The effect of morphology in named entity recognition with sequence tagging

Gungor, Onur; Güngör, Tunga; Uskudarli, Suzan

doi:10.1017/s1351324918000281

Cited by 19 publications

(32 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown by Lample et al (2016) and Ma and Hovy (2016), these approaches yield state-of-the-art accuracy without the need for hand-crafted features or gazetteers employed in previous state-of-the-art statistical models (Finkel et al, 2005). In addition, it was recently shown by Güngör et al (2019Güngör et al ( , 2018 that, especially for morphologically rich languages such as Turkish and Finnish, using additional word representations based on linguistic properties of the words (encoded as the output of a morphological analyser) improves the performance further compared with using only representations based on the surface forms of words. Despite their success, however, these architectures have an evident shortcoming in that they only consider the top-level NE annotation while ignoring the nested entities during both training and prediction.…”

Section: Neural Network Architecturesmentioning

confidence: 90%

See 1 more Smart Citation

A Finnish news corpus for named entity recognition

Ruokolainen

Kauppinen

Silfverberg

et al. 2019

Lang Resources & Evaluation

View full text Add to dashboard Cite

We present a corpus of Finnish news articles with a manually prepared named entity annotation. The corpus consists of 953 articles (193,742 word tokens) with six named entity classes (organization, location, person, product, event, and date). The articles are extracted from the archives of Digitoday, a Finnish online technology news source. The corpus is available for research purposes. We present baseline experiments on the corpus using a rule-based and two deep learning systems on two, in-domain and out-of-domain, test sets.

show abstract

Section: Neural Network Architecturesmentioning

confidence: 90%

“…Finally, Güngör et al (2019) employed the Digitoday corpus as a part of their study on the effect of morphology on named entity recognition. Again, their experiments were run on a version under development.…”

Section: Previous Workmentioning

confidence: 99%

A Finnish news corpus for named entity recognition

Ruokolainen

Kauppinen

Silfverberg

et al. 2019

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…Lample et al (2016) proposed a LSTM-CRF (conditional random fields) model and this has been widely used and extended for the flat NER, e.g., Akbik et al (2018). In recent studies of neural network based flat NER, Gungor et al (2018Gungor et al ( , 2019 have shown that morphological analysis using additional word representations based on linguistic properties of the words, especially for morphologically rich languages such as Turkish and Finnish, improves the NER performances further compared with using only representations based on the surface forms of words.…”

Section: Related Workmentioning

confidence: 99%

A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models

Sohrab

Pham²,

Misawa

et al. 2019

Proceedings of the 5th Workshop on BioNLP Open Shared Tasks

View full text Add to dashboard Cite

We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forwardand backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76% on Sub-task 1 (NER) and the F-score of 79.97% (strict) on Sub-task 2 (CI).

show abstract

“…We demonstrate the method on named entity recognition (NER) task by using a NER tagger trained on Turkish and Finnish both of which are morphologically rich languages [ 7 , 8 ]. The tagger requires all the morphological analyses of each token in the sentence to be provided to the model.…”

Section: Introductionmentioning

confidence: 99%

EXSEQREG: Explaining sequence-based NLP tasks with regions with a case study using morphological features for named entity recognition

2020

Self Cite

View full text Add to dashboard Cite

The state-of-the-art systems for most natural language engineering tasks employ machine learning methods. Despite the improved performances of these systems, there is a lack of established methods for assessing the quality of their predictions. This work introduces a method for explaining the predictions of any sequence-based natural language processing (NLP) task implemented with any model, neural or non-neural. Our method named EXSEQREG introduces the concept of region that links the prediction and features that are potentially important for the model. A region is a list of positions in the input sentence associated with a single prediction. Many NLP tasks are compatible with the proposed explanation method as regions can be formed according to the nature of the task. The method models the prediction probability differences that are induced by careful removal of features used by the model. The output of the method is a list of importance values. Each value signifies the impact of the corresponding feature on the prediction. The proposed method is demonstrated with a neural network based named entity recognition (NER) tagger using Turkish and Finnish datasets. A qualitative analysis of the explanations is presented. The results are validated with a procedure based on the mutual information score of each feature. We show that this method produces reasonable explanations and may be used for i) assessing the degree of the contribution of features regarding a specific prediction of the model, ii) exploring the features that played a significant role for a trained model when analyzed across the corpus.

show abstract

The effect of morphology in named entity recognition with sequence tagging

Cited by 19 publications

References 48 publications

A Finnish news corpus for named entity recognition

A Finnish news corpus for named entity recognition

A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models

EXSEQREG: Explaining sequence-based NLP tasks with regions with a case study using morphological features for named entity recognition

Contact Info

Product

Resources

About