How to generate data for acronym detection and expansion

Choi, S.K.; Puranik, Piyush; Dahal, Binay; Taghva, Kazem

doi:10.1007/s43674-021-00024-6

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in practice, the BERT model yielded poor results, largely due to the lack of definitions retained in the model. In a previous paper [19], we explored the use of BERT on acronym-type abbreviations, and it presented a 94% acceptance rate. Using the same method, but querying for contractions, the BERT model scored 0% for acceptance.…”

Section: Ad Hoc Abbreviationsmentioning

confidence: 99%

“…Essentially, BERT is an upgrade on recurrent neural network models, as it is able to take in information directionlessly. Previously, we demonstrated some of the power of BERT in its ability to generate abbreviation definitions [19] and further successfully tested it on ambiguous definitions [13]. The authors Daza et al utilized a SloBERTa model with an additional single neural layer to tackle abbreviation disambiguation for Slovenian biographical lexicons [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Findings on Ad Hoc Contractions

Choi

Taghva

2023

Information

Self Cite

View full text Add to dashboard Cite

Abbreviations are often overlooked, since their frequency and acceptance are almost second nature in everyday communication. Business names, handwritten notes, online messaging, professional domains, and different languages all have their own set of abbreviations. The abundance and frequent introduction of new abbreviations cause multiple areas of overlaps and ambiguity, which mean documents often lose their clarity. We reverse engineered the process of creating these ad hoc abbreviations and revealed some preliminary statistics on what makes them easier or harder to define. In addition, we generated candidate definitions for which it proved difficult for a word sense disambiguation model to select the correct definition.

show abstract

Section: Ad Hoc Abbreviationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Findings on Ad Hoc Contractions

Choi

Taghva

2023

Information

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, Wikipedia pages are used as a source for doing their experiments. But a drawback of this method is that it cannot find alternative meanings for the same acronym even in the same passage (Choi et al, 2022). 5 Ambiguity in the acronym meaning exists across the categories.…”

Section: Related Workmentioning

confidence: 99%

Heuristics‐based sequence labelling model for finding educational domain acronym expansions

Menaha¹,

Jayanthi

2022

Expert Systems

View full text Add to dashboard Cite

An acronym is a short form of the text used in many applications like Web search, Research and scientific documents, information retrieval, biomedical documents, etc.The main objective of the work is to develop a heuristics-based sequence labelling model to identify acronym expansion pairs in educational documents. The proposed system is implemented in four phases: (i) Data Collection (ii) Acronym Sequence Identification (iii) Expansion Determination and (iv) Acronym Expansion Validation. In this work, the acronym sequences identification is done by heuristic rules. Determining expansions is accomplished by a heuristics-based sequence labelling model. Again, the validation of acronym expansion sequences is also done by using heuristics rules.The result section shows that our proposed heuristics-based sequence labelling model achieved 98.4% accuracy in finding acronym expansion pairs from education research documents. The results are also compared with the acronym finder online acronym expansion repository and proved that more new acronym expansion sequences are identified by using our model.

show abstract

Abbreviation Disambiguation: A Review of Modern Techniques to Improve Machine Reading Comprehension

Choi,

Taghva

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

How to generate data for acronym detection and expansion

Cited by 3 publications

References 13 publications

Findings on Ad Hoc Contractions

Findings on Ad Hoc Contractions

Heuristics‐based sequence labelling model for finding educational domain acronym expansions

Abbreviation Disambiguation: A Review of Modern Techniques to Improve Machine Reading Comprehension

Contact Info

Product

Resources

About