Mohammad Golam Sohrab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mohammad Golam Sohrab has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Makoto Miwa
Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan
4 shared publications- Makoto Miwa
Toyota Technological Institute
3 shared publications - Hiroya Takamura
National Institute of Advanced Industrial Science and Technology
2 shared publications - Toru Nakata
National Institute of Advanced Industrial Science and Technology (AIST)
2 shared publications Yutaka Sasaki
2 shared publicationsFuji Ren
Faculty of Engineering, University of Tokushima, 2-1 Minami Josanjima, Tokushima 770-8506, Japan
1 shared publication
Latest Publications
- 22 August 2024
- Published by Springer Nature
- p. 157-173
KAT5: Knowledge-Aware Transfer Learning with a Text-to-Text Transfer Transformer
- 22 August 2024
- Published by Springer Nature
- p. 157-173
KAT5: Knowledge-Aware Transfer Learning with a Text-to-Text Transfer Transformer
- Open Access
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 23-33
BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints
We introduce BERT-NAR-BERT (BnB) – a pre-trained non-autoregressive sequence-to-sequence model, which employs BERT as the backbone for the encoder and decoder for natural language understanding and generation tasks. During the pre-training and fine-tuning with BERT-NAR-BERT, two challenging aspects are considered by adopting the length classification and connectionist temporal classification models to control the output length of BnB. We evaluate it using a standard natural language understanding benchmark GLUE and three generation tasks – abstractive summarization, question generation, and machine translation. Our results show substantial improvements in inference speed (on average 10x faster) with only little deficiency in output quality when compared to our direct autoregressive baseline BERT2BERT model. We plan to release our code on GitHub with the final version of this paper.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 23-33
Open AccessBERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints
We introduce BERT-NAR-BERT (BnB) – a pre-trained non-autoregressive sequence-to-sequence model, which employs BERT as the backbone for the encoder and decoder for natural language understanding and generation tasks. During the pre-training and fine-tuning with BERT-NAR-BERT, two challenging aspects are considered by adopting the length classification and connectionist temporal classification models to control the output length of BnB. We evaluate it using a standard natural language understanding benchmark GLUE and three generation tasks – abstractive summarization, question generation, and machine translation. Our results show substantial improvements in inference speed (on average 10x faster) with only little deficiency in output quality when compared to our direct autoregressive baseline BERT2BERT model. We plan to release our code on GitHub with the final version of this paper.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 549-557
Disease Network Constructor: a Pathway Extraction and Visualization
Mohammad Golam Sohrab, Khoa Duong, Goran Topić, Masami Ikeda, Nozomi Nagano, Yayoi Natsume-Kitatani, Masakata Kuroda, Mari Itoh, Hiroya Takamura. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 549-557
Open AccessDisease Network Constructor: a Pathway Extraction and Visualization
Mohammad Golam Sohrab, Khoa Duong, Goran Topić, Masami Ikeda, Nozomi Nagano, Yayoi Natsume-Kitatani, Masakata Kuroda, Mari Itoh, Hiroya Takamura. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2023.
- Open Access
- 17 March 2020
- Published by Springer Nature in Beni-Suef University Journal of Basic and Applied Sciences
- Vol. 9 (1) , 1-12
Customer gender prediction system on hierarchical E-commerce data
- 17 March 2020
- Published by Springer Nature in Beni-Suef University Journal of Basic and Applied Sciences
- Vol. 9 (1) , 1-12
Open AccessCustomer gender prediction system on hierarchical E-commerce data
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 47-55
A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models
Mohammad Golam Sohrab, Minh Thang Pham, Makoto Miwa, Hiroya Takamura. Proceedings of The 5th Workshop on BioNLP Open Shared Tasks. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 47-55
Open AccessA Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models
Mohammad Golam Sohrab, Minh Thang Pham, Makoto Miwa, Hiroya Takamura. Proceedings of The 5th Workshop on BioNLP Open Shared Tasks. 2019.
- Open Access
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
Deep Exhaustive Model for Nested Named Entity Recognition
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
Open AccessDeep Exhaustive Model for Nested Named Entity Recognition
- 1 January 2018
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 21 (4) , 569-579
EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning
EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning
- 1 January 2018
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 21 (4) , 569-579
EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning
EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning
- 20 June 2017
- Published by Springer Nature
- p. 221-229
Detection of Typical Progress Patterns of Industrial Incidents by Text Mining Technique
- 20 June 2017
- Published by Springer Nature
- p. 221-229
Detection of Typical Progress Patterns of Industrial Incidents by Text Mining Technique
- 17 April 2015
- Published by Springer Nature
- p. 289-300
Centroid-Means-Embedding: An Approach to Infusing Word Embeddings into Features for Text Classification
- 17 April 2015
- Published by Springer Nature
- p. 289-300
Centroid-Means-Embedding: An Approach to Infusing Word Embeddings into Features for Text Classification