scholarly journals HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment

2017 ◽  
Vol 43 (4) ◽  
pp. 781-835 ◽  
Author(s):  
Ivan Vulić ◽  
Daniela Gerz ◽  
Douwe Kiela ◽  
Felix Hill ◽  
Anna Korhonen
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
Semantic Category ◽  
Representation Learning ◽  
Native English Speakers ◽  
Category Membership ◽  
Future Application ◽  
Data Set ◽  
Diverse Range ◽  
Concept Pairs

We introduce HyperLex—a data set and evaluation resource that quantifies the extent of the semantic category membership, that is, type-of relation, also known as hyponymy–hypernymy or lexical entailment (LE) relation between 2,616 concept pairs. Cognitive psychology research has established that typicality and category/class membership are computed in human semantic memory as a gradual rather than binary relation. Nevertheless, most NLP research and existing large-scale inventories of concept category membership (WordNet, DBPedia, etc.) treat category membership and LE as binary. To address this, we asked hundreds of native English speakers to indicate typicality and strength of category membership between a diverse range of concept pairs on a crowdsourcing platform. Our results confirm that category membership and LE are indeed more gradual than binary. We then compare these human judgments with the predictions of automatic systems, which reveals a huge gap between human performance and state-of-the-art LE, distributional and representation learning models, and substantial differences between the models themselves. We discuss a pathway for improving semantic models to overcome this discrepancy, and indicate future application areas for improved graded LE systems.

scholarly journals Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity

2020 ◽  
pp. 1-51
Author(s):  
Ivan Vulić ◽  
Simon Baker ◽  
Edoardo Maria Ponti ◽  
Ulla Petti ◽  
Ira Leviant ◽  
...  
Keyword(s):  
Semantic Similarity ◽  
Large Scale ◽  
Representation Learning ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lexical Representations ◽  
Language Data ◽  
Weakly Supervised ◽  
Cross Lingual

We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering data sets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e.g., Welsh, Kiswahili). Each language data set is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs, adjectives, adverbs), frequency ranks, similarity intervals, lexical fields, and concreteness levels. Additionally, owing to the alignment of concepts across languages, we provide a suite of 66 crosslingual semantic similarity data sets. Because of its extensive size and language coverage, Multi-SimLex provides entirely novel opportunities for experimental evaluation and analysis. On its monolingual and crosslingual benchmarks, we evaluate and analyze a wide array of recent state-of-the-art monolingual and crosslingual representation models, including static and contextualized word embeddings (such as fastText, monolingual and multilingual BERT, XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised crosslingual word embeddings. We also present a step-by-step data set creation protocol for creating consistent, Multi-Simlex -style resources for additional languages.We make these contributions—the public release of Multi-SimLex data sets, their creation protocol, strong baseline results, and in-depth analyses which can be be helpful in guiding future developments in multilingual lexical semantics and representation learning—available via aWeb site that will encourage community effort in further expansion of Multi-Simlex to many more languages. Such a large-scale semantic resource could inspire significant further advances in NLP across languages.

scholarly journals An effective drug-disease associations prediction model based on graphic representation learning over multi-biomolecular network

2022 ◽  
Vol 23 (1) ◽  
Author(s):  
Hanjing Jiang ◽  
Yabing Huang
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Representation Learning ◽  
Biological Data ◽  
Graph Representation ◽  
Data Set ◽  
Validation Experiment ◽  
Biomolecular Network ◽  
Disease Associations ◽  
Drug Reposition

Abstract Background Drug-disease associations (DDAs) can provide important information for exploring the potential efficacy of drugs. However, up to now, there are still few DDAs verified by experiments. Previous evidence indicates that the combination of information would be conducive to the discovery of new DDAs. How to integrate different biological data sources and identify the most effective drugs for a certain disease based on drug-disease coupled mechanisms is still a challenging problem. Results In this paper, we proposed a novel computation model for DDA predictions based on graph representation learning over multi-biomolecular network (GRLMN). More specifically, we firstly constructed a large-scale molecular association network (MAN) by integrating the associations among drugs, diseases, proteins, miRNAs, and lncRNAs. Then, a graph embedding model was used to learn vector representations for all drugs and diseases in MAN. Finally, the combined features were fed to a random forest (RF) model to predict new DDAs. The proposed model was evaluated on the SCMFDD-S data set using five-fold cross-validation. Experiment results showed that GRLMN model was very accurate with the area under the ROC curve (AUC) of 87.9%, which outperformed all previous works in terms of both accuracy and AUC in benchmark dataset. To further verify the high performance of GRLMN, we carried out two case studies for two common diseases. As a result, in the ranking of drugs that were predicted to be related to certain diseases (such as kidney disease and fever), 15 of the top 20 drugs have been experimentally confirmed. Conclusions The experimental results show that our model has good performance in the prediction of DDA. GRLMN is an effective prioritization tool for screening the reliable DDAs for follow-up studies concerning their participation in drug reposition.

