Relatedness Computation Research Articles

Language relatedness evaluation for multilingual neural machine translation

Multilingual neural machine translation (MNMT) has attracted more and more attention in recent days because it can use a single neural machine translation (NMT) model to translate between multiple languages. As several languages are involved in MNMT, recent studies have shown that using part of these languages rather than all of them to train the model leads to comparable results. However, previous work on this topic mainly focuses on language clustering and features defined by linguists. The semantic relationship and language distance are not fully considered. How to select the most related language pairs to current low-resource pair to optimize the performance of MNMT is still an open question. In this paper, we propose to take language relatedness computation as a ranking problem, where features such as language distance, linguistic typological information and semantic relatedness features are incorporated into a random decision forest to improve the language relatedness evaluation (LRE) for MNMT. Since the model only focuses on monolingual LRE in general cross-lingual natural language processing tasks, we also propose two features related to machine translation (data size and bilingual relatedness) to predict the final language pairs. Experimental results on IWSLT and WMT datasets show that our proposed LRE method can achieve significant improvements compared with other models. We also conducted several groups of experiments on IWSLT and WMT datasets to further evaluate the effectiveness of the proposed method on MNMT. The results show that the MNMT model trained on language pairs predicted by the LRE method outperforms other language selection methods.

Wikipedia bi-linear link (WBLM) model: A new approach for measuring semantic similarity and relatedness between linguistic concepts using Wikipedia link structure

Wikipedia links its articles by manually defined semantic relations called the Wikipedia hyperlink (link) structure. The existing Wikipedia link-based semantic similarity (SS) and semantic relatedness (SR) computation models, such as Wikipedia one-way link (WOLM) model and Wikipedia two-way link (WTLM) model, do not assess the strengths of the relationships between a candidate concept and its links (out-links or in-links). These models treat all the links as equally important even though some links are semantically more influential than others and should be given more importance. This phenomenon reduces the accuracy of these models. This paper presents the Wikipedia bi-linear link (WBLM) model that extends the previously proposed WOLM and WTLM models. The WBLM model explores the Wikipedia link structure as a semantic graph and discovers the strongly (bi-linear links) and weakly (out-links or in-links) connected links of a candidate concept. It improves the link-based vector representations of concepts by assigning weights to their connected links according to the strengths of their semantic associations. The experimental results demonstrate that the proposed WBLM model significantly improves the SS and SR computation accuracy of the WOLM model (6.9%, 8%, 24%, 17.3%, 31.2%, 30.6%, 26.5%, and 35.4%) and WTLM model (1.2%, 3.9%, 7.1%, 9.9%, 11%, 6.3%, 12.7%, and 13%), in terms of linear correlations with human judgments on gold standard benchmarks, including MC30, RG65, WS203, SimLex, 353All, MTurk287, MTurk771, and MEN3000, respectively. Moreover, this research offers a deep insight into the Wikipedia link structure and provides an adequate base for understanding it as a semantic graph.

On Computing Entity Relatedness in Wikipedia, with Applications

Many text mining tasks, such as clustering, classification, retrieval, and named entity linking, benefit from a measure of relatedness between entities in a knowledge graph. We present a thorough study of all entity relatedness measures in recent literature based on Wikipedia as the knowledge graph. To facilitate this study, we introduce a new dataset with human judgments of entity relatedness. No clear dominance is seen between measures based on textual similarity and graph proximity. Some of the better measures involve expensive global graph computations. We propose a new, space-efficient, computationally lightweight, two-stage framework for relatedness computation. In the first stage, a small weighted subgraph is dynamically grown around the two query entities; in the second stage, relatedness is derived based on computations on this subgraph. Our system shows better agreement with human judgment than existing proposals both on the new dataset and on an established one. Our framework also shows improvements with respect to the state-of-the-art on three different extrinsic evaluations in the domains of ranking entity pairs, entity linking, and synonym extraction.

