Search

Your search keyword '"Pavlova A. A."' showing total 37,085 results
Start Over Author "Pavlova A. A."

Refine your results

more »

more »

more »

more »

more »

more »

more »
37,085 results on '"Pavlova A. A."'

1. Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust

Author

Pavlova, Vera and Makhlouf, Mohammed

Subjects
Computer Science - Computation and Language
Abstract

The widespread use of large language models (LLMs) has dramatically improved many applications of Natural Language Processing (NLP), including Information Retrieval (IR). However, domains that are not driven by commercial interest often lag behind in benefiting from AI-powered solutions. One such area is religious and heritage corpora. Alongside similar domains, Islamic literature holds significant cultural value and is regularly utilized by scholars and the general public. Navigating this extensive amount of text is challenging, and there is currently no unified resource that allows for easy searching of this data using advanced AI tools. This work focuses on the development of a multilingual non-profit IR system for the Islamic domain. This process brings a few major challenges, such as preparing multilingual domain-specific corpora when data is limited in certain languages, deploying a model on resource-constrained devices, and enabling fast search on a limited budget. By employing methods like continued pre-training for domain adaptation and language reduction to decrease model size, a lightweight multilingual retrieval model was prepared, demonstrating superior performance compared to larger models pre-trained on general domain data. Furthermore, evaluating the proposed architecture that utilizes Rust Language capabilities shows the possibility of implementing efficient semantic search in a low-resource setting.

Published
2024

2. Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Author

Pavlova, Maya, Brinkman, Erik, Iyer, Krithika, Albiero, Vitor, Bitton, Joanna, Nguyen, Hailey, Li, Joe, Ferrer, Cristian Canton, Evtimov, Ivan, and Grattafiori, Aaron

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the way humans tend to interact with AI models. Common users of AI models may not have advanced knowledge of adversarial machine learning methods or access to model internals, and they do not spend a lot of time crafting a single highly effective adversarial prompt. Instead, they are likely to make use of techniques commonly shared online and exploit the multiturn conversational nature of LLMs. While manual testing addresses this gap, it is an inefficient and often expensive process. To address these limitations, we introduce the Generative Offensive Agent Tester (GOAT), an automated agentic red teaming system that simulates plain language adversarial conversations while leveraging multiple adversarial prompting techniques to identify vulnerabilities in LLMs. We instantiate GOAT with 7 red teaming attacks by prompting a general-purpose model in a way that encourages reasoning through the choices of methods available, the current target model's response, and the next steps. Our approach is designed to be extensible and efficient, allowing human testers to focus on exploring new areas of risk while automation covers the scaled adversarial stress-testing of known risk territory. We present the design and evaluation of GOAT, demonstrating its effectiveness in identifying vulnerabilities in state-of-the-art LLMs, with an ASR@10 of 97% against Llama 3.1 and 88% against GPT-4 on the JailbreakBench dataset.

Published
2024

3. Flipped Dialogic Learning Method with ChatGPT: A Case Study

Author

Nataliya Hristova Pavlova

Abstract

This article presents a case study and ideas to flip classical dialogic learning method. Some possibilities of using ChatGPT to stimulate the active role of the student in the dialogic teaching method are shown. Data from observations of students training to be teachers of mathematics and informatics in their work with artificial intelligence (AI) are presented. A model for the application of the flipped dialogue in the education of students is proposed. An example of dialogue is given. The study concludes that that the main advantages of using flipped dialog learning with AI are easy access to the platforms, the lack of stress and stimulating the research qualities of students when searching for specific information or stimulating the system to make mistakes. The ability to ask the right leading questions and to detect the gaps of the "interlocutor" are important competencies applicable in dealing with life's problems.

Published
2024

4. Enhancing the reactivity of Si(100)-Cl toward PBr3 by charging Si dangling bonds

Author

Pavlova, T. V. and Shevlyuga, V. M.

