Tahmid Hasan

Email: tahmidhasan [at] cse.buet.ac.bd

Links: [Curriculum Vitae] [Google Scholar] [Twitter] [GitHub]

Publications

1. XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
   Tahmid Hasan, Abhik Bhattacharjee, Md. Saiful Islam, Kazi Mubasshir, Yuan-Fang Li, Yong-Bin Kang, M. Sohel Rahman, Rifat Shahriyar
   In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
   [bib] [abstract] [code]

   Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by human and intrinsic evaluation. We fine-tune mT5, a state-of-the-art pretrained multilingual model, with XL-Sum and experiment on multilingual and low-resource summarization tasks. XL-Sum induces competitive results compared to the ones obtained using similar monolingual datasets: we show higher than 11 ROUGE-2 scores on 10 languages we benchmark on, with some of them exceeding 15, as obtained by multilingual training. Additionally, training on low-resource languages individually also provides competitive performance. To the best of our knowledge, XL-Sum is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and the number of languages covered. We are releasing our dataset and models to encourage future research on multilingual abstractive summarization. The resources can be found at https://github.com/csebuetnlp/xl-sum.

                                       @inproceedings{hasan-etal-2021-xl,
                                           title = "{XL}-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages",
                                           author = "Hasan, Tahmid  and
                                               Bhattacharjee, Abhik  and
                                               Islam, Md. Saiful  and
                                               Mubasshir, Kazi  and
                                               Li, Yuan-Fang  and
                                               Kang, Yong-Bin  and
                                               Rahman, M. Sohel  and
                                               Shahriyar, Rifat",
                                           booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
                                           month = aug,
                                           year = "2021",
                                           address = "Online",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2021.findings-acl.413",
                                           doi = "10.18653/v1/2021.findings-acl.413",
                                           pages = "4693--4703",
                                       }
                                   



2. CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs
   Abhik Bhattacharjee*, Tahmid Hasan*, Wasi Uddin Ahmad, Yuan-Fang Li, Yong-Bin Kang, Rifat Shahriyar
   *: Equal contribution
   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
   [bib] [abstract] [code]

   We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatically evaluating model-generated summaries. LaSE is strongly correlated with ROUGE and, unlike ROUGE, can be reliably measured even in the absence of references in the target language. Performance on ROUGE and LaSE indicate that our proposed model consistently outperforms baseline models. To the best of our knowledge, CrossSum is the largest cross-lingual summarization dataset and the first ever that is not centered around English. We are releasing the dataset, training and evaluation scripts, and models to spur future research on cross-lingual summarization. The resources can be found at https://github.com/csebuetnlp/CrossSum.

                                       @inproceedings{bhattacharjee-etal-2023-crosssum,
                                           title = "{C}ross{S}um: Beyond {E}nglish-Centric Cross-Lingual Summarization for 1,500+ Language Pairs",
                                           author = "Bhattacharjee, Abhik  and
                                             Hasan, Tahmid  and
                                             Ahmad, Wasi Uddin  and
                                             Li, Yuan-Fang  and
                                             Kang, Yong-Bin  and
                                             Shahriyar, Rifat",
                                           booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
                                           month = jul,
                                           year = "2023",
                                           address = "Toronto, Canada",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2023.acl-long.143",
                                           pages = "2541--2564",
                                           abstract = "We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatically evaluating model-generated summaries. LaSE is strongly correlated with ROUGE and, unlike ROUGE, can be reliably measured even in the absence of references in the target language. Performance on ROUGE and LaSE indicate that our proposed model consistently outperforms baseline models. To the best of our knowledge, CrossSum is the largest cross-lingual summarization dataset and the first ever that is not centered around English. We are releasing the dataset, training and evaluation scripts, and models to spur future research on cross-lingual summarization. The resources can be found at https://github.com/csebuetnlp/CrossSum",
                                       }
                                   



3. Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation
   Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar
   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
   [bib] [abstract] [code]

