Chemical entity recognition in patents by combining dictionary-based and statistical approaches

Akhondi, Saber A.; Pons, Ewoud; Afzal, Zubair; Haagen, Herman van; Becker, Benedikt; Hettne, Kristina; Mulligen, Erik M. van; Kors, Jan A.

doi:10.1093/database/baw061

Cited by 21 publications

(15 citation statements)

References 38 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extraction of chemical compounds from chemical-related patents has recently been studied, focusing on patent titles and abstracts (28, 31, 52) or full texts (3, 20, 21, 27, 51). The majority of these studies concentrated on identifying chemical compounds in text while disregarding the structures of the extracted compounds (31, 52).…”

Section: Discussionmentioning

confidence: 99%

“…Obtaining high precision and recall values in the first step is essential for the success of the second step. Based on the findings of our previous studies (27, 28), we used an ensemble approach combining dictionary-based and morphology-based approaches to obtain high precision and recall. These approaches require a small annotated corpus (26, 33) and can provide a structural representation of the extracted compounds.…”

Section: Discussionmentioning

confidence: 99%

“…CER was loaded with a dictionary derived from the manually curated compounds in the Reaxys database. Similar to previous studies (27, 28), an exclusion list was used to filter out any noise (e.g. frequent compounds such as oxygen) from the extracted compounds.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic identification of relevant chemical compounds from patents

Akhondi

Rey²,

Schwörer³

et al. 2019

Database

View full text Add to dashboard Cite

In commercial research and development projects, public disclosure of new chemical compounds often takes place in patents. Only a small proportion of these compounds are published in journals, usually a few years after the patent. Patent authorities make available the patents but do not provide systematic continuous chemical annotations. Content databases such as Elsevier’s Reaxys provide such services mostly based on manual excerptions, which are time-consuming and costly. Automatic text-mining approaches help overcome some of the limitations of the manual process. Different text-mining approaches exist to extract chemical entities from patents. The majority of them have been developed using sub-sections of patent documents and focus on mentions of compounds. Less attention has been given to relevancy of a compound in a patent. Relevancy of a compound to a patent is based on the patent’s context. A relevant compound plays a major role within a patent. Identification of relevant compounds reduces the size of the extracted data and improves the usefulness of patent resources (e.g. supports identifying the main compounds). Annotators of databases like Reaxys only annotate relevant compounds. In this study, we design an automated system that extracts chemical entities from patents and classifies their relevance. The gold-standard set contained 18 789 chemical entity annotations. Of these, 10% were relevant compounds, 88% were irrelevant and 2% were equivocal. Our compound recognition system was based on proprietary tools. The performance (F-score) of the system on compound recognition was 84% on the development set and 86% on the test set. The relevancy classification system had an F-score of 86% on the development set and 82% on the test set. Our system can extract chemical compounds from patents and classify their relevance with high performance. This enables the extension of the Reaxys database by means of automation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic identification of relevant chemical compounds from patents

Akhondi

Rey²,

Schwörer³

et al. 2019

Database

View full text Add to dashboard Cite

show abstract

“…There is growing interest in hybrid machine learning and dictionary systems such as the one described in [ 10 ], which obtains interesting performance on chemical entity recognition in patent texts. The authors of [ 55 ] use different approaches for different entity types (machine learning for chemical names, dictionary-based for organism and assay entities); given the complementary application, this is not a hybrid approach in the strict sense.…”

Section: Discussionmentioning

confidence: 99%

“…Two or more of the previously mentioned approaches are used together to combine their strengths and, hopefully, overcome their weaknesses. For example, [ 9 ] and [ 10 ] successfully use a hybrid dictionary-machine learning approach.…”

Section: Introductionmentioning

confidence: 99%

Entity recognition in the biomedical domain using a hybrid approach

et al. 2017

View full text Add to dashboard Cite

BackgroundThis article describes a high-recall, high-precision approach for the extraction of biomedical entities from scientific articles.MethodThe approach uses a two-stage pipeline, combining a dictionary-based entity recognizer with a machine-learning classifier. First, the OGER entity recognizer, which has a bias towards high recall, annotates the terms that appear in selected domain ontologies. Subsequently, the Distiller framework uses this information as a feature for a machine learning algorithm to select the relevant entities only. For this step, we compare two different supervised machine-learning algorithms: Conditional Random Fields and Neural Networks.ResultsIn an in-domain evaluation using the CRAFT corpus, we test the performance of the combined systems when recognizing chemicals, cell types, cellular components, biological processes, molecular functions, organisms, proteins, and biological sequences. Our best system combines dictionary-based candidate generation with Neural-Network-based filtering. It achieves an overall precision of 86% at a recall of 60% on the named entity recognition task, and a precision of 51% at a recall of 49% on the concept recognition task.ConclusionThese results are to our knowledge the best reported so far in this particular task.

show abstract

Overview of ChEMU 2022 Evaluation Campaign: Information Extraction in Chemical Patents

Fang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Chemical entity recognition in patents by combining dictionary-based and statistical approaches

Cited by 21 publications

References 38 publications

Automatic identification of relevant chemical compounds from patents

Automatic identification of relevant chemical compounds from patents

Entity recognition in the biomedical domain using a hybrid approach

Overview of ChEMU 2022 Evaluation Campaign: Information Extraction in Chemical Patents

Contact Info

Product

Resources

About