Subjects
Condensed Matter - Materials Science, Condensed Matter - Mesoscale and Nanoscale Physics
Abstract

The interaction of the PBr3 molecule with Si dangling bonds (DBs) on a chlorinated Si(100) surface was studied. The DBs were charged in a scanning tunneling microscope (STM) and then exposed to PBr3 directly in the STM chamber. Uncharged DBs rarely react with molecules. On the contrary, almost all positively charged DBs were filled with molecule fragments. As a result of the PBr3 interaction with the positively charged DB, the molecule dissociated into PBr2 and Br with the formation of a Si-Br bond and PBr2 desorption. These findings show that charged DBs significantly modify the reactivity of the surface towards PBr3. Additionally, we calculated PH3 adsorption on a Si(100)-2x1-H surface with DBs and found that the DB charge also has a significant impact. As a result, we demonstrated that the positively charged DB with a doubly unoccupied state enhances the adsorption of molecules with a lone pair of electrons.

Published
2024
Full Text
View/download PDF

5. The Llama 3 Herd of Models

Author

Grattafiori, Aaron, Dubey, Abhimanyu, Jauhri, Abhinav, Pandey, Abhinav, Kadian, Abhishek, Al-Dahle, Ahmad, Letman, Aiesha, Mathur, Akhil, Schelten, Alan, Vaughan, Alex, Yang, Amy, Fan, Angela, Goyal, Anirudh, Hartshorn, Anthony, Yang, Aobo, Mitra, Archi, Sravankumar, Archie, Korenev, Artem, Hinsvark, Arthur, Rao, Arun, Zhang, Aston, Rodriguez, Aurelien, Gregerson, Austen, Spataru, Ava, Roziere, Baptiste, Biron, Bethany, Tang, Binh, Chern, Bobbie, Caucheteux, Charlotte, Nayak, Chaya, Bi, Chloe, Marra, Chris, McConnell, Chris, Keller, Christian, Touret, Christophe, Wu, Chunyang, Wong, Corinne, Ferrer, Cristian Canton, Nikolaidis, Cyrus, Allonsius, Damien, Song, Daniel, Pintz, Danielle, Livshits, Danny, Wyatt, Danny, Esiobu, David, Choudhary, Dhruv, Mahajan, Dhruv, Garcia-Olano, Diego, Perino, Diego, Hupkes, Dieuwke, Lakomkin, Egor, AlBadawy, Ehab, Lobanova, Elina, Dinan, Emily, Smith, Eric Michael, Radenovic, Filip, Guzmán, Francisco, Zhang, Frank, Synnaeve, Gabriel, Lee, Gabrielle, Anderson, Georgia Lewis, Thattai, Govind, Nail, Graeme, Mialon, Gregoire, Pang, Guan, Cucurell, Guillem, Nguyen, Hailey, Korevaar, Hannah, Xu, Hu, Touvron, Hugo, Zarov, Iliyan, Ibarra, Imanol Arrieta, Kloumann, Isabel, Misra, Ishan, Evtimov, Ivan, Zhang, Jack, Copet, Jade, Lee, Jaewon, Geffert, Jan, Vranes, Jana, Park, Jason, Mahadeokar, Jay, Shah, Jeet, van der Linde, Jelmer, Billock, Jennifer, Hong, Jenny, Lee, Jenya, Fu, Jeremy, Chi, Jianfeng, Huang, Jianyu, Liu, Jiawen, Wang, Jie, Yu, Jiecao, Bitton, Joanna, Spisak, Joe, Park, Jongsoo, Rocca, Joseph, Johnstun, Joshua, Saxe, Joshua, Jia, Junteng, Alwala, Kalyan Vasuden, Prasad, Karthik, Upasani, Kartikeya, Plawiak, Kate, Li, Ke, Heafield, Kenneth, Stone, Kevin, El-Arini, Khalid, Iyer, Krithika, Malik, Kshitiz, Chiu, Kuenley, Bhalla, Kunal, Lakhotia, Kushal, Rantala-Yeary, Lauren, van der Maaten, Laurens, Chen, Lawrence, Tan, Liang, Jenkins, Liz, Martin, Louis, Madaan, Lovish, Malo, Lubo, Blecher, Lukas, Landzaat, Lukas, de Oliveira, Luke, Muzzi, Madeline, Pasupuleti, Mahesh, Singh, Mannat, Paluri, Manohar, Kardas, Marcin, Tsimpoukelli, Maria, Oldham, Mathew, Rita, Mathieu, Pavlova, Maya, Kambadur, Melanie, Lewis, Mike, Si, Min, Singh, Mitesh