   Despite being the seventh most widely spoken language in the world, Bengali has received much less attention in machine translation literature due to being low in resources. Most publicly available parallel corpora for Bengali are not large enough; and have rather poor quality, mostly because of incorrect sentence alignments resulting from erroneous sentence segmentation, and also because of a high volume of noise present in them. In this work, we build a customized sentence segmenter for Bengali and propose two novel methods for parallel corpus creation on low-resource setups: aligner ensembling and batch filtering. With the segmenter and the two methods combined, we compile a high-quality Bengali-English parallel corpus comprising of 2.75 million sentence pairs, more than 2 million of which were not available before. Training on neural models, we achieve an improvement of more than 9 BLEU score over previous approaches to Bengali-English machine translation. We also evaluate on a new test set of 1000 pairs made with extensive quality control. We release the segmenter, parallel corpus, and the evaluation set, thus elevating Bengali from its low-resource status. To the best of our knowledge, this is the first ever large scale study on Bengali-English machine translation. We believe our study will pave the way for future research on Bengali-English machine translation as well as other low-resource languages. Our data and code are available at https://github.com/csebuetnlp/banglanmt.

                                       @inproceedings{hasan-etal-2020-low,
                                           title = "Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for {B}engali-{E}nglish Machine Translation",
                                           author = "Hasan, Tahmid  and
                                             Bhattacharjee, Abhik  and
                                             Samin, Kazi  and
                                             Hasan, Masum  and
                                             Basak, Madhusudan  and
                                             Rahman, M. Sohel  and
                                             Shahriyar, Rifat",
                                           booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
                                           month = nov,
                                           year = "2020",
                                           address = "Online",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2020.emnlp-main.207",
                                           doi = "10.18653/v1/2020.emnlp-main.207",
                                           pages = "2612--2623",                                        
                                       }
                                   



4. BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla
   Abhik Bhattacharjee*, Tahmid Hasan*, Wasi Uddin Ahmad, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Anindya Iqbal, Rifat Shahriyar
   *: Equal contribution
   In Findings of the North American Chapter of the Association for Computational Linguistics: NAACL 2022
   [bib] [abstract] [code]

   In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed'Bangla2B+') by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Benchmark (BLUB). BanglaBERT achieves state-of-the-art results outperforming multilingual and monolingual models. We are making the models, datasets, and a leaderboard publicly available at https://github.com/csebuetnlp/banglabert to advance Bangla NLP .

                                       @inproceedings{bhattacharjee-etal-2022-banglabert,
   					    title = "{B}angla{BERT}: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in {B}angla",
   					    author = "Bhattacharjee, Abhik  and
   					      Hasan, Tahmid  and
   					      Ahmad, Wasi  and
   					      Mubasshir, Kazi Samin  and
   					      Islam, Md Saiful  and
   					      Iqbal, Anindya  and
   					      Rahman, M. Sohel  and
   					      Shahriyar, Rifat",
   					    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
   					    month = jul,
   					    year = "2022",
   					    address = "Seattle, United States",
   					    publisher = "Association for Computational Linguistics",
   					    url = "https://aclanthology.org/2022.findings-naacl.98",
   					    pages = "1318--1327",
   					    abstract = "In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed {`}Bangla2B+{'}) by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Benchmark (BLUB). BanglaBERT achieves state-of-the-art results outperforming multilingual and monolingual models. We are making the models, datasets, and a leaderboard publicly available at \url{https://github.com/csebuetnlp/banglabert} to advance Bangla NLP.",
   					}
                                   



5. BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
   Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Rifat Shahriyar
   In Findings of the Association for Computational Linguistics: EACL 2023
   [bib] [abstract] [code]

   This work presents ‘BanglaNLG,’ a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language. We aggregate six challenging conditional text generation tasks under the BanglaNLG benchmark, introducing a new dataset on dialogue generation in the process. Furthermore, using a clean corpus of 27.5 GB of Bangla data, we pretrain ‘BanglaT5’, a sequence-to-sequence Transformer language model for Bangla. BanglaT5 achieves state-of-the-art performance in all of these tasks, outperforming several multilingual models by up to 9% absolute gain and 32% relative gain. We are making the new dialogue dataset and the BanglaT5 model publicly available at https://github.com/csebuetnlp/BanglaNLG in the hope of advancing future research on Bangla NLG.

