.53, which is substantially lower than the 0.87 achieved with the All-LKB.…”

“…One is based on the RG-65 similarity test [17], which contains 65 pairs of nouns and their similarity of meaning, between 0 and 4, computed from 51 human judgements. RG-65 was translated to Portuguese by Granada et al [15] and similarity was re-scored from the opinions of 50 native speakers of Portuguese. It was renamed to PT-65 and is freely available online, from http://www.inf.pucrs.br/linatural/wikimodels/similarity.html.…”

“…When it comes to word similarity, Granada et al [15] created a Portuguese test for this purpose, compared the judge agreement with other languages, and applied a distributional approach, based on Wikipedia, to answer it. Wilkens et al [16] compiled the B 2 SG test and used it to assess distributional similarity measures.…”

SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity

“…A reliable multilingual word similarity benchmark can be hugely beneficial in evaluating the robustness and reliability of semantic representation techniques across languages. Despite this, very few word similarity datasets exist for languages other than English: The original English RG-65 (Rubenstein and Goodenough, 1965) and WordSim-353 (Finkelstein et al, 2002) datasets have been translated into other languages, either by experts (Gurevych, 2005;Joubarne and Inkpen, 2011;Granada et al, 2014;Camacho-Collados et al, 2015), or by means of crowdsourcing (Leviant and Reichart, 2015), thereby creating equivalent datasets in languages other than English. However, the existing English word similarity datasets suffer from various issues:…”

A Unified Multilingual Semantic Representation of Concepts

“…Monolingual. We benchmark our system against four other approaches that exploit Wikipedia as their main knowledge resource: SSA 5 (Hassan and Mihalcea, 2011), ESA (Gabrilovich and Markovitch, 2007), Wiki-wup (Ponzetto and Strube, 2007), and LSA-Wiki (Granada et al, 2014). We also provide results for systems that use distributional semantics for modeling words, both the conventional co-occurrence based approach, i.e., PMI-SVD (Baroni et al, 2014), PMI and SOC-PMI (Joubarne and Inkpen, 2011), and Retrofitting (Faruqui et al, 2015), and the newer word embeddings, i.e., Word2Vec (Mikolov et al, 2013).…”