UMDuluth-CS8761 at SemEval-2018 Task9: Hypernym Discovery using
            Hearst Patterns, Co-occurrence frequencies and Word Embeddings

Hassan, Arshia Zernab; Vallabhajosyula, Manikya Swathi; Pedersen, Ted

doi:10.18653/v1/s18-1149

Cited by 5 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypernym discovery enables the extraction of hierarchical relationships to form entity taxonomies and augment existing ontologies or vocabularies. Rule-based [42,43,44], vector space-based [45] neural [46] or hybrid [47] Alignment-based pattern-matching [54] and rule-based matching strategies [55], supervised machine learning [56], unsupervised [57], semi-supervised [3] and deep learning approaches, such as long-short term memory (LSTM) [58] or sequence-to-sequence architectures [59] Acronym disambiguation…”

Section: Semantic Analysismentioning

confidence: 99%

Exploring Natural Language Processing in Model-To-Model Transformations

Danėnas

Skersys

2022

IEEE Access

View full text Add to dashboard Cite

In this paper, we explore the possibility to apply natural language processing in visual modelto-model (M2M) transformations. Therefore, we present our research results on information extraction from text labels in process models modeled using Business Process Modeling Notation (BPMN) and use case models depicted in Unified Modeling Language (UML) using the most recent developments in natural language processing (NLP). In this paper, we focus on three relevant tasks, namely, the extraction of verb/noun phrases that would be used to form relations, parsing of conjunctive/disjunctive statements, and the detection of abbreviations and acronyms. Relation extraction was attempted to solve by implementing techniques that combine state-of-the-art NLP language models with formal regular expressions grammarbased structure detection. In this paper, we perform thorough testing of the most recent state-of-the-art NLP tools (CoreNLP, Stanford Stanza, Flair, Spacy, AllenNLP, BERT, ELECTRA), as well as custom BERT-BiLSTM-CRF and ELMo-BiLSTM-CRF implementations, trained with certain data augmentations to improve performance on the most ambiguous cases; these tools are used as a foundation for building tools to extract noun and verb phrases from short text labels generally used in UML and BPMN models. Furthermore, we describe our attempts to improve these extractors by solving the abbreviation/acronym detection problem using machine learning-based detection, as well as process conjunctive and disjunctive statements, due to their relevance to performing advanced text normalization. The obtained results show that the best phrase extraction and conjunctive phrase processing performance was obtained using Stanza based implementation, yet, our trained BERT-BiLSTM-CRF outperformed it for the verb phrase detection task. Our acronym detection approach resulted in the precision of 0.78 and F1-Score of 0.73 which may also be considered quite positive. While this work was inspired by our ongoing research on partial model-to-model transformations, we believe it to be applicable in other areas requiring similar text processing capabilities as well. INDEX TERMSinformation extraction; relation extraction; acronym detection; process models; use-case models; natural language processing; model-to-model transformation This work is inspired by our previous research on NLPenhanced information extraction in model-to-model trans- formations [6, 7]. However, the need for similar solutions was also identified in other areas involving visual modeling, such as business process modeling [8,9,10]. In this paper, we address the issue of relation extraction from graphical

show abstract

Section: Semantic Analysismentioning

confidence: 99%

Exploring Natural Language Processing in Model-To-Model Transformations

Danėnas

Skersys

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This is one of the key techniques used in noun phrase and verb phrase extraction, which is required to process element designations for proper generation of target elements. [83], neural [84], and hybrid [85] approaches are among the most prominent ones in this category.…”

mentioning

confidence: 99%

Extending Drag-and-Drop Actions-Based Model-to-Model Transformations with Natural Language Processing

2020

View full text Add to dashboard Cite

Model-to-model (M2M) transformations are among the key components of model-driven development, enabling a certain level of automation in the process of developing models. The developed solution of using drag-and-drop actions-based M2M transformations contributes to this purpose by providing a flexible, reusable, customizable, and relatively easy-to-use transformation method and tool support. The solution uses model-based transformation specifications triggered by user-initiated drag-and-drop actions within the model deployed in a computer-aided software engineering (CASE) tool environment. The transformations are called partial M2M transformations, meaning that a specific user-defined fragment of the source model is being transformed into a specific fragment of the target model and not running the whole model-level transformation. In this paper, in particular, we present the main aspects of the developed extension to that M2M transformation method, delivering a set of natural language processing (NLP) techniques on both the conceptual and implementation level. The paper addresses relevant developments and topics in the field of natural language processing and presents a set of operators that can be used to satisfy the needs of advanced textual preprocessing in the scope of M2M transformations. Also in this paper, we describe the extensions to the previous M2M transformation metamodel necessary for enabling the solution’s NLP-related capabilities. The usability and actual benefits of the proposed extension are introduced by presenting a set of specific partial M2M transformation use cases where natural language processing provides actual solutions to previously unsolvable situations when using the previous M2M transformation development.

show abstract