NaCTeM

AIRC Collaboration

Introduction

Prof. Sophia Ananiadou, director of NaCTeM and Prof. Angelo Cangelosi's Cognitive Robotics Lab at Manchester are collaborating with the Artificial Intelligence Research Center (AIRC), in Tokyo, Japan, to carry out fundamental NLP and text mining research. AIRC is directed by Prof. Jun'ichi Tsujii, who also holds the position of Professor of Text Mining at the University of Manchester, and is NaCTeM's scientific advisor. This research was also linked with Prof. Sophia Ananiadou's Alan Turing fellowship. AIRC is exploring possible directions of NLP/machine learning research with ATI fellows, and funding was allocated to facilitate this exploration.

Aims and Objectives

The strands of work that are being indertaken as part of this project include the following:

Deep-Learning Based Natural Language Processing

The aim of this work is to build practical deep learning-based methods for various natural language processing tasks, including document clustering, named entity recognition, coreference resolution and relation extraction, along with annotated corpora that can aid in their development. Work on entity detection has tackled important issues such as specific handling of nested entities (entities embedded in other entities) and polysemous entities (entities annotated with multiple semantic types), as well as splitting words into sub-words to better handle rare and unknown words. Novel relation extraction work has investigated different approaches that can recognise both intra-sentence and inter-sentence relations.

Robotics Research

Joint research between AIST-AIRC and Prof. Cangelosi's Cognitive Robotics Lab at Manchester concerns the field of cognitive robotics and human-robot interaction. One area investigates the use of deep learning models for language and non-verbal communication in joint object manipulation tasks with humanoid robots (In collaboration with Tetsuya Ogata). The second area looks at novel experiments on machine learning approaches to dialog and human-robot interaction in the context of social robots for older people (with Kristiina Jokinen).

Publications

Natural Language Processing

Tran, T. T., Miwa, M. and Ananiadou, S. (2020). Syntactically-Informed Word Representations from Graph Neural Network. Neurocomputing

Trieu, H-L., Tran, T. T., Duong, K. N. A., Nguyen, A., Miwa, M. and Ananiadou, S. (2020). DeepEventMine: End-to-end Neural Nested Event Extraction from Biomedical Texts. Bioinformatics, btaa540

Christopoulou, F., Miwa, M. and Ananiadou, S. (2019). Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs. Proceedings of EMNLP 2019, pp. 4927-4938

Espinosa, K., Miwa, M. and Ananiadou, S. (In Press). Search-based Neural Model for Biomedical Nested and Overlapping Event Detection. Proceedings of EMNLP 2019, pp. 3670-3677

Christopoulou, F., Tran, T. T., Sahu, S. K., Miwa, M. and Ananiadou, S. (2019). Adverse Drug Events and Medication Relation Extraction in EHRs with Ensemble Deep Learning Methods, Journal of the American Medical Informatics Association, ocz101

Sahu, S. K., Christopoulou, F., Miwa, M. and Ananiadou, S. (2019). Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network. Proceedings of ACL 2019, pp. 4309-4316

Ju., M., Nguyen, N. T. H., Miwa, M. and Ananiadou, S. (2019). An Ensemble of Neural Models for Nested Adverse Drug Events and Medication Extraction with Subwords. Journal of the American Medical Informatics Association, ocz075.

Thompson, P., Daikou, S., Ueno, K., Batista-Navarro, R., Tsujii, J. and Ananiadou, S.. (2018). Annotation and Detection of Drug Effects in Text for Pharmacovigilance. Journal of Cheminformatics, 10:37

Ju., M., Miwa, M. and Ananiadou, S. (2018). A Neural Layered Model for Nested Named Entity Recognition. Proceedings of NAACL 2018, pp. 1446-1459.

Christopoulou, F., Miwa, M. and Ananiadou, S. (2018). A Walk-based Model on Entity Graphs for Relation Extraction. Proceedings of ACL 2018, pp. 81-88

Trieu, H-L., Nguyen, N. T. H., Miwa, M. and Ananiadou, S. (2018). Investigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts. Proceedings of the BioNLP 2018 workshop, pp. 183-188.

Sato, M., Brockmeier, A. J., Kontonatsios, G., Mu, T., Goulermas, J. Y, Tsujii, J. and Ananiadou, S. (2017). Distributed Document and Phrase Co-embeddings for Descriptive Clustering. Proceedings of EACL, pp. 991-1001

Robotics

Antunes A., Laflaquière A., Ogata T., Cangelosi A. (In Press). A bi-directional multiple timescales LSTM model for grounding of actions and verbs. Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau.

Luperto M., Romeo M., Lunardini F., Basilico N., Abbate C., Jones R., Cangelosi A., Ferrante S., Borghese N.A., (In Press). Evaluating the acceptability of assistive robots for early detection of mild cognitive impairment. Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau

Romeo M., Hernandez D., Jones R., Cangelosi A (In Press). Deploying a deep learning agent for HRI with potential "end-users" at multiple sheltered housing sites. Proceedings of the 7th International Conference on Human-Agent Interaction, Kyoto, October

Thabet M., Patacchiola M., Cangelosi A. (In Press). Sample-efficient deep reinforcement learning with imaginary rollouts for human-robot interaction. Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau

Zhong J., Han T., Lotfi A., Cangelosi A., Liu X. (In Press). Bridging the gap between robotic applications and computational intelligence in domestic robotics. Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, IEEE Press

Zhong J., Ogata T., Cangelosi A., Yang C. (In press). The emerge of disentanglement in the conceptual space during sensorimotor interaction. IET Cognitive Computation and Systems