Kumar, Hassan, Mona, Goyal, Naman, Torabi, Narjes, Bashlykov, Nikolay, Bogoychev, Nikolay, Chatterji, Niladri, Zhang, Ning, Duchenne, Olivier, Çelebi, Onur, Alrassy, Patrick, Zhang, Pengchuan, Li, Pengwei, Vasic, Petar, Weng, Peter, Bhargava, Prajjwal, Dubal, Pratik, Krishnan, Praveen, Koura, Punit Singh, Xu, Puxin, He, Qing, Dong, Qingxiao, Srinivasan, Ragavan, Ganapathy, Raj, Calderer, Ramon, Cabral, Ricardo Silveira, Stojnic, Robert, Raileanu, Roberta, Maheswari, Rohan, Girdhar, Rohit, Patel, Rohit, Sauvestre, Romain, Polidoro, Ronnie, Sumbaly, Roshan, Taylor, Ross, Silva, Ruan, Hou, Rui, Wang, Rui, Hosseini, Saghar, Chennabasappa, Sahana, Singh, Sanjay, Bell, Sean, Kim, Seohyun Sonia, Edunov, Sergey, Nie, Shaoliang, Narang, Sharan, Raparthy, Sharath, Shen, Sheng, Wan, Shengye, Bhosale, Shruti, Zhang, Shun, Vandenhende, Simon, Batra, Soumya, Whitman, Spencer, Sootla, Sten, Collot, Stephane, Gururangan, Suchin, Borodinsky, Sydney, Herman, Tamar, Fowler, Tara, Sheasha, Tarek, Georgiou, Thomas, Scialom, Thomas, Speckbacher, Tobias, Mihaylov, Todor, Xiao, Tong, Karn, Ujjwal, Goswami, Vedanuj, Gupta, Vibhor, Ramanathan, Vignesh, Kerkez, Viktor, Gonguet, Vincent, Do, Virginie, Vogeti, Vish, Albiero, Vítor, Petrovic, Vladan, Chu, Weiwei, Xiong, Wenhan, Fu, Wenyin, Meers, Whitney, Martinet, Xavier, Wang, Xiaodong, Wang, Xiaofang, Tan, Xiaoqing Ellen, Xia, Xide, Xie, Xinfeng, Jia, Xuchao, Wang, Xuewei, Goldschlag, Yaelle, Gaur, Yashesh, Babaei, Yasmine, Wen, Yi, Song, Yiwen, Zhang, Yuchen, Li, Yue, Mao, Yuning, Coudert, Zacharie Delpierre, Yan, Zheng, Chen, Zhengxing, Papakipos, Zoe, Singh, Aaditya, Srivastava, Aayushi, Jain, Abha, Kelsey, Adam, Shajnfeld, Adam, Gangidi, Adithya, Victoria, Adolfo, Goldstand, Ahuva, Menon, Ajay, Sharma, Ajay, Boesenberg, Alex, Baevski, Alexei, Feinstein, Allie, Kallet, Amanda, Sangani, Amit, Teo, Amos, Yunus, Anam, Lupu, Andrei, Alvarado, Andres, Caples, Andrew, Gu, Andrew, Ho, Andrew, Poulton, Andrew, Ryan, Andrew, Ramchandani, Ankit, Dong, Annie, Franco, Annie, Goyal, Anuj, Saraf, Aparajita, Chowdhury, Arkabandhu, Gabriel, Ashley, Bharambe, Ashwin, Eisenman, Assaf, Yazdan, Azadeh, James, Beau, Maurer, Ben, Leonhardi, Benjamin, Huang, Bernie, Loyd, Beth, De Paola, Beto, Paranjape, Bhargavi, Liu, Bing, Wu, Bo, Ni, Boyu, Hancock, Braden, Wasti, Bram, Spence, Brandon, Stojkovic, Brani, Gamido, Brian, Montalvo, Britt, Parker, Carl, Burton, Carly, Mejia, Catalina, Liu, Ce, Wang, Changhan, Kim, Changkyu, Zhou, Chao, Hu, Chester, Chu, Ching-Hsiang, Cai, Chris, Tindal, Chris, Feichtenhofer, Christoph, Gao, Cynthia, Civin, Damon, Beaty, Dana, Kreymer, Daniel, Li, Daniel, Adkins, David, Xu, David, Testuggine, Davide, David, Delia, Parikh, Devi, Liskovich, Diana, Foss, Didem, Wang, Dingkang, Le, Duc, Holland, Dustin, Dowling, Edward, Jamil, Eissa, Montgomery, Elaine, Presani, Eleonora, Hahn, Emily, Wood, Emily, Le, Eric-Tuan, Brinkman, Erik, Arcaute, Esteban, Dunbar, Evan, Smothers, Evan, Sun, Fei, Kreuk, Felix, Tian, Feng, Kokkinos, Filippos, Ozgenel, Firat, Caggioni, Francesco, Kanayet, Frank, Seide, Frank, Florez, Gabriela