David Ifeoluwa Adelani

David Adelani

Email :

Linkedin : David ADELANI

Google Scholar : David Adelani

Github : dadelani

Twitter : @davlanade

About me

I am a PhD Student at the Spoken Language Systems group and a member of the Saarbrücken Graduate School of Computer Science at the Saarland Informatics Campus . My advisor is Prof. Dr. Dietrich Klakow and I am working on privacy-respecting dialog systems funded by the COMPRISE (Cost-effective, Multilingual, Privacy-driven voice-enabled Services) project.

News

- Our paper " Preventing Author Profiling through Zero-Shot Multilingual Back-Translation (with Miaoran Zhang, Xiaoyu Shen, Ali Davody, Thomas Kleinbauer, and Dietrich Klakow) has been accepted at EMNLP 2021 (Main Conference) (17.09.2021)

- Our paper " The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation (with Dana Ruiter, Jesujoba O. Alabi, Damilola Adebonojo, Adesina Ayeni, Mofe Adeyemi, Ayodele Awokoya, and Cristina España-Bonet) has been accepted at MT Summit (Research Track) (15.06.2021)

- Our paper "MasakhaNER: Named Entity Recognition for African Languages (with Jade Abbott, Graham Neubig, Daniel D'souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jesujoba Alabi, Seid Muhie Yimam, and 40 more authors) has been accepted at the Transactions of the Association for Computational Linguistics (TACL) 2021 (14.06.2021)

- Our paper " MENYO-20k: A Multi-domain English-Yorùbá Corpus for Machine Translation and Domain Adaptation (with Dana Ruiter, Jesujoba O. Alabi, Damilola Adebonojo, Adesina Ayeni, Mofe Adeyemi, Ayodele Awokoya, and Cristina España-Bonet) has been accepted at AfricaNLP workshop at EACL 2021 (04.03.2021)

- Our paper "Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages (with Michael A. Hedderich, Dawei Zhu, Jesujoba O. Alabi, Udia Markus, and Dietrich Klakow) has been accepted at EMNLP 2020 (short paper) (15.09.2020)

- Our paper "Estimating Community Feedback Effect on Topic Choice in Social Media with Predictive Modeling (with Ryota Kobayashi and Ingmar Weber and Przemyslaw A. Grabowicz) has been accepted at EPJ Data Science Journal 2020 (03.08.2020)

- Our paper "Privacy Guarantees for De-identifying Text Transformations (with Ali Davody, Thomas Kleinbauer and Dietrich Klakow) has been accepted at Interspeech 2020 (24.07.2020)

- Our paper "Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks (with Aleena Thomas, Ali Davody, Aditya Mogadala, and Dietrich Klakow) has been accepted at the 23rd International Conference on Text, Speech and Dialogue (TSD 2020) (05.06.2020)

- Our paper "Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá (with Michael A. Hedderich, Dawei Zhu, Esther van den Berg, Dietrich Klakow) has been accepted at the Practical ML for Developing Countries Workshop at ICLR 2020 (02.03.2020)

- Our paper "Improving Yorùbá Diacritic Restoration" (with Iroro Orife, Timi Fasubaa, Victor Williamson, Wuraola Fisayo Oyewusi, Ọlámilékan Wahab, Kọ́lá Túbọ̀sún ) has been accepted at the AfricaNLP Workshop at ICLR 2020 (02.03.2020)

- Our paper "Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training" (with Ernie Chang, Xiaoyu Shen, Vera Demberg) ) has been accepted at the AfricaNLP Workshop at ICLR 2020 (02.03.2020)

- Our paper "Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yorùbá and Twi (with Jesujoba O. Alabi, Kwabena Amponsah-Kaakyire, and Cristina España-Bonet) has been accepted at the 12th International Conference on Language Resources and Evaluation (LREC 2020) (11.02.2020)

- Our paper "Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection (with Haotian Mai, Fuming Fang, Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen) has been accepted at the 34-th International Conference on Advanced Information Networking and Applications (AINA-2020) (22.01.2020)

- Attended PRAIRIE AI summer school @Paris, great experience, thank you PR[AI]RIE! (October 3 - 5, 2019)

- Our First COMPRISE delivarable with partners from INRIA and USAAR: "Baseline speech and text transformation and model learning library is out (30.08.2019)

- Attended Google NLP Summit @Zürich, great experience, thank you Google! (June 24 - 26, 2019)

- Our paper "Demographic Inference and Representative Population Estimates from Multilingual Social Media Data" (with Zijian Wang, Scott Hale, Przemyslaw Grabowicz, Timo Hartmann, Fabian Flöck and David Jurgens) has been accepted at the Web Conference 2019 (21.01.2019)

Research interests

- Natural language processing (NLP)

- Privacy-preserving machine learning

- Differential privacy

- NLP for low resource languages (e.g Yorùbá)

- Neural machine translation and

- Computational social science

Media Coverage

- The languages that defy auto-translate on BBC Future featuring MENYO-20k

Projects

- COMPRISE EU H2020 (Dec 2018 - Nov 2021)

- Lacuna NER/POS (June 2021 - Nov 2021)

- AI4D--African Language Program (July 2020 - Nov 2020)

- MasakhaNER (July 2020 - Jan 2021)

Talks and Podcasts

- Apr 19, 2021 MENYO-20k: A Multi-domain English-Yorùbá Corpus for Machine Translation and Domain Adaptation at the AfricaNLP Workshop @EACL 2021

- Apr 19, 2021 MasakhaNER: Named Entity Recognition for African Languages at the AfricaNLP Workshop @EACL 2021

- Mar 26, 2021 MasakhaNER: Named Entity Recognition for African Languages at the LTI Colloquium in CMU

- Oct 29, 2020 Privacy guarantees for dee identifying text transformation at Interspeech 2020

- Sep 23, 2020 Development of NLP datasets and models for African Languages at NLP with Friends

- Jul 7, 2020 Sentiment Preserving Fake Reviews with Data Skeptic

- Jul 3, 2020 Ensuring good text quality in African Language Datasets at the AI4D Africa Webinar Series: Making NLP work in Africa – with an introduction to the GIZ AI4D African Language Dataset Challenge

- Apr 26, 2020 Improving Yorùbá Diacritic Restoration at the AfricaNLP Workshop @ICLR 2020

- Apr 26, 2020 Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá at the AfricaNLP Workshop @ICLR 2020

More information

I have an MSc in Computer Science from the African University of Science and Technology, Abuja and a BSc in Computer Science from the Federal University of Agriculture, Abeokuta, Nigeria. For more, see my [C.V] .

Favourite Quote: "Anything you find your hands doing, do it with all your might" (since 2006)