Linked Disambiguated Distributional Semantic Networks

Abstract

Abstract. We present a new hybrid lexical knowledge base that combines the contextual information of distributional models with the conciseness and precision of manually constructed lexical networks. The computation of our countbased distributional model includes the induction of word senses for single-word and multi-word terms, the disambiguation of word similarity lists, taxonomic relations extracted by patterns and context clues for disambiguation in context. In contrast to dense vector representations, our resource is human readable and interpretable, and thus can be easily embedded within the Semantic Web ecosystem.

Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction

“…1 1 1 0 0 building 1 1 1 0 1 0 building 2 0 0 0 0 1 currently not known. We recover the sense labels of nodes in a context using the sense disambiguated approach proposed by Faralli et al (2016) as follows. We represent each context as a vector in a vector space model (Salton, Wong, and Yang 1975) constructed for all the contexts.…”

Using Linked Disambiguated Distributional Networks for Word Sense Disambiguation

“…We rely on the hybrid aligned lexical semantic resource proposed by Faralli et al (2016) to perform WSD. We start with a short description of this resource and then discuss how it is used for WSD.…”

“…We experiment with two different corpora for PCZ induction as in (Faralli et al, 2016), namely a 100 million sentence news corpus (news) from Gigaword (Parker et al, 2011) and LCC (Richter et al, 2006), and a 35 million sentence Wikipedia corpus (wiki). 1 Chinese Whispers sense clustering is performed with the default parameters, producing an average number of 2.3 (news) and 1.8 (wiki) senses per word in a vocabulary of 200 thousand words each, with the usual power-law distribution of sense cluster sizes.…”

“…On average, each sense is related to about 47 senses and has assigned 5 hypernym labels. These disambiguated distributional networks were linked to WordNet 3.1 using the method of Faralli et al (2016).…”

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

“…To build this model, induced word senses are first globally clustered using the Chinese Whispers graph clustering algorithm (Biemann, 2006). The edges in this sense graph are established by disambiguation of the related words (Faralli et al, 2016;Ustalov et al, 2017). The resulting clusters represent semantic classes grouping words sharing a common hypernym, e.g.…”