Measuring similarity and relatedness using multiple semantic relations in WordNet

Semantic similarity and relatedness computation has attracted an increasing amount of attention among researchers. The majority of previous studies, including edge-based and information content-based methods, rely on a single semantic relationship in WordNet such as the “is-a” relation. However, a performance ceiling may have been created by semantic unicity and inadequate calculation in solely “is-a” relation-based measurements, i.e., the computed results for some word pairs are too small and significantly deviate from human judgments. For this problem, we propose the following solutions: (1) We introduce the notion of the nearest common descendant to provide a supplement for commonalities between concepts according to genetics theory. (2) We design various targeted methods for different incomplete semantic relations. Therefore, various semantic relations can participate in similarity and relatedness computations in their most appropriate manners. (3) We utilize the cross-use of incomplete semantic relations similar-to and antonymy to solve the challenge of adjective and adverb similarity/relatedness measurements in WordNet. (4) We propose a targeted independent computation and largest contribution aggregation method to break through the performance ceiling of similarity/relatedness measurements based on single “is-a” relations. We conduct evaluations of our proposed model using seven extensively employed datasets. These evaluations indicate that our method significantly improves the performance of the existing methods based on single “is-a” relations. Their best Pearson coefficient with human judgments on both the MC30 and RG65 is increased to 0.9. With the development and enrichment of semantic relations in WordNet, our proposed model can be expected to have a more prominent role.

Çizge Tabanlı WordNet Ağı Üzerinde Anlamsal İlişki Ağırlıklarının Tespiti

Determination of semantic relatedness between two textual items is one of the crucial phases in many Natural Language Processing applications. In this study, a new approach to lexicon based semantic relation determination methods was experienced using WordNet 3.0 and Men’s real-life similarity dataset. Men’s test collection was used for the determination of the relation weights and determined weights were used in semantic relatedness computation. RG65 similarity dataset was used for a benchmark of the proposed method and Spearman correlation 0.81 was gained, taking into account that retrieving the relations weight using a large scale dataset and testing them with another real-life dataset promises new perspectives to the determination of the relations weight and to the relatedness computation .

Approaches for Semantic Relatedness Computation for Big Data

Computation of semantic relatedness between words, concepts, sentences or documents is a fundamental task in many areas like Text Mining, Information Retrieval and so on but as we know that data is increasing day by day Leading to Big Data. Traditional softwares which were much efficient and heavily used are not able to handle Big Data i.e. they cannot give result in reasonable amount of time for Big Data. So Hadoop and Spark like tools have been developed to handle Big Data. Similarly our different algorithms and formulas, being efficient on small data, needs to be updated and tuned according to big data. Thus in text mining semantic mining leads to the extraction of semantic vector or context vector and using different formula like Mutual Information (MI), Balanced Mutual Information (BMI), Normalized Google Distance(NGD), etc. techniques to calculate fuzzy membership values of elements of vector to its corresponding concepts. Thus Semantic Similarity is calculated between two concepts by considering repeatedly the semantic similarity or information gain between two elements of each vector. Then Semantic similarity between two concepts is calculated. Thus we have a matrix similar to Vector Space Model (VSM) but these contains fuzzy membership values rather than frequency of terms. We have proposed Map Reduce based Semantic Relatedness computation technique for Big Data.

A Lexical Resource-Constrained Topic Model for Word Relatedness

Word relatedness computation is an important supporting technology for many tasks in natural language processing. Traditionally, there have been two distinct strategies for word relatedness measurement: one utilizes corpus-based models, whereas the other leverages external lexical resources. However, either solution has its strengths and weaknesses. In this paper, we propose a lexical resource-constrained topic model to integrate the two complementary strategies effectively. Our model is an extension of probabilistic latent semantic analysis, which automatically learns word-level distributed representations forward relatedness measurement. Furthermore, we introduce generalized expectation maximization (GEM) algorithm for statistical estimation. The proposed model not merely inherit the advantage of conventional topic models in dimension reduction, but it also refines parameter estimation by using word pairs that are known to be related. The experimental results in different languages demonstrate the effectiveness of our model in topic extraction and word relatedness measurement.

