A reproducible survey on word embeddings and ontology-based methods for word similarity: Linear combinations outperform the state of the art

Lastra-Díaz, Juan J.; Goikoetxea, Josu; Taieb, Mohamed Ali Hadj; Garcı́a-Serrano, Ana; Aouicha, Mohamed Ben; Agirre, Eneko

doi:10.1016/j.engappai.2019.07.010

Cited by 76 publications

(85 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastra‐Díaz et al stated that the collocation of word embeddings and ontologies resulted the best overall results on word similarity and relatedness according to their experiments (Lastra‐Díaz et al, ). Ali et al proposed an ontology and LDA‐based topic modelling and word embedding system to enhance the performance of document representation and sentiment classification (Ali et al, ).…”

Section: Discussionmentioning

confidence: 99%

Assessment of text coherence using an ontology‐based relatedness measurement method

Giray¹,

Ünalır

2019

Expert Systems

View full text Add to dashboard Cite

This paper proposes a novel method for assessing text coherence. Central to this approach is an ontology‐based representation of text, which captures the level of relatedness between consecutive sentences via ontologies. Our method encompasses annotating text using ontological concepts and assessing text coherence based on relatedness measurement among these concepts. The ontology‐based relatedness measurement method used in this study considers various types of relationships in ontologies and derived relationships via an inference engine for computing relatedness. We hypothesized that rich variety of relationships and inferred facts in ontologies would improve the success of text coherence assessment. Our results demonstrate that the use of ontologies yields to coherence values that have a higher correlation with human ratings.

show abstract

Section: Discussionmentioning

confidence: 99%

Assessment of text coherence using an ontology‐based relatedness measurement method

Giray¹,

Ünalır

2019

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Specialized clinical text embeddings have been used to improve clinical named entity recognition (75), resolve abbreviations in clinical text (76), expand a structured lexicon of radiology terms (77) and build a lexicon of dietary supplements (78). Second, an embedding can incorporate structured information beyond what is found in the text (79), and embeddings have been created to represent CUIs (80), documents (81,82), or entire patient records (83). Any task in which the notion of similarity is important, particularly when that similarity is based on patterns in text, can probably benefit from embeddings.…”

Section: Word Phrase and Character Embeddingsmentioning

confidence: 99%

Modern Clinical Text Mining: A Guide and Review

Percha¹

2020

Preprint

View full text Add to dashboard Cite

Electronic health records (EHRs) are becoming a vital source of data for healthcare quality improvement, research, and operations. However, much of the most valuable information contained in EHRs remains buried in unstructured text. The field of clinical text mining has advanced rapidly in recent years, transitioning from rule-based approaches to machine learning and, more recently, deep learning. With new methods come new challenges, however, especially for those new to the field. This review provides an overview of clinical text mining for those who are encountering it for the first time (e.g. physician researchers, operational analytics teams, machine learning scientists from other domains). While not a comprehensive survey, it describes the state of the art, with a particular focus on new tasks and methods developed over the past few years. It also identifies key barriers between these remarkable technical advances and the practical realities of implementation at health systems and in industry.

show abstract

“…Indeed for word embeddings there is an increase in methods to evaluate words representations intrinsically such as (Schnabel et al, 2015). All these techniques are thoroughly summarized by the survey (Lastra-Díaz et al, 2019). This is a fruitful direction, because having such evaluation metrics we can validate the knowledge acquired by all trained embedding spaces.…”

Section: Introductionmentioning

confidence: 99%

dom2vec: Unsupervised protein domain embeddings capture domains structure and function providing data-driven insights into collocations in domain architectures

Malone²,

Nejdl

2020

Preprint

View full text Add to dashboard Cite

Motivation: Word embedding approaches have revolutionized Natural Lange Processing (NLP) research. These approaches aim to map words to a low-dimensional vector space in which words with similar linguistic features are close in the vector space. These NLP approaches also preserve local linguistic features, such as analogy. Embedding-based approaches have also been developed for proteins. To date, such approaches treat amino acids as words, and proteins are treated as sentences of amino acids. These approaches have been evaluated either qualitatively, via visual inspection of the embedding space, or extrinsicaly, via performance on a downstream task. However, it is difficult to directly assess the intrinsic quality of the learned embeddings. Results: In this paper, we introduce dom2vec, an approach for learning protein domain embeddings. We also present four intrinsic evaluation strategies which directly assess the quality of protein domain embeddings. We leverage the hierarchy relationship of InterPro domains, known secondary structure classes, Enzyme Commision class information, and Gene Ontology annotations in these assessments. Importantly, these evaluations allow us to assess the quality of learned embeddings independently of a particular downstream task, similar to the local linguistic features used in traditional NLP. We also show that dom2vec embeddings are competitive with, or even outperform, state-of-the-art approaches on downstream tasks. Availability: The protein domain embeddings vectors and the entire code to reproduce the results will become available. Contact: melidis@l3s.uni-hannover.de

show abstract

A reproducible survey on word embeddings and ontology-based methods for word similarity: Linear combinations outperform the state of the art

Cited by 76 publications

References 78 publications

Assessment of text coherence using an ontology‐based relatedness measurement method

Assessment of text coherence using an ontology‐based relatedness measurement method

Modern Clinical Text Mining: A Guide and Review

dom2vec: Unsupervised protein domain embeddings capture domains structure and function providing data-driven insights into collocations in domain architectures

Contact Info

Product

Resources

About