Computing inter-document similarity with Context Semantic Analysis

Abstract

We propose a novel knowledge-based technique for inter-document similarity computation, called Context Semantic Analysis (CSA). Several specialized approaches built on top of specific knowledge base (e.g. Wikipedia) exist in literature, but CSA differs from them because it is designed to be portable to any RDF knowledge base. In fact, our technique relies on a generic RDF knowledge base (e.g. DBpedia and Wikidata) to extract from it a Semantic Context Vector, a novel model for representing the context of a document, which is exploited by CSA to compute inter-document similarity effectively. Moreover, we show how CSA can be effectively applied in the Information Retrieval domain. Experimental results show that: (i) for the general task of inter-document similarity, CSA outperforms baselines built on top of traditional methods, and achieves a performance similar to the ones built on top of specific knowledge bases; (ii) for Information Retrieval tasks, enriching documents with context (i.e., employing the Semantic Context Vector model) improves the results quality of the state-of-the-art technique that employs such similar semantic enrichment.

Introduction

Recent years have seen a growing number of knowledge bases employed in several domains and applications. Besides DBpedia [1], which is the heart of the Linked Open Data (LOD) cloud [2], other important knowledge bases are: Wikidata [3], a collaborative knowledge base; YAGO [4], a huge semantic knowledge base derived from Wikipedia, WordNet and GeoNames; Snomed CT [5], the best known ontology in the medical domain and AGROVOC [6], a multilingual agricultural thesaurus we recently used for annotating agricultural resources [7].

In the literature, knowledge-based approaches have been employed for improving existing techniques in Natural Language Processing (NLP) [8] and Information Retrieval (IR) domains [9]. Yet, there is much room for improvement in order to effectively exploit these rich models in these fields [10]. For instance, in the context of inter-document similarity, which plays an important role in many NLP and IR applications, classic techniques rely solely on syntactic information and are usually based on Vector Space Models [11], where the documents are represented in a vector space having document words as dimensions. Nevertheless, such techniques fail in detecting relationships among concepts in simple scenarios like the following sentences: “The Rolling Stones with the participation of Roger Daltrey opened the concerts’ season in Trafalgar Square” and “The bands headed by Mick Jagger with the leader of The Who played in London last week”. These two sentences contain highly related concepts (e.g., Roger Daltrey is the leader of The Who) which can be found by exploiting the knowledge network encoded within knowledge bases such as DBpedia.

To overcome the limitation of a purely syntactical approach, in [12] we proposed Context Semantic Analysis (CSA), a novel semantic technique for estimating inter-document similarity, leveraging the information contained in a knowledge base. One of the main novelties of CSA w.r.t. other knowledge-based approaches is its applicability over any RDF knowledge base, so that all datasets belonging to the LOD cloud [2] (more than one thousand) can be used. CSA is based on the notion of contextual graph of a document, i.e. a subgraph of the knowledge base that contains the contextual information of the document; the notion of contextual graph is very similar to the one of semantic graph defined in [10]. The contextual graph is then suitably weighted to capture the degree of associativity between its concepts, i.e., the degree of relevance of a property for the entities it connects. The vertices of such a weighted contextual graph are then ranked by using PageRank methods, so obtaining a Semantic Context Vector, a novel model able to represent the context of the document. Thus, the similarity of two documents is computed by comparing their Semantic Context Vectors with general vector comparison methods, such as the cosine similarity. By evaluating our method on a standard benchmark for document similarity (which consider correlations with human judges), we showed how CSA outperforms almost all other methods and how it can exploit any RDF knowledge base. Moreover we analyzed its scalability in a clustering task with a large corpus of documents, and showed that our approach outperforms the considered baselines.

This paper extends our previous work at the SISAP 2016 Conference. The main novel contribution of the extended paper is to test Context Semantic Analysis (CSA) applicability and effectiveness in a real-world application domain, such as Information Retrieval (IR). To this purpose, we analyzed the semantic based approaches recently proposed in the Information Retrieval research community. We found that, the most effective and general IR framework, adopting semantic enrichment of documents, is KE4IR [13]. We studied its layered architecture and tried to improve its performance, by including CSA, as a new semantic layer. The outcome was really positive as we were able to show that KE4IR + CSA outperforms the original KE4IR framework (see Section 5.2).

The paper is structured as follows. Section 2 describes the related work, while Section 3 is devoted to some preliminaries useful for the rest of the paper. Then, CSA is described in Section 4 and Section 5 shows its evaluation. Finally, Section 6 outlines conclusions and future work.