Semantic Similarity from Natural Language and Ontology Analysis

Harispe, Sébastien; Ranwez, Sylvie; Janaqi, Stefan; Montmain, Jacky

doi:10.1007/978-3-031-02156-5

Cited by 59 publications

(27 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various frameworks have been introduced to automatically measure the semantic similarity between concepts [46, 47]. Among them, many focus on deriving statistical information from cohorts and combining them with lexical resources and knowledge graphs [48].…”

Section: Methodsmentioning

confidence: 99%

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding

Daniali

Galer

Lewis‐Smith

et al. 2022

Preprint

View full text Add to dashboard Cite

The Human Phenotype Ontology (HPO) is a dictionary of more than 15,000 clinical phenotypic terms with defined semantic relationships, developed to standardize their representation for phenotypic analysis. Over the last decade, the HPO has been used to accelerate the implementation of precision medicine into clinical practice. In addition, recent research in representation learning, specifically in graph embedding, has led to notable progress in automated prediction via learned features. Here, we present a novel approach to phenotype representation by incorporating phenotypic frequencies based on 53 million full- text health care notes from more than 1.5 million individuals. We demonstrate the efficacy of our proposed phenotype embedding technique by comparing our work to existing phenotypic similarity- measuring methods. Using phenotype frequencies in our embedding technique, we are able to identify phenotypic similarities that surpass the current computational models. In addition, we show that our embedding technique aligns with domain experts' judgment at a level that exceeds their agreement. We show that our proposed technique efficiently represents complex and multidimensional phenotypes in HPO format, which can then be used as input for various downstream tasks that require deep phenotyping, including patient similarity analyses and disease trajectory prediction.

show abstract

Section: Methodsmentioning

confidence: 99%

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding

Daniali

Galer

Lewis‐Smith

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A number of approaches for computing semantic similarity in computational linguistics and artificial intelligence have been proposed (Harispe et al, 2015;Lane et al, 2019;Chandrasekaran and Mago, 2021). These approaches include cosine, Manhattan distance, Kullback-Leibler divergence, Euclidean distance, and product measure etc.…”

Section: Contextual Semantic Similarity In Language Comprehension/pro...mentioning

confidence: 99%

“…Semantic similarity concerns the semantic connections or the relations between words, sen-tences, documents, or concepts. Semantic similarity, as a metric, has been widely applied in computational linguistics, artificial intelligence, and information science (see Harispe et al, 2015;Jabeen et al, 2020;Chandrasekaran and Mago, 2021). A number of approaches or models have been proposed for investigating the semantic similarity between words, such as Latent Semantic Analysis (LSA; Landauer et al, 1998) and the Bayesian models (Griffiths et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

An interpretable semantic similarity for predicting eye movements in reading: Approach comparison

Sun¹

2022

Preprint

View full text Add to dashboard Cite

Expectations or predictions about upcoming content play an important role during language comprehension and processing. Semantic similarity as a metric has been used to predict the experimental data on language comprehension and processing. Some approaches have been proposed to compute contextual semantic similarity to predict how words in a context are processed. However, these approaches can be improved. This study uses a massive and naturalistic discourse as stimuli for collecting data on eye-movement in reading. It proposes asimple but effective approach to computing contextual semantic similarity. In order to test the efficiency of the new approach, we compare it to the recently developed cosine method and the Euclidean method. This comparison reveals that our approach can make good predictions about fixation durations on reading and that it outperforms the two aforementioned approaches. To our knowledge, this is the first study to compare a number of approaches on contextual semantic similarity that are used to process naturalistic discourse in the fields of cogni-tion, psycholinguistics and neuroscience. The findings of this study aretherefore of significance to the acquisition of a better understanding ofhow humans process words in a real-world context and how they makepredictions in language comprehension and processing. This study creates an interpretable but more effective approach for computing contextual semantic similarity, which allows further explorations of the data on naturalistic discourse reading, language comprehension and neuroscience.

show abstract

“…Regarding the similarity of textual content, two common types of metrics are semantic similarity and semantic relatedness. These measures have been subject to intensive research efforts and are central to many Natural Language Processing applications [49]. Although the two are sometimes confused with each other, they are distinct: while semantic similarity measures how similar in meaning two pieces of text are, semantic relatedness can measure diverse types of relationships between them [40].…”

Section: Automatic Identificationmentioning

confidence: 99%

“…An implementation of the approach can use the textual content of the analysis spaces, including description, keywords, and contributions from the collaboration tools, to compare the semantic similarity/relatedness of two analysis spaces and automatically link them. The semantic measures rely on data sources such as text corpora and knowledge models [49]. The former consists of unstructured or semistructured texts such as plain text and dictionaries and evidence extraction can be based on co-occurrence of terms.…”

Section: Automatic Identificationmentioning

confidence: 99%

Collaborative geovisual analytics

Chapeton

View full text Add to dashboard Cite

show abstract

Semantic Similarity from Natural Language and Ontology Analysis

Cited by 59 publications

References 0 publications

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology Embedding

An interpretable semantic similarity for predicting eye movements in reading: Approach comparison

Collaborative geovisual analytics

Contact Info

Product

Resources

About