Papers by Masum Hasan
CoDesc: A Large Code–Description Parallel Dataset (2021.findings-acl)
Copied to clipboard
Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq, Kazi Sajeed Mehrab, Md. Mahim Anjum Haque, Tahmid Hasan, Wasi Ahmad, Anindya Iqbal, Rifat Shahriyar
| Challenge: | Existing models for natural language and programming languages are lagging behind due to a lack of large datasets and benchmarks. |
| Approach: | They present a large parallel dataset of Java methods and natural language descriptions that is used to train deep neural models. |
| Outcome: | The proposed dataset improves code summarization and code search by 22% and opens up possibilities for pretrained language models for Java. |
Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate Video (2021.emnlp-main)
Copied to clipboard
| Challenge: | Current literature mostly considers textual content while assessing argument quality, and it is limited to datasets containing short text sequences (18-48 words). |
| Approach: | They propose a set of interpretable debate centric features that are inspired by theories of argument quality and propose MARQ model that summarizes the multimodal signals on long debate videos. |
| Outcome: | The proposed model outperforms baseline models with an error rate reduction of 22.7% on the argument quality prediction task and achieves 81.91% accuracy. |
Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation (2020.emnlp-main)
Copied to clipboard
Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar
| Challenge: | despite being the seventh most widely spoken language, Bengali has received little attention in machine translation due to being low in resources. |
| Approach: | They propose a customized sentence segmenter for Bengali and two new methods for parallel corpus creation on low-resource setups. |
| Outcome: | The proposed method improves Bengali-English parallel corpus by 9 BLEU over previous approaches . the results will pave the way for future research on Bengali and other low-resource languages . |