An Approach to Measuring Semantic Relatedness of Geographic Terminologies Using a Thesaurus and Lexical Database Sources

In geographic information science, semantic relatedness is important for Geographic Information Retrieval (GIR), Linked Geospatial Data, geoparsing, and geo-semantics. But computing the semantic similarity/relatedness of geographic terminology is still an urgent issue to tackle. The thesaurus is a ubiquitous and sophisticated knowledge representation tool existing in various domains. In this article, we combined the generic lexical database (WordNet or HowNet) with the Thesaurus for Geographic Science and proposed a thesaurus–lexical relatedness measure (TLRM) to compute the semantic relatedness of geographic terminology. This measure quantified the relationship between terminologies, interlinked the discrete term trees by using the generic lexical database, and realized the semantic relatedness computation of any two terminologies in the thesaurus. The TLRM was evaluated on a new relatedness baseline, namely, the Geo-Terminology Relatedness Dataset (GTRD) which was built by us, and the TLRM obtained a relatively high cognitive plausibility. Finally, we applied the TLRM on a geospatial data sharing portal to support data retrieval. The application results of the 30 most frequently used queries of the portal demonstrated that using TLRM could improve the recall of geospatial data retrieval in most situations and rank the retrieval results by the matching scores between the query of users and the geospatial dataset.

Web documents semantic similarity by extending document ontology using current trends

Semantic evaluation of similarity index is computation of relatedness between terms/concepts/documents. In this paper, we have given a novel semantic similarity approach to overcome the limitations that exists in calculating semantic similarity score. In our approach we are extracting words/terms from the set of documents, and then replacing the extracted words/terms by their respective set of probable concepts stored in a dictionary. The concepts retrieved from the dictionary are connected using relationships from a base ontology for construction of document ontology corresponding to a given document. The ontology constructed this way is further extended using trend relationships stored in a separate database. Finally, the extended documents' ontology is compared for finding the relatedness between the documents. It is proved empirically that the proposed approach gives the better results of semantic similarity as compared with the conventional approaches.

Large scale biomedical texts classification: a kNN and an ESA-based approaches

BackgroundWith the large and increasing volume of textual data, automated methods for identifying significant topics to classify textual documents have received a growing interest. While many efforts have been made in this direction, it still remains a real challenge. Moreover, the issue is even more complex as full texts are not always freely available. Then, using only partial information to annotate these documents is promising but remains a very ambitious issue.MethodsWe propose two classification methods: a k-nearest neighbours (kNN)-based approach and an explicit semantic analysis (ESA)-based approach. Although the kNN-based approach is widely used in text classification, it needs to be improved to perform well in this specific classification problem which deals with partial information. Compared to existing kNN-based methods, our method uses classical Machine Learning (ML) algorithms for ranking the labels. Additional features are also investigated in order to improve the classifiers’ performance. In addition, the combination of several learning algorithms with various techniques for fixing the number of relevant topics is performed. On the other hand, ESA seems promising for this classification task as it yielded interesting results in related issues, such as semantic relatedness computation between texts and text classification. Unlike existing works, which use ESA for enriching the bag-of-words approach with additional knowledge-based features, our ESA-based method builds a standalone classifier. Furthermore, we investigate if the results of this method could be useful as a complementary feature of our kNN-based approach.ResultsExperimental evaluations performed on large standard annotated datasets, provided by the BioASQ organizers, show that the kNN-based method with the Random Forest learning algorithm achieves good performances compared with the current state-of-the-art methods, reaching a competitive f-measure of 0.55 % while the ESA-based approach surprisingly yielded unsatisfactory results.ConclusionsWe have proposed simple classification methods suitable to annotate textual documents using only partial information. They are therefore adequate for large multi-label classification and particularly in the biomedical domain. Thus, our work contributes to the extraction of relevant information from unstructured documents in order to facilitate their automated processing. Consequently, it could be used for various purposes, including document indexing, information retrieval, etc.

Exploiting salient semantic analysis for information retrieval

ABSTRACTRecently, many Wikipedia-based methods have been proposed to improve the performance of different natural language processing (NLP) tasks, such as semantic relatedness computation, text classification and information retrieval. Among these methods, salient semantic analysis (SSA) has been proven to be an effective way to generate conceptual representation for words or documents. However, its feasibility and effectiveness in information retrieval is mostly unknown. In this paper, we study how to efficiently use SSA to improve the information retrieval performance, and propose a SSA-based retrieval method under the language model framework. First, SSA model is adopted to build conceptual representations for documents and queries. Then, these conceptual representations and the bag-of-words (BOW) representations can be used in combination to estimate the language models of queries and documents. The proposed method is evaluated on several standard text retrieval conference (TREC) collections. Experiment results on standard TREC collections show the proposed models consistently outperform the existing Wikipedia-based retrieval methods.

