Joint Learning of Named Entity Recognition and Dependency Parsing using Separate Datasets

Akdemir, Arda; Güngör, Tunga

doi:10.13053/cys-23-3-3247

Cited by 5 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conventional model requires a single dataset annotated with labels for both tasks, which is a delimiting constraint for less resourced languages. Instead, we proposed using separate datasets for each task (Akdemir and Güngör, 2019b) which allows the model to be trained on a larger dataset.…”

Section: Discussionmentioning

confidence: 99%

“…Specifically, we will apply this method to leverage our previously proposed joint learner for Dependency Parsing and Named Entity Recognition. Part-of-speech tags strongly correlate with named entities and dependencies (Hashimoto et al, 2017;Akdemir and Güngör, 2019b). Thus, we argue that learning joint label embeddings of these tasks can help to further capture the relations between them.…”

Section: Research Planmentioning

confidence: 93%

See 1 more Smart Citation

Research on Task Discovery for Transfer Learning in Deep Neural Networks

Akdemir

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Self Cite

View full text Add to dashboard Cite

Deep neural network based machine learning models are shown to perform poorly on unseen or out-of-domain examples by numerous recent studies. Transfer learning aims to avoid overfitting and to improve generalizability by leveraging the information obtained from multiple tasks. Yet, the benefits of transfer learning depend largely on task selection and finding the right method of sharing. In this thesis, we hypothesize that current deep neural network based transfer learning models do not achieve their fullest potential for various tasks and there are still many task combinations that will benefit from transfer learning that are not considered by the current models. To this end, we started our research by implementing a novel multi-task learner with relaxed annotated data requirements and obtained a performance improvement on two NLP tasks. We will further devise models to tackle tasks from multiple areas of machine learning, such as Bioinformatics and Computer Vision, in addition to NLP.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Research Planmentioning

confidence: 93%

Research on Task Discovery for Transfer Learning in Deep Neural Networks

Akdemir

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, this work also encapsulates the most recent NER results for four different morphologically rich languages, which are Czech (81.05% F1), Hungarian (96.11% F1), Finnish (84.34% F1), and Spanish (86.95% F1). Concurrently, Akdemir (2018) combined the same input configuration with joint learning of dependency parsing and NER, which was initially described by Finkel and Manning (2009). This model reached up to a 90.9% F1 score.…”

Section: Ner Models Developed For Turkishmentioning

confidence: 99%

“…As Yeniterzi, Tür, and Oflazer (2018) wrapped up, the first adaptations of Turkish NER were again mainly consisting of handcrafted rules (Küçük and Yazıcı 2009;Dalklç, Gelişli, and Diri 2010) and statistical models (Hakkani-Tür, Oflazer, and Tür 2002;Tür, Hakkani-Tür, and Oflazer 2003). Later, machine learning approaches dominated contemporary applications with conditional random fields (CRFs) (Yeniterzi 2011;Şeker and Eryigit 2012;Küçük and Steinberger 2014) and neural network-based models (Demir and özgür 2014;Akdemir 2018;Güngör et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Named-entity recognition in Turkish legal texts

2022

View full text Add to dashboard Cite

Natural language processing (NLP) technologies and applications in legal text processing are gaining momentum. Being one of the most prominent tasks in NLP, named-entity recognition (NER) can substantiate a great convenience for NLP in law due to the variety of named entities in the legal domain and their accentuated importance in legal documents. However, domain-specific NER models in the legal domain are not well studied. We present a NER model for Turkish legal texts with a custom-made corpus as well as several NER architectures based on conditional random fields and bidirectional long-short-term memories (BiLSTMs) to address the task. We also study several combinations of different word embeddings consisting of GloVe, Morph2Vec, and neural network-based character feature extraction techniques either with BiLSTM or convolutional neural networks. We report 92.27% F1 score with a hybrid word representation of GloVe and Morph2Vec with character-level features extracted with BiLSTM. Being an agglutinative language, the morphological structure of Turkish is also considered. To the best of our knowledge, our work is the first legal domain-specific NER study in Turkish and also the first study for an agglutinative language in the legal domain. Thus, our work can also have implications beyond the Turkish language.

show abstract

“…For this reason, studies are carried out to collect dedicated data for social media texts (Okur et al, 2016). The most recent studies in Turkish NER field utilize Transformers and BERT based models (Yıldırım, 2019;Akdemir and Güngör, 2019;Aras et al, 2021).…”

Section: Introductionmentioning

confidence: 99%