scholarly journals Matching Biomedical Ontologies: Construction of Matching Clues and Systematic Evaluation of Different Combinations of Matchers (Preprint)

2021 ◽  
Author(s):  
Peng Wang ◽  
Yunyan Hu ◽  
Shaochen Bai ◽  
Shiyi Zou
Keyword(s):  
Time Complexity ◽  
Large Scale ◽  
Empirical Studies ◽  
Representation Learning ◽  
Substantial Improvement ◽  
Systematic Evaluation ◽  
Ontology Matching ◽  
Biomedical Ontologies ◽  
Data Set ◽  
Combination Strategies

BACKGROUND Ontology matching seeks to find semantic correspondences between ontologies. With an increasing number of biomedical ontologies being developed independently, matching these ontologies to solve the interoperability problem has become a critical task in biomedical applications. However, some challenges remain. First, extracting and constructing matching clues from biomedical ontologies is a nontrivial problem. Second, it is unknown whether there are dominant matchers while matching biomedical ontologies. Finally, ontology matching also suffers from computational complexity owing to the large-scale sizes of biomedical ontologies. OBJECTIVE To investigate the effectiveness of matching clues and composite match approaches, this paper presents a spectrum of matchers with different combination strategies and empirically studies their influence on matching biomedical ontologies. Besides, extended reduction anchors are introduced to effectively decrease the time complexity while matching large biomedical ontologies. METHODS In this paper, atomic and composite matching clues are first constructed in 4 dimensions: terminology, structure, external knowledge, and representation learning. Then, a spectrum of matchers based on a flexible combination of atomic clues are designed and utilized to comprehensively study the effectiveness. Besides, we carry out a systematic comparative evaluation of different combinations of matchers. Finally, extended reduction anchor is proposed to significantly alleviate the time complexity for matching large-scale biomedical ontologies. RESULTS Experimental results show that considering distinguishable matching clues in biomedical ontologies leads to a substantial improvement in all available information. Besides, incorporating different types of matchers with reliability results in a marked improvement, which is comparative to the state-of-the-art methods. The dominant matchers achieve F1 measures of 0.9271, 0.8218, and 0.5 on Anatomy, FMA-NCI (Foundation Model of Anatomy-National Cancer Institute), and FMA-SNOMED data sets, respectively. Extended reduction anchor is able to solve the scalability problem of matching large biomedical ontologies. It achieves a significant reduction in time complexity with little loss of F1 measure at the same time, with a 0.21% decrease on the Anatomy data set and 0.84% decrease on the FMA-NCI data set, but with a 2.65% increase on the FMA-SNOMED data set. CONCLUSIONS This paper systematically analyzes and compares the effectiveness of different matching clues, matchers, and combination strategies. Multiple empirical studies demonstrate that distinguishing clues have significant implications for matching biomedical ontologies. In contrast to the matchers with single clue, those combining multiple clues exhibit more stable and accurate performance. In addition, our results provide evidence that the approach based on extended reduction anchors performs well for large ontology matching tasks, demonstrating an effective solution for the problem.

scholarly journals Matching Biomedical Ontologies: Construction of Matching Clues and Systematic Evaluation of Different Combinations of Matchers

10.2196/28212 ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. e28212
Author(s):  
Peng Wang ◽  
Yunyan Hu ◽  
Shaochen Bai ◽  
Shiyi Zou
Keyword(s):  
Time Complexity ◽  
Large Scale ◽  
Empirical Studies ◽  
Representation Learning ◽  
Substantial Improvement ◽  
Systematic Evaluation ◽  
Ontology Matching ◽  
Biomedical Ontologies ◽  
Data Set ◽  
Combination Strategies