                                       @inproceedings{bhattacharjee-etal-2023-banglanlg,
                                           title = "{B}angla{NLG} and {B}angla{T}5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in {B}angla",
                                           author = "Bhattacharjee, Abhik  and
                                             Hasan, Tahmid  and
                                             Ahmad, Wasi Uddin  and
                                             Shahriyar, Rifat",
                                           booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
                                           month = may,
                                           year = "2023",
                                           address = "Dubrovnik, Croatia",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2023.findings-eacl.54",
                                           pages = "726--735",
                                           abstract = "This work presents {`}BanglaNLG,{'} a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language. We aggregate six challenging conditional text generation tasks under the BanglaNLG benchmark, introducing a new dataset on dialogue generation in the process. Furthermore, using a clean corpus of 27.5 GB of Bangla data, we pretrain {`}BanglaT5{'}, a sequence-to-sequence Transformer language model for Bangla. BanglaT5 achieves state-of-the-art performance in all of these tasks, outperforming several multilingual models by up to 9{\%} absolute gain and 32{\%} relative gain. We are making the new dialogue dataset and the BanglaT5 model publicly available at https://github.com/csebuetnlp/BanglaNLG in the hope of advancing future research on Bangla NLG.",
                                       }
                                   



6. Contrastive Learning for API Aspect Analysis
   GM Shahariar, Tahmid Hasan, Anindya Iqbal, Gias Uddin
   In Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)
   [bib] [abstract] [code]

   We present a novel approach - CLAA - for API aspect detection in API reviews that utilizes transformer models trained with a supervised contrastive loss objective function. We evaluate CLAA using performance and impact analysis. For performance analysis, we utilized a benchmark dataset on developer discussions collected from Stack Overflow and compare the results to those obtained using state-of-the-art transformer models. Our experiments show that contrastive learning can significantly improve the performance of transformer models in detecting aspects such as Performance, Security, Usability, and Documentation. For impact analysis, we performed empirical and developer study. On a randomly selected and manually labeled 200 online reviews, CLAA achieved 92% accuracy while the SOTA baseline achieved 81.5%. According to our developer study involving 10 participants, the use of 'Stack Overflow + CLAA' resulted in increased accuracy and confidence during API selection. Replication package: https://github.com/shahariar-shibli/Contrastive-Learning-for-API-Aspect-Analysis.

                                       @inproceedings{Shahariar-etal-2023-contrastive,
                                           title = "{C}ontrastive {L}earning for {A}PI {A}spect Analysis",
                                           author = "Shahariar, GM  and
                                             Hasan, Tahmid  and
                                             Iqbal, Anindya  and
                                             Uddin, Gias",
                                           booktitle = "Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)",
                                           month = september,
                                           year = "2023",
                                           address = "Kirchberg, Luxembourg",
                                           publisher = "IEEE/ACM",
                                           url = "https://conf.researchr.org/home/ase-2023",
                                       }
                                   



7. CoDesc: A Large Code–Description Parallel Dataset
   Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq, Kazi Sajeed Mehrab, Md. Mahim Anjum Haque, Tahmid Hasan, Wasi Ahmad, Anindya Iqbal, Rifat Shahriyar
   In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
   [bib] [abstract] [code]

   Translation between natural language and source code can help software development by enabling developers to comprehend, ideate, search, and write computer programs in natural language. Despite growing interest from the industry and the research community, this task is often difficult due to the lack of large standard datasets suitable for training deep neural models, standard noise removal methods, and evaluation benchmarks. This leaves researchers to collect new small-scale datasets, resulting in inconsistencies across published works. In this study, we present CoDesc -- a large parallel dataset composed of 4.2 million Java methods and natural language descriptions. With extensive analysis, we identify and remove prevailing noise patterns from the dataset. We demonstrate the proficiency of CoDesc in two complementary tasks for code-description pairs: code summarization and code search. We show that the dataset helps improve code search by up to 22\% and achieves the new state-of-the-art in code summarization. Furthermore, we show CoDesc's effectiveness in pre-training--fine-tuning setup, opening possibilities in building pretrained language models for Java. To facilitate future research, we release the dataset, a data processing tool, and a benchmark at https://github.com/csebuetnlp/CoDesc.