Medina, Schwarz, Gabriella, Badeer, Gada, Swee, Georgia, Halpern, Gil, Herman, Grant, Sizov, Grigory, Guangyi, Zhang, Lakshminarayanan, Guna, Inan, Hakan, Shojanazeri, Hamid, Zou, Han, Wang, Hannah, Zha, Hanwen, Habeeb, Haroun, Rudolph, Harrison, Suk, Helen, Aspegren, Henry, Goldman, Hunter, Zhan, Hongyuan, Damlaj, Ibrahim, Molybog, Igor, Tufanov, Igor, Leontiadis, Ilias, Veliche, Irina-Elena, Gat, Itai, Weissman, Jake, Geboski, James, Kohli, James, Lam, Janice, Asher, Japhet, Gaya, Jean-Baptiste, Marcus, Jeff, Tang, Jeff, Chan, Jennifer, Zhen, Jenny, Reizenstein, Jeremy, Teboul, Jeremy, Zhong, Jessica, Jin, Jian, Yang, Jingyi, Cummings, Joe, Carvill, Jon, Shepard, Jon, McPhie, Jonathan, Torres, Jonathan, Ginsburg, Josh, Wang, Junjie, Wu, Kai, U, Kam Hou, Saxena, Karan, Khandelwal, Kartikay, Zand, Katayoun, Matosich, Kathy, Veeraraghavan, Kaushik, Michelena, Kelly, Li, Keqian, Jagadeesh, Kiran, Huang, Kun, Chawla, Kunal, Huang, Kyle, Chen, Lailin, Garg, Lakshya, A, Lavender, Silva, Leandro, Bell, Lee, Zhang, Lei, Guo, Liangpeng, Yu, Licheng, Moshkovich, Liron, Wehrstedt, Luca, Khabsa, Madian, Avalani, Manav, Bhatt, Manish, Mankus, Martynas, Hasson, Matan, Lennie, Matthew, Reso, Matthias, Groshev, Maxim, Naumov, Maxim, Lathi, Maya, Keneally, Meghan, Liu, Miao, Seltzer, Michael L., Valko, Michal, Restrepo, Michelle, Patel, Mihir, Vyatskov, Mik, Samvelyan, Mikayel, Clark, Mike, Macey, Mike, Wang, Mike, Hermoso, Miquel Jubert, Metanat, Mo, Rastegari, Mohammad, Bansal, Munish, Santhanam, Nandhini, Parks, Natascha, White, Natasha, Bawa, Navyata, Singhal, Nayan, Egebo, Nick, Usunier, Nicolas, Mehta, Nikhil, Laptev, Nikolay Pavlovich, Dong, Ning, Cheng, Norman, Chernoguz, Oleg, Hart, Olivia, Salpekar, Omkar, Kalinli, Ozlem, Kent, Parkin, Parekh, Parth, Saab, Paul, Balaji, Pavan, Rittner, Pedro, Bontrager, Philip, Roux, Pierre, Dollar, Piotr, Zvyagina, Polina, Ratanchandani, Prashant, Yuvraj, Pritish, Liang, Qian, Alao, Rachad, Rodriguez, Rachel, Ayub, Rafi, Murthy, Raghotham, Nayani, Raghu, Mitra, Rahul, Parthasarathy, Rangaprabhu, Li, Raymond, Hogan, Rebekkah, Battey, Robin, Wang, Rocky, Howes, Russ, Rinott, Ruty, Mehta, Sachin, Siby, Sachin, Bondu, Sai Jayesh, Datta, Samyak, Chugh, Sara, Hunt, Sara, Dhillon, Sargun, Sidorov, Sasha, Pan, Satadru, Mahajan, Saurabh, Verma, Saurabh, Yamamoto, Seiji, Ramaswamy, Sharadh, Lindsay, Shaun, Feng, Sheng, Lin, Shenghao, Zha, Shengxin Cindy, Patil, Shishir, Shankar, Shiva, Zhang, Shuqiang, Wang, Sinong, Agarwal, Sneha, Sajuyigbe, Soji, Chintala, Soumith, Max, Stephanie, Chen, Stephen, Kehoe, Steve, Satterfield, Steve, Govindaprasad, Sudarshan, Gupta, Sumit, Deng, Summer, Cho, Sungmin, Virk, Sunny, Subramanian, Suraj, Choudhury, Sy, Goldman, Sydney, Remez, Tal, Glaser, Tamar, Best, Tamara, Koehler, Thilo, Robinson, Thomas, Li, Tianhe, Zhang, Tianjun, Matthews, Tim, Chou, Timothy, Shaked, Tzook, Vontimitta, Varun, Ajayi, Victoria, Montanez, Victoria, Mohan, Vijai, Kumar, Vinay Satish, Mangla, Vishal, Ionescu, Vlad, Poenaru, Vlad, Mihailescu, Vlad Tiberiu, Ivanov, Vladimir, Li, Wei, Wang, Wenchen, Jiang, Wenwen, Bouaziz, Wes, Constable, Will, Tang, Xiaocheng, Wu, Xiaojian, Wang, Xiaolan, Wu, Xilun, Gao, Xinbo, Kleinman, Yaniv, Chen, Yanjun, Hu, Ye, Jia, Ye, Qi, Ye, Li, Yenda, Zhang, Yilin, Zhang, Ying, Adi, Yossi, Nam, Youngjin, Yu, Wang, Zhao, Yu, Hao, Yuchen, Qian, Yundi, Li, Yunlu, He, Yuzi, Rait, Zach, DeVito, Zachary, Rosnbrick, Zef, Wen, Zhaoduo, Yang, Zhenyu, Zhao, Zhiwei, and Ma, Zhiyu

