A Compositional-Distributional Semantic Model for Searching Complex Entity Categories

Abstract

Users combine attributes and types to describe and classify entities into categories. These categories are fundamental for organising knowledge in a decentralised way acting as tags and predicates. When searching for entities, categories frequently describes the search query. Considering that users do not know in which terms the categories are expressed, they might query the same concept by a paraphrase. While some categories are composed of simple expressions (e.g. Presidents of Ireland), others have more complex compositional patterns (e.g. French Senators Of The Second Empire). This work proposes a hybrid semantic model based on syntactic analysis, distributional semantics and named entity recognition to recognise paraphrases of entity categories. Our results show that the proposed model outperformed the comparative baseline, in terms of recall and mean reciprocal rank, thus being suitable for addressing the vocabulary gap between user queries and entity categories.

Indirectly Named Entity Recognition

“…Synonym entity recognition has also been evocated in the more global context of "paraphrase identification" (Mohamed and Oussalah, 2020;Wanachai and Cardey-Greenfield, 2012;Shinyama et al, 2002, Sales et al, 2016. In this context, possible variations in the expression of phrases or whole sentences are studied, and the use of INE or other synonym entities appear as possible aspects that these variations can take.…”

SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News

“…With the exception of Cabanski et al (2017), few approaches explicitly tackled the problem of compositionality (Sales et al, 2016), valency shifting (Malo et al, 2014a), and clausal disembedding (Niklaus et al, 2016), a fact that is reflected by the lack of submissions which explored syntactic features.…”

The Robot Who Loved Me: Building Consciousness Models for Use in Human Robot Interaction Following a Collaborative Systems Approach

“…Knowledge discovery from digital big multimodal data can be done effectively by employing techniques like machine learning (such as Deep learning, SIFT), distributional semantics in NLP e.g. for text mining purposes and semantic augmentation (use of domain specific formal ontologies) [7].…”