A supervised learning approach to automatic synonym identification based on distributional features

Abstract

Distributional similarity has been widely used to capture the semantic relatedness of words in many NLP tasks. However, various parameters such as similarity measures must be handtuned to make it work effectively. Instead, we propose a novel approach to synonym identification based on supervised learning and distributional features, which correspond to the commonality of individual context types shared by word pairs. Considering the integration with pattern-based features, we have built and compared five synonym classifiers. The evaluation experiment has shown a dramatic performance increase of over 120% on the F-1 measure basis, compared to the conventional similarity-based classification. On the other hand, the pattern-based features have appeared almost redundant.

Towards an Automatized Generation of Rule-Based Systems for Architecting Eco-Industrial Parks

“…As Word2Vec is based on a neural network, extensive training data is required. A third approach, called DFEAT, is based on supervised learning and distributional features [21]. The value of the distributional feature indicates the commonality of the context of a word pair.…”

“…Compared to other synonym classifiers on the test set, the DFEAT algorithm showed a superior performance. Ranked list of synonyms [21] Similar to finding synonyms, a number of algorithms have been proposed for identifying part-whole relationships. [25] presents an approach for finding part-whole relationships in domain-specific data.…”

Semantic similarity based approach for reducing Arabic texts dimensionality

“…The proposed method creates clusters of similar or related words extracted from the same root or stem and regrouped along with their synonyms. The distributional similarity is used for discovering words' semantic information that allows us to group similar words and eliminate word redundancy from the text (Hagiwara 2008). This paper is organized as follows.…”

“…It is a statistical-based model that uses the statistical distribution of words along with their contexts to determine the degree of semantic similarity between them. This model describes the words by contextvectors built on the distributional hypothesis, which states that similar words appear in similar contexts (Hagiwara 2008).…”

Turkish synonym identification from multiple resources: monolingual corpus, mono/bilingual online dictionaries, and WordNet

“…The authors proposed that while dependency relations and proximity perform relatively well by themselves, the combination of two or more kinds of contextual information gives more stable results. In another study [26], a synonym extraction method was proposed using supervised learning based on distributional and/or pattern-based features. Yet another study [27] used 3 vector-based models to detect semantically related nouns in Dutch and analyzed the impact of 3 linguistic properties of the nouns.…”