                                       @inproceedings{hasan-etal-2021-codesc,
                                           title = "{C}o{D}esc: A Large Code{--}Description Parallel Dataset",
                                           author = "Hasan, Masum  and
                                             Muttaqueen, Tanveer  and
                                             Ishtiaq, Abdullah Al  and
                                             Mehrab, Kazi Sajeed  and
                                             Haque, Md. Mahim Anjum  and
                                             Hasan, Tahmid  and
                                             Ahmad, Wasi  and
                                             Iqbal, Anindya  and
                                             Shahriyar, Rifat",
                                           booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
                                           month = aug,
                                           year = "2021",
                                           address = "Online",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2021.findings-acl.18",
                                           doi = "10.18653/v1/2021.findings-acl.18",
                                           pages = "210--218",
                                       }
                                   



8. GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
   Sebastian Gehrmann, ... Tahmid Hasan, ...
   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
   [bib] [abstract] [code]

   Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances.We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other’s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.

                                       @inproceedings{gehrmann-etal-2022-gemv2,
                                           title = "{GEM}v2: Multilingual {NLG} Benchmarking in a Single Line of Code",
                                           author = "Gehrmann, Sebastian  and
                                             Bhattacharjee, Abhik  and
                                             Mahendiran, Abinaya  and
                                             Wang, Alex  and
                                             Papangelis, Alexandros  and
                                             Madaan, Aman  and
                                             Mcmillan-major, Angelina  and
                                             Shvets, Anna  and
                                             Upadhyay, Ashish  and
                                             Bohnet, Bernd",
                                           booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
                                           month = dec,
                                           year = "2022",
                                           address = "Abu Dhabi, UAE",
                                           publisher = "Association for Computational Linguistics",
                                           url = "https://aclanthology.org/2022.emnlp-demos.27",
                                           pages = "266--281",
                                           abstract = "Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances.We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other{'}s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.",
                                       }
                                   



9. Using Adaptive Heartbeat Rate on Long-Lived TCP Connections
   M. Saifur Rahman, Md. Yusuf Sarwar Uddin, Tahmid Hasan, M. Sohel Rahman, M. Kaykobad
   In IEEE/ACM Transactions on Networking (Volume: 26, Issue: 1, Feb. 2018)
   [bib] [abstract] [code]

   In this paper, we propose techniques for dynamically adjusting heartbeat or keep-alive interval of long-lived TCP connections, particularly the ones that are used in push notification service in mobile platforms. When a device connects to a server using TCP, often times the connection is established through some sort of middle-box, such as NAT, proxy, firewall, and so on. When such a connection is idle for a long time, it may get torn down due to binding timeout of the middle-box. To keep the connection alive, the client device needs to send keep-alive packets through the connection when it is otherwise idle. To reduce resource consumption, the keep-alive packet should preferably be sent at the farthest possible time within the binding timeout. Due to varied settings of different network equipments, the binding timeout will not be identical in different networks. Hence, the heartbeat rate used in different networks should be changed dynamically. We propose a set of iterative probing techniques, namely binary, exponential, and composite search, that detect the middle-box binding timeout with varying degree of accuracy; and in the process, keeps improving the keep-alive interval used by the client device. We also analytically derive performance bounds of these techniques. To the best of our knowledge, ours is the first work that systematically studies several techniques to dynamically improve keep-alive interval. To this end, we run experiments in simulation as well as make a real implementation on android to demonstrate the proof-of-concept of the proposed schemes.