Background Ontology matching seeks to find semantic correspondences between ontologies. With an increasing number of biomedical ontologies being developed independently, matching these ontologies to solve the interoperability problem has become a critical task in biomedical applications. However, some challenges remain. First, extracting and constructing matching clues from biomedical ontologies is a nontrivial problem. Second, it is unknown whether there are dominant matchers while matching biomedical ontologies. Finally, ontology matching also suffers from computational complexity owing to the large-scale sizes of biomedical ontologies. Objective To investigate the effectiveness of matching clues and composite match approaches, this paper presents a spectrum of matchers with different combination strategies and empirically studies their influence on matching biomedical ontologies. Besides, extended reduction anchors are introduced to effectively decrease the time complexity while matching large biomedical ontologies. Methods In this paper, atomic and composite matching clues are first constructed in 4 dimensions: terminology, structure, external knowledge, and representation learning. Then, a spectrum of matchers based on a flexible combination of atomic clues are designed and utilized to comprehensively study the effectiveness. Besides, we carry out a systematic comparative evaluation of different combinations of matchers. Finally, extended reduction anchor is proposed to significantly alleviate the time complexity for matching large-scale biomedical ontologies. Results Experimental results show that considering distinguishable matching clues in biomedical ontologies leads to a substantial improvement in all available information. Besides, incorporating different types of matchers with reliability results in a marked improvement, which is comparative to the state-of-the-art methods. The dominant matchers achieve F1 measures of 0.9271, 0.8218, and 0.5 on Anatomy, FMA-NCI (Foundation Model of Anatomy-National Cancer Institute), and FMA-SNOMED data sets, respectively. Extended reduction anchor is able to solve the scalability problem of matching large biomedical ontologies. It achieves a significant reduction in time complexity with little loss of F1 measure at the same time, with a 0.21% decrease on the Anatomy data set and 0.84% decrease on the FMA-NCI data set, but with a 2.65% increase on the FMA-SNOMED data set. Conclusions This paper systematically analyzes and compares the effectiveness of different matching clues, matchers, and combination strategies. Multiple empirical studies demonstrate that distinguishing clues have significant implications for matching biomedical ontologies. In contrast to the matchers with single clue, those combining multiple clues exhibit more stable and accurate performance. In addition, our results provide evidence that the approach based on extended reduction anchors performs well for large ontology matching tasks, demonstrating an effective solution for the problem.

scholarly journals Semantic Data Set Construction from Human Clustering and Spatial Arrangement

2021 ◽  
pp. 1-48
Author(s):  
Olga Majewska ◽  
Diana McCarthy ◽  
Jasper J. F. van den Bosch ◽  
Nikolaus Kriegeskorte ◽  
Ivan Vulić ◽  
...  
Keyword(s):  
Semantic Similarity ◽  
Large Scale ◽  
Evaluation Method ◽  
Representation Learning ◽  
Full Description ◽  
Second Phase ◽  
Learning Models ◽  
Data Set ◽  
Semantic Classification ◽  
Similarity Judgments

Research into representation learning models of lexical semantics usually utilizes some form of intrinsic evaluation to ensure that the learned representations reflect human semantic judgments. Lexical semantic similarity estimation is a widely used evaluation method, but efforts have typically focused on pairwise judgments of words in isolation, or are limited to specific contexts and lexical stimuli. There are limitations with these approaches that either do not provide any context for judgments, and thereby ignore ambiguity, or provide very specific sentential contexts that cannot then be used to generate a larger lexical resource. Furthermore, similarity between more than two items is not considered. We provide a full description and analysis of our recently proposed methodology for large-scale data set construction that produces a semantic classification of a large sample of verbs in the first phase, as well as multiway similarity judgments made within the resultant semantic classes in the second phase. The methodology uses a spatial multi-arrangement approach proposed in the field of cognitive neuroscience for capturing multi-way similarity judgments of visual stimuli. We have adapted this method to handle polysemous linguistic stimuli and much larger samples than previous work.We specifically target verbs, but the method can equally be applied to other parts of speech. We perform cluster analysis on the data from the first phase and demonstrate how this might be useful in the construction of a comprehensive verb resource. We also analyze the semantic information captured by the second phase and discuss the potential of the spatially induced similarity judgments to better reflect human notions of word similarity.We demonstrate how the resultant data set can be used for fine-grained analyses and evaluation of representation learning models on the intrinsic tasks of semantic clustering and semantic similarity. In particular, we find that stronger static word embedding methods still outperform lexical representations emerging from more recent pre-training methods, both on word-level similarity and clustering. Moreover, thanks to the data set’s vast coverage, we are able to compare the benefits of specializing vector representations for a particular type of external knowledge by evaluating FrameNet- and VerbNet-retrofitted models on specific semantic domains such as “Heat” or “Motion.”

