Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition

Casillas, Arantza; Ezeiza, Nerea; Goenaga, Iakes; Pérez, Alicia; Soto, Xabier

doi:10.1016/j.ijmedinf.2019.05.022

Cited by 13 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes different word embeddings (CoRoLa and MARCELL embeddings) and also combinations of the two embeddings. Previous work (Pȃis , and Mitrofan, 2021), (Casillas et al, 2019) has shown that using different word embeddings and combinations can improve NER performance. For each word representation we adapted the main BiLSTM layer size to match the embedding size.…”

Section: System Architecturementioning

confidence: 99%

Named Entity Recognition in the Romanian Legal Domain

Pais¹,

Mitrofan²,

Gasan³

et al. 2021

Proceedings of the Natural Legal Language Processing Workshop 2021

View full text Add to dashboard Cite

Recognition of named entities present in text is an important step towards information extraction and natural language understanding. This work presents a named entity recognition system for the Romanian legal domain. The system makes use of the gold annotated Legal-NERo corpus. Furthermore, the system combines multiple distributional representations of words, including word embeddings trained on a large legal domain corpus. All the resources, including the corpus, model and word embeddings are open sourced. Finally, the best system is available for direct usage in the RE-LATE platform.

show abstract

Section: System Architecturementioning

confidence: 99%

Named Entity Recognition in the Romanian Legal Domain

Pais¹,

Mitrofan²,

Gasan³

et al. 2021

Proceedings of the Natural Legal Language Processing Workshop 2021

View full text Add to dashboard Cite

show abstract

“…Word embedding techniques have been effective in learning low-dimensional vector space representations of an input word and capturing semantic relationships among words. Word embedding has been extended to the representations of sentences and paragraphs [24], relational entities [25,26], descriptive texts of images [27,28], entities [29,30] and so on. It is computationally more efficient than many other competitive techniques [8,31,32] and thus, many IR systems have recently attained enhanced performance with less human engineering using such techniques.…”

Section: Related Workmentioning

confidence: 99%

Improving personalised query reformulation with embeddings

Zhang

2021

Journal of Information Science

View full text Add to dashboard Cite

As a mechanism to guide users towards a better representation of their information needs, the query reformulation method generates new queries based on users’ historical queries. To preserve the original search intent, query reformulations should be context-aware and should attempt to meet users’ personal information needs. The mainstream method aims to generate candidate queries first, according to their past frequencies, and then score (re-rank) these candidates based on the semantic consistency of terms, dependency among latent semantic topics and user preferences. We exploit embeddings (i.e. term, user and topic embeddings) to use contextual information and individual preferences more effectively to improve personalised query reformulation. Our work involves two major tasks. In the first task, candidate queries are generated from an original query by substituting or adding one term, and the contextual similarities between the terms are calculated based on the term embeddings and augmented with user personalisation. In the second task, the candidate queries generated in the first task are evaluated and scored (re-ranked) according to the consistency of the semantic meaning of the candidate query and the user preferences based on a graphical model with the term, user and topic embeddings. Experiments show that our proposed model yields significant improvements compared with the current state-of-the-art methods.

show abstract

“…Besides these competitions in recent years, improvements have been made mostly in the entity recognition subtask using neural networks such as Bi-LSTM + CRFs (Lample et al, 2016). (Casillas et al, 2019) used the tool for the detection of entities in clinical texts in Spanish, obtaining improvements with respect to previous works (Perez et al, 2017), from an F1-Score of 70.30 to 72.01. Employing a similar system (Goenaga et al, 2018) obtained the first position at the last IberEval shared task (Hermenegildo Fabregat and Araujo, 2018).…”

Section: Related Workmentioning

confidence: 99%

IxaMed at PharmacoNER Challenge 2019

Lahuerta

Goenaga

Gojenola

et al. 2019

Proceedings of the 5th Workshop on BioNLP Open Shared Tasks

Self Cite

View full text Add to dashboard Cite

The aim of this paper is to present our approach (IxaMed) on the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.

show abstract

Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition

Cited by 13 publications

References 17 publications

Named Entity Recognition in the Romanian Legal Domain

Named Entity Recognition in the Romanian Legal Domain

Improving personalised query reformulation with embeddings

IxaMed at PharmacoNER Challenge 2019

Contact Info

Product

Resources

About