                                       @article{rahman2017using,
                                           title={Using adaptive heartbeat rate on long-lived TCP connections},
                                           author={Rahman, M Saifur and Uddin, Md Yusuf Sarwar and Hasan, Tahmid and Rahman, M Sohel and Kaykobad, M},
                                           journal={IEEE/ACM Transactions on Networking},
                                           volume={26},
                                           number={1},
                                           pages={203--216},
                                           year={2017},
                                           publisher={IEEE}
                                         }
                                   

Pre-prints:

1. BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?
   Abdullah Al Ishtiaq, Masum Hasan, Md. Mahim Anjum Haque, Kazi Sajeed Mehrab, Tanveer Muttaqueen, Tahmid Hasan, Anindya Iqbal, Rifat Shahriyar
   ArXiv Pre-print, 2021
   [bib] [abstract]

   Millions of repetitive code snippets are submitted to code repositories every day. To search from these large codebases using simple natural language queries would allow programmers to ideate, prototype, and develop easier and faster. Although the existing methods have shown good performance in searching codes when the natural language description contains keywords from the code, they are still far behind in searching codes based on the semantic meaning of the natural language query and semantic structure of the code. In recent years, both natural language and programming language research communities have created techniques to embed them in vector spaces. In this work, we leverage the efficacy of these embedding models using a simple, lightweight 2-layer neural network in the task of semantic code search. We show that our model learns the inherent relationship between the embedding spaces and further probes into the scope of improvement by empirically analyzing the embedding methods. In this analysis, we show that the quality of the code embedding model is the bottleneck for our model's performance, and discuss future directions of study in this area.

                                       @article{ishtiaq2021bert2code,
                                           title={BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?},
                                           author={Ishtiaq, Abdullah Al and Hasan, Masum and Haque, Md and Anjum, Mahim and Mehrab, Kazi Sajeed and Muttaqueen, Tanveer and Hasan, Tahmid and Iqbal, Anindya and Shahriyar, Rifat},
                                           journal={arXiv preprint arXiv:2104.08017},
                                           year={2021}
                                       }
                                   

Ongoing Projects

1. Aligning Large Language Models with Human Values [statement]

   The rapid advancement of large language models, such as OpenAI's GPT-3, has raised concerns about their potential to generate biased or harmful outputs. Ensuring that these models align with human values is crucial for their responsible deployment in various domains. This research aims to investigate and develop techniques for aligning large language models with human values. The BUET CSE NLP Group is actively engaged in pretraining billion-scale GPT and T5 models in Bangla, which are serving as primary testbeds for our proposed research. The project is exploring directions such as instruction fine-tuning and reinforcement learning with human feedback to enhance the model's alignment with specific human values in the Bangla language context. Additionally, the project is focusing on developing interpretability frameworks to shed light on the decision-making processes of these models, enabling better understanding and control over their output. Additionally, we are also exploring ideas from game theory, cognitive science, and behavioral economics to design objective/reward functions aligned with human rationales.

   
   Supervisor: Prof. Rifat Shahriyar
   
   
2. Retrieval-Augmented Large Language Models [statement]

   This research is focusing on exploring the potential of retrieval-augmented large language models, aiming to enhance their performance in natural language understanding and generation tasks. Retrieval-based methods have shown promising results in improving the quality and relevance of generated responses in conversational AI systems. This project proposes to investigate techniques that combine the strengths of large language models with effective retrieval mechanisms to generate more contextually relevant and coherent responses. The research involves designing and training retrieval models that can efficiently retrieve relevant information from large knowledge bases or corpora to support the language model's generation process. Furthermore, the project exploring methods for fine-tuning large language models using retrieval-based objectives, enabling it to leverage retrieved information for more accurate and informed responses. Potential applications include open-domain and/or cross-lingual question answering.

   
   Supervisor: Prof. Rifat Shahriyar
   
   
3. Vision-Enhanced Large Language Models [statement]

   This research aims to investigate the integration of vision in large language models to enhance their capabilities in visual understanding and generation tasks. While large language models have achieved remarkable success in natural language processing, they often lack the ability to comprehend and generate content related to visual information. This project proposes to explore techniques that combine the power of large language models with computer vision methodologies, enabling the models to understand and generate text based on visual input. The research involves designing and training models that can effectively process and analyze images, extracting meaningful visual features to enrich the language model's understanding. Furthermore, the project explores methods for fine-tuning the language model using visual-based objectives, allowing it to generate text that is coherent and aligned with the visual content. The proposal has potential applications in areas such as visual question answering and multimodal summarization.