CPRel: Semantic Relatedness Computation Using Wikipedia based Context Profiles

Semantic relatedness is a well known problem with its sig- nicance ranging from computational linguistics to Natural language Processing applications. Relatedness computation is restricted by the amount of common sense and background knowledge required to relate any two terms. This paper proposes a novel model of relatedness using context prole built on features extracted from encyclopedic knowledge. Proposed research makes use of Wikipedia to represent the context of a word in the high dimensional space of Wikipedia labels. Semantic relat- edness of a word pair is then assessed by comparing their corresponding context proles based on three dierent weighting schemes using tradi- tional Cosine similarity metrics. To evaluate proposed relatedness ap- proach, three well known benchmark datasets are used and it is shown that Wikipedia article contents can be used eectively to compute term relatedness. The experiments demonstrate that the proposed approach is computationally cheap as well as eective when correlated with human judgments.

The semantic measures library and toolkit: fast computation of semantic similarity and relatedness using biomedical ontologies

The semantic measures library and toolkit are robust open-source and easy to use software solutions dedicated to semantic measures. They can be used for large-scale computations and analyses of semantic similarities between terms/concepts defined in terminologies and ontologies. The comparison of entities (e.g. genes) annotated by concepts is also supported. A large collection of measures is available. Not limited to a specific application context, the library and the toolkit can be used with various controlled vocabularies and ontology specifications (e.g. Open Biomedical Ontology, Resource Description Framework). The project targets both designers and practitioners of semantic measures providing a JAVA library, as well as a command-line tool that can be used on personal computers or computer clusters. Downloads, documentation, tutorials, evaluation and support are available at http://www.semantic-measures-library.org.

Semantic Relatedness Measures in E-learning: A study

paper, a detailed study of works that have been carried out in finding the semantic relatedness or relatedness (in short) of Learning Objects (LO) in the context of E-learning has been presented. Learning Objects are small instructional chunks of learning elements which can be archived, extracted and shared in the learning process. Semantic relatedness in general specifies the degree of relatedness between two concepts in a taxonomy computed using different types of relations defined between the concepts. Semantic relatedness measures have been used in applications like Word sense Disambiguation, Information Retrieval, Natural Language Processing, Query Expansion etc. In the context of E-learning, there are several scenarios like learning object sequencing, query answering, scaffolding, clustering etc. where the computation of semantic relatedness between LO has promising scope. But only few works have been carried out in the quantification of semantic relatedness between LO. The objective of this paper is to present the existing semantic relatedness measures in general and with respect to learning object in specific and to analyze the adeptness of the measures. Keywords-learning, Learning Objects, Semantic Relatedness Measures

Text Relatedness Based on a Word Thesaurus

The computation of relatedness between two fragments of text in an automated manner requires taking into account a wide range of factors pertaining to the meaning the two fragments convey, and the pairwise relations between their words. Without doubt, a measure of relatedness between text segments must take into account both the lexical and the semantic relatedness between words. Such a measure that captures well both aspects of text relatedness may help in many tasks, such as text retrieval, classification and clustering. In this paper we present a new approach for measuring the semantic relatedness between words based on their implicit semantic links. The approach exploits only a word thesaurus in order to devise implicit semantic links between words. Based on this approach, we introduce Omiotis, a new measure of semantic relatedness between texts which capitalizes on the word-to-word semantic relatedness measure (SR) and extends it to measure the relatedness between texts. We gradually validate our method: we first evaluate the performance of the semantic relatedness measure between individual words, covering word-to-word similarity and relatedness, synonym identification and word analogy; then, we proceed with evaluating the performance of our method in measuring text-to-text semantic relatedness in two tasks, namely sentence-to-sentence similarity and paraphrase recognition. Experimental evaluation shows that the proposed method outperforms every lexicon-based method of semantic relatedness in the selected tasks and the used data sets, and competes well against corpus-based and hybrid approaches.