Using the Structure of a Conceptual Network in Computing Semantic Relatedness

By Iryna Gurevych. 2005

131 citations recorded by the source corpus.

We present a new method for computing semantic relatedness of concepts. The method relies solely on the structure of a conceptual network and eliminates the need for performing additional corpus analysis. The network structure is employed to generate artificial conceptual glosses. They replace textual definitions proper written by humans and are processed by a dictionary based metric of semantic relatedness [1]. We implemented the metric on the basis of GermaNet, the German counterpart of WordNet, and evaluated the results on a German dataset of 57 word pairs rated by human subjects for their semantic relatedness. Our approach can be easily applied to compute semantic relatedness based on alternative conceptual networks, e.g. in the domain of life sciences.

Subfields: Artificial Intelligence, Natural Language Processing, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Knowledge Graphs & Representation

Citations in the corpus

Compositional Morphology for Word Representations and Language Modelling (2014, background): “ES WS353 (Hassan & Mihalcea, 2009); Gur350 (Gurevych, 2005); RG65 (Rubenstein & Goodenough, 1965) with FR (Joubarne & Inkpen, 2011); ZG222 (Zesch & Gurevych, 2006).”
A Survey of Cross-lingual Word Embedding Models (2017, background): “Extending them to the multilingual setting then mainly involves translating the word pairs into different languages: WordSim-353 has been translated to Spanish, Romanian, and Arabic (Hassan & Mihalcea, 2009) and to German, Italian, and Russian (Leviant & Reichart, 2015); RG was translated to German ”
Multilingual Reliability and “Semantic” Structure of Continuous Word Spaces (2015, background): “RG (Rubenstein and Goodenough, 1965) and its German equivalent Gur65 (Gurevych, 2005).”
Human and Machine Judgements for Russian Semantic Relatedness (2016, methodology): “Yang and Powers [19] proposed a dataset speciﬁcally for measuring verb similarity, which was later translated into German by Meyer and Gurevych [20].”
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity (2017, background): “, 2002) datasets have been translated into other languages, either by experts (Gurevych, 2005; Joubarne and Inkpen, 2011; Granada et al., 2014; CamachoCollados et al., 2015), or by means of crowdsourcing (Leviant and Reichart, 2015), thereby creating equivalent datasets in languages other than Engli”
Probabilistic FastText for Multi-Sense Word Embeddings (2018, methodology): “For datasets GUR350 and GUR65, we use the results reported in the F AST T EXT publication (Bojanowski et al., 2016).”
Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling (2015, background): “…of scored word pairs in languages other than English (e.g. Arabic, French, Farsi, German, Portuguese, Romanian and Spanish) were presented (Gurevych, 2005; Zesch and Gurevych, 2006; Hassan and Mihalcea, 2009; Schmidt et al., 2011; Camacho-Collados et al., 2015; Köper et al., 2015, inter…”
Automatically Creating Datasets for Measures of Semantic Relatedness (2006, methodology): “tween two words (Gurevych, 2005).”