   
   Supervisor: Prof. Rifat Shahriyar
   
   

Education

• (June 2019 - May 2022) Master of Science in Computer Science and Engineering
  Department of Computer Science and Engineering
  Bangladesh University of Engineering and Technology (BUET)
  Supervisor: Prof. Rifat Shahriyar
  CGPA: 3.92/4.00
  
  
• (February 2015 - April 2019) Bachelor of Science in Computer Science and Engineering
  Department of Computer Science and Engineering
  Bangladesh University of Engineering and Technology (BUET)
  CGPA: 3.98/4.00
  Thesis Supervisor: Prof. M. Sohel Rahman
  

Professional Experience

• (July 2022 - Present) Assistant Professor
  Department of Computer Science and Engineering
  Bangladesh University of Engineering and Technology (BUET)
  
  
• (October 2019 - July 2022) Lecturer
  Department of Computer Science and Engineering
  Bangladesh University of Engineering and Technology (BUET)
  
  
• (June 2022 - Present) Research Affiliate
  BUET CSE NLP Group
  Supervisor: Prof. Rifat Shahriyar
  
  
• (June 2019 - May 2022) Graduate Research Assistant
  Department of Computer Science and Engineering
  Bangladesh University of Engineering and Technology (BUET)
  Supervisor: Prof. Rifat Shahriyar
  

Honors & Awards

• (2019 - 2022) University Merit Scholarships in each semester for excellent postgraduate results
  
• (2015 - 2019) Dean's Award in each academic year for excellent undergraduate results
  
• (2015 - 2019) University Merit Scholarships in each semester for excellent undergraduate results
  

Teaching Experience

• (January 2023) Course Instructor @ Mathematical Analysis for Computer Science (CSE 301)
• (January 2023) Course Instructor @ Information System Design Sessional (CSE 326)
• (January 2023) Course Instructor @ Software Development Sessional (CSE 408)
• (July 2022) Course Instructor @ Mathematical Analysis for Computer Science (CSE 301)
• (July 2022) Course Instructor @ Numerical Methods Sessional (CSE 218)
• (July 2022) Course Instructor @ Operating Systems Sessional (CSE 314)
• (January 2022) Course Instructor @ Computer Architecture (CSE 305)
• (January 2022) Course Instructor @ Computer Architecture Sessional (CSE 306)
• (January 2022) Course Instructor @ Software Development (CSE 408)
• (January 2022) Course Instructor @ Object Oriented Programming Language Sessional (CSE 108)
• (July 2021) Course Instructor @ Machine Learning (CSE 471)
• (July 2021) Course Instructor @ Data Structures and Algorithms I Sessional (CSE 204)
• (July 2021) Course Instructor @ Database Sessional (CSE 216)
• (July 2021) Course Instructor @ Numerical Methods Sessional (CSE 218)
• (July 2021) Course Instructor @ Machine Learning Sessional (CSE 472)
• (January 2021) Course Instructor @ Object Oriented Programming Language Sessional (CSE 108)
• (January 2021) Course Instructor @ Digital Logic Design Sessional (CSE 206)
• (January 2021) Course Instructor @ Software Engineering Sessional (CSE 308)
• (January 2021) Course Instructor @ Microprocessors, Microcontrollers, and Embedded Systems Sessional (CSE 316)
• (January 2020) Course Instructor @ Data Structures and Algorithms II Sessional (CSE 208)
• (January 2020) Course Instructor @ Computer Networks Sessional (CSE 322)
• (January 2020) Course Instructor @ Simulation and Modeling Sessional (CSE 412)
• (January 2020) Course Instructor @ Algorithm Engineering Sessional (CSE 462)
• (January 2020) Course Instructor @ Machine Learning Sessional (CSE 472)
• (July 2019) Course Instructor @ Data Structures and Algorithms I Sessional (CSE 204)
• (July 2019) Course Instructor @ Numerical Methods (CSE 218)
• (July 2019) Course Instructor @ Computer Programming Techniques Sessional (CSE 296)
• (July 2019) Course Instructor @ Software Development (CSE 408)