Overview of the Bacteria Biotope Task at BioNLP Shared Task 2016

Deléger, Louise; Bossy, Robert; Chaix, Estelle; Ba, Mouhamadou Lamine; Ferré, Arnaud; Bessières, Philippe

doi:10.18653/v1/w16-3002

Cited by 93 publications

(100 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The data used are those of the Bacteria Biotope categorization task (Task 3) of the 2016 BioNLP Shared Task (Deléger et al, 2016). The documents are references from MEDLINE, composed of titles and abstracts of scientific articles in the field of biology.…”

Section: Methodsmentioning

confidence: 99%

Representation of complex terms in a vector space structured by an ontology for a normalization task

Ferré¹,

Zweigenbaum²,

Nédellec³

2017

BioNLP 2017

View full text Add to dashboard Cite

We propose in this paper a semisupervised method for labeling terms of texts with concepts of a domain ontology. The method generates continuous vector representations of complex terms in a semantic space structured by the ontology. The proposed method relies on a distributional semantics approach, which generates initial vectors for each of the extracted terms. Then these vectors are embedded in the vector space constructed from the structure of the ontology. This embedding is carried out by training a linear model. Finally, we apply a cosine similarity to determine the proximity between vectors of terms and vectors of concepts and thus to assign ontology labels to terms. We have evaluated the quality of these representations for a normalization task by using the concepts of an ontology as semantic labels. Normalization of terms is an important step to extract a part of the information contained in texts, but the vector space generated might find other applications. The performance of this method is comparable to that of the state of the art for this task of standardization, opening up encouraging prospects.

show abstract

Section: Methodsmentioning

confidence: 99%

Representation of complex terms in a vector space structured by an ontology for a normalization task

Ferré¹,

Zweigenbaum²,

Nédellec³

2017

BioNLP 2017

View full text Add to dashboard Cite

show abstract

“…Each hidden state contains information about the whole input sequence with a strong focus on the parts surrounding the i-th word. The context vector (c i ) was computed as a weighted sum of these hidden states (h i ) using equation (2). The attention weight (a i ) of each hidden state (h j ) was then computed using equation (3).…”

Section: Additive Attentionmentioning

confidence: 99%

“…where they live. Information pertaining to the habitats where bacteria live is particularly critical in applied microbiology fields such as food safety, health sciences, and waste processing [2,3,4]. An example relation between bacteria and their location in this task is shown in Figure 1.…”

mentioning

confidence: 99%

Relation Extraction Between Bacteria and Biotopes from Biomedical Texts with Attention Mechanisms and Domain-Specific Contextual Representations

Jettakul

Wichadakul

Vateekul

2019

Preprint

View full text Add to dashboard Cite

The Bacteria Biotope (BB) task is biomedical relation extraction (RE) that aims to study the interaction between bacteria and their locations. This task is considered to pertain to fundamental knowledge in applied microbiology. Some previous investigations have used feature-based models; others have presented deep-learning-based models such as convolutional and recurrent neural networks used with the shortest dependency paths (SDPs). Although SDPs contain valuable and concise information, sections of significant information necessary to define bacterial location relationships are often neglected. In addition, the traditional word embedding used in previous studies may suffer from word ambiguation across linguistic contexts.Here, we present a deep learning model for biomedical RE. The model incorporates feature combinations of SDPs and full sentences with various attention mechanisms. We also used pre-trained contextual representations based on domain-specific vocabularies. In order to assess the model's robustness, we introduced a mean F1 score on many models using different random seeds. The experiments were conducted on the standard BB corpus in BioNLP-ST'16. Our experimental results revealed that the model performed better (in terms of both maximum and average F1 scores; 60.77% and 57.63%, respectively) compared with other existing models. We demonstrated that our proposed contributions to this task can be used to extract rich lexical, syntactic, and semantic features that effectively boost the model's performance. Moreover, we analyzed the trade-off between precision and recall in order to choose the proper cut-off to use in real-world applications.K eywords Biomedical text mining · Relation extraction · Deep learning · Attention networks · Contextual word embeddings · Domain-specific language IntroductionDue to the rapid development of computational and biological technology, the biomedical literature is expanding at an exponential rate [1]. This situation leads to difficulty manually extracting required information. In BioNLP-ST 2016, the Bacteria Biotope (BB) task [2] followed the general outline and goals of previous tasks defined in 2011 [3] and 2013 [4]. This task aims to investigate the interactions of bacteria and its biotope; habitats or geographical entity, from genetic, phylogenetic, and ecology perspectives. It involves the Lives_in relation, which is a mandatory relation between related arguments, the bacteria and the location * peerapon.v@chula.ac.th Our highest precision (0.975 cut-off) Recall: 46.90 Precision: 72.60 F1 score: 56.99 Our default (0.5 cut-off) Recall: 65.28 Precision: 56.85 F1 score: 60.77 Our highest recall (0.025 cut-off) Recall: 70.54 Precision: 50.11 F1 score: 58.59 BGRU-Attn Recall: 69.82 Precision: 48.76 F1 score: 57.42 TurkuNLP Recall: 44.80 Precision: 62.30 F1 score: 52.10

show abstract

“…The 2016 Bacteria/Biotope track 1 (Deléger et al, 2016) consists in three main objectives: (i) named entity recognition (NER) to identify mentions of bacteria and biotopes from scientific abstracts, (ii) categorization to normalize mentions of bacteria in the NCBI taxonomy and mentions of biotopes in the OntoBiotope ontology, and (iii) event extraction to identify relations of localization between a bacteria and a biotope.…”

Section: Presentationmentioning

confidence: 99%