ProGen:Provenance database generator for large-scale data set

2009 ◽  
Vol 28 (11) ◽  
pp. 2737-2740
Author(s):  
Xiao ZHANG ◽  
Shan WANG ◽  
Na LIAN
Keyword(s):  
Large Scale ◽  
Data Set ◽  
Large Scale Data ◽  
Scale Data

A Drug Target Interaction Prediction Based on LINE-RF Learning

2020 ◽  
Vol 15 (7) ◽  
pp. 750-757
Author(s):  
Jihong Wang ◽  
Yue Shi ◽  
Xiaodan Wang ◽  
Huiyou Chang
Keyword(s):  
Network Topology ◽  
Drug Target ◽  
Large Scale ◽  
Representation Learning ◽  
New Drugs ◽  
Combination Method ◽  
Learning Methods ◽  
Network Representation ◽  
On Line ◽  
Clinical Experiments

Background: At present, using computer methods to predict drug-target interactions (DTIs) is a very important step in the discovery of new drugs and drug relocation processes. The potential DTIs identified by machine learning methods can provide guidance in biochemical or clinical experiments. Objective: The goal of this article is to combine the latest network representation learning methods for drug-target prediction research, improve model prediction capabilities, and promote new drug development. Methods: We use large-scale information network embedding (LINE) method to extract network topology features of drugs, targets, diseases, etc., integrate features obtained from heterogeneous networks, construct binary classification samples, and use random forest (RF) method to predict DTIs. Results: The experiments in this paper compare the common classifiers of RF, LR, and SVM, as well as the typical network representation learning methods of LINE, Node2Vec, and DeepWalk. It can be seen that the combined method LINE-RF achieves the best results, reaching an AUC of 0.9349 and an AUPR of 0.9016. Conclusion: The learning method based on LINE network can effectively learn drugs, targets, diseases and other hidden features from the network topology. The combination of features learned through multiple networks can enhance the expression ability. RF is an effective method of supervised learning. Therefore, the Line-RF combination method is a widely applicable method.

Integrative Data Analysis from a Unifying Research Synthesis Perspective

2018 ◽  
Author(s):  
Eun-Young Mun ◽  
Anne E. Ray
Keyword(s):  
Data Analysis ◽  
Large Scale ◽  
Research Synthesis ◽  
Alcohol Intervention ◽  
Data Set ◽  
Integrative Data Analysis ◽  
Level Data ◽  
Model Complex ◽  
Wide Range ◽  
Individual Participant

Integrative data analysis (IDA) is a promising new approach in psychological research and has been well received in the field of alcohol research. This chapter provides a larger unifying research synthesis framework for IDA. Major advantages of IDA of individual participant-level data include better and more flexible ways to examine subgroups, model complex relationships, deal with methodological and clinical heterogeneity, and examine infrequently occurring behaviors. However, between-study heterogeneity in measures, designs, and samples and systematic study-level missing data are significant barriers to IDA and, more broadly, to large-scale research synthesis. Based on the authors’ experience working on the Project INTEGRATE data set, which combined individual participant-level data from 24 independent college brief alcohol intervention studies, it is also recognized that IDA investigations require a wide range of expertise and considerable resources and that some minimum standards for reporting IDA studies may be needed to improve transparency and quality of evidence.

Building a Culture of Ethical, Comparable, Authentic Assessment

2019 ◽  
pp. 463-481
Author(s):  
Andrew Reid ◽  
Julie Ballantyne
Keyword(s):  
Teaching And Learning ◽  
Large Scale ◽  
Authentic Assessment ◽  
Subject Area ◽  
Music Educators ◽  
System Level ◽  
Diverse Range ◽  
Effective Learning ◽  
School Based ◽  
The Subject

In an ideal world, assessment should be synonymous with effective learning and reflect the intricacies of the subject area. It should also be aligned with the ideals of education: to provide equitable opportunities for all students to achieve and to allow both appropriate differentiation for varied contexts and students and comparability across various contexts and students. This challenge is made more difficult in circumstances in which the contexts are highly heterogeneous, for example in the state of Queensland, Australia. Assessment in music challenges schooling systems in unique ways because teaching and learning in music are often naturally differentiated and diverse, yet assessment often calls for standardization. While each student and teacher has individual, evolving musical pathways in life, the syllabus and the system require consistency and uniformity. The challenge, then, is to provide diverse, equitable, and quality opportunities for all children to learn and achieve to the best of their abilities. This chapter discusses the designing and implementation of large-scale curriculum as experienced in secondary schools in Queensland, Australia. The experiences detailed explore the possibilities offered through externally moderated school-based assessment. Also discussed is the centrality of system-level clarity of purpose, principles and processes, and the provision of supportive networks and mechanisms to foster autonomy for a diverse range of music educators and contexts. Implications for education systems that desire diversity, equity, and quality are discussed, and the conclusion provokes further conceptualization and action on behalf of students, teachers, and the subject area of music.

Sign in / Sign up

Export Citation Format

Share Document