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition
Abstract

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Published
2024

6. ESG-FTSE: A corpus of news articles with ESG relevance labels and use cases

Author

Pavlova, Mariya, Casey, Bernard, and Wang, Miaosen

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

We present ESG-FTSE, the first corpus comprised of news articles with Environmental, Social and Governance (ESG) relevance annotations. In recent years, investors and regulators have pushed ESG investing to the mainstream due to the urgency of climate change. This has led to the rise of ESG scores to evaluate an investment's credentials as socially responsible. While demand for ESG scores is high, their quality varies wildly. Quantitative techniques can be applied to improve ESG scores, thus, responsible investing. To contribute to resource building for ESG and financial text mining, we pioneer the ESG-FTSE corpus. We further present the first of its kind ESG annotation schema. It has three levels: a binary classification (relevant versus irrelevant news articles), ESG classification (ESG-related news articles), and target company. Both supervised and unsupervised learning experiments for ESG relevance detection were conducted to demonstrate that the corpus can be used in different settings to derive accurate ESG predictions. Keywords: corpus annotation, ESG labels, annotation schema, news article, natural language processing, Comment: The corpus is available at https://github.com/mariavpavlova/ESG-FTSE-Corpus. https://aclanthology.org/2024.finnlp-1.14/

Published
2024

18. Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications

Author

Ryzhakov, Gleb, Pavlova, Svetlana, Sevriugov, Egor, and Oseledets, Ivan

Subjects
Computer Science - Machine Learning
Abstract

This paper