Indra: A Word Embedding and Semantic Relatedness Server

Indra: A Word Embedding and Semantic Relatedness Server Juliano Efson Sales†, Leonardo Souza†, Siamak Barzegar§, Brian Davis§∓, Andr´e Freitasδ and Siegfried Handschuh† †Department of Computer Science and Mathematics - University of Passau, Germany §Insight Centre for Data Analytics - National University of Ireland, Galway ∓Department of Computer Science - Maynooth University, Ireland δSchool of Computer Science - The University of Manchester, United Kingdom {juliano-sales, siegfried.handschuh}@uni-passau.de, siamak.barzegar@insight-centre.org brian.davis@.mu.ie, andre.freitas@manchester.ac.uk Abstract In recent years word embedding/distributional semantic models evolved to become a fundamental component in many natural language processing (NLP) architectures due to their ability of capturing and quantifying semantic associations at scale. Word embedding models can be used to satisfy recurrent tasks in NLP such as lexical and semantic generalisation in machine learning tasks, finding similar or related words and computing semantic relatedness of terms. However, building and consuming specific word embedding models require the setting of a large set of configurations, such as corpus-dependant parameters, distance measures as well as compositional models. Despite their increasing relevance as a component in NLP architectures, existing frameworks provide limited options in their ability to systematically build, parametrise, compare and evaluate different models. To answer this demand, this paper describes INDRA, a multi-lingual word embedding/distributional semantics framework which supports the creation, use and evaluation of word embedding models. In addition to the tool, INDRA also shares more than 65 pre-computed models in 14 languages. Keywords: word embedding server, semantic relatedness server, semantic toolkit, corpus pre-processor 1. Introduction Word embedding is a popular semantic model which rep- resents words and sentences in computational linguistics systems and machine learning models. In recent years a large set of algorithms for both generating and consum- ing word embedding models (WEMs) have been proposed, which includes corpus pre-processing strategies, WEM al- gorithms or weighting schemes, vector compositions and distance measures (Turney and Pantel, 2010; Lapesa and Evert, 2014; Mitchell and Lapata, 2010). Determining the optimal set of strategies for a given problem demands the support of a tool that facilitates the exploration of the con- figuration space of parameters. Furthermore, given the applicability and maturity achieved by these systems and models, they have been promoted from academic prototypes to industry-level applications (Loebbecke and Picot, 2015; Hengstler et al., 2016; Moro et al., 2015). In this new production scenario, a candidate tool should be able to scale to large number of requests and to the construction of models from large corpora, making use of parallel execution and traceability. From the functional point of view, integrated corpus pre-processing, generation of predictive-based and count-based models and unified ac- cess as a service are key features. To support this demand, this paper describes INDRA, a word embedding/distributional semantics framework which supports the creation, use and evaluation of word embedding models. INDRA provides a software infrastruc- ture to facilitate the experimentation and customisation of multilingual WEMs, allowing end-users and applications to consume and operate over multiple word embedding spaces as a service or library. INDRA is available from two repositories (github.com/ Lambda-3/Indra and github.com/Lambda-3/ …

Content truncated to 500 words