Aykut Koc Lab is a research group at Bilkent University focusing on machine
learning and signal processing that extend into natural language
processing (NLP) and graph signal processing (GSP).
Aykut Koc Lab has published the first legal domain-specific NER study in Turkish in the paper “Named Entity Recognition in Turkish Legal Texts“ at Natural Language Engineering journal of Cambridge University Press. This work presents 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.
Our group’s undergraduate member Mustafa Bozdağ will be continuing his graduate studies at Northeastern University starting from the next academic year. We wish him good luck and success…
Our group’s undergraduate member Enes Burak Bilgin will be continuing his graduate studies at the University of Southern California (USC) starting from the next academic year. We wish him good luck and success…
Our group’s undergraduate member Bünyamin Kartal will be continuing his graduate studies at the Massachusetts Institute of Technology (MIT) starting from the next academic year. We wish him good luck and success…
Aykut Koc Lab has published the first study on detecting and eliminating gender, race and other societal bias issues present in word embeddings for the case of legal domain in the paper “Gender Bias in Legal Corpora and Debiasing It” at Natural Language Engineering journal of Cambridge University Press. This work brings the important bias issues to the attention of computational law community, where the importance of law for society has doubled the need for studying bias.
In collaboration with the Center for Information and Language Processing (CIS) of Ludwig Maximilian University of Munich (LMU), Icon Lab (Bilkent) and ASELSAN Research Center, Aykut Koc Lab has published “Learning Interpretable Word Embeddings via Bidirectional Alignment of Dimensions with Semantic Concepts” in Information Processing and Management journal. The paper proposes the bidirectional imparting (BiImp) method which aligns both positive and negative dimension of the word embeddings with concepts in order to have more interpretable word embeddings. BiImp is also shown to be applied to mitigating gender bias in word embeddings.
In the paper “Semantic Change Detection with Gaussian Word Embeddings” published at IEEE Transactions on Audio, Speech and Language Processing, Aykut Koc Lab has developed the first Gaussian word embedding (w2g)-based approach to the problem of lexical semantic change detection. The proposed method reached high rankings (including the first rank at one of the two sub-tasks) at the SemEval 2020 Task 1, which is the standardized evaluation framework of the field.
Aykut Koc Lab has published a pioneering paper on Natural Language Processing (NLP) in law with a specific emphasis on the Turkish legal system. The paper entitled “Natural Language Processing in Law: Prediction of outcomes in the Higher Courts of Turkey” has been published at Information Processing and Management and addresses the Turkish Legal System in a comprehensive manner and develops NLP techniques for the legal system of the Republic of Turkey.
Aykut Koc Lab’s new paper entitled “Graph Signal Processing: Vertex Multiplication” has been published at IEEE Signal Processing Letters, where we made a fundamental contribution to graph signal processing (GSP) by introducing an important and fundamental GSP operator.
We and our collaborators have published the paper entitled “Optimal fractional Fourier filtering for graph signals” at IEEE Transactions on Signal Processing, where we studied Wiener filtering in the graph signal processing (GSP) domain.
Our new paper “Zipfian regularities in non-point word representations”, where we revealed a new Zipfian regularity for semantic breadth, has been published at Information Processing & Management. Code and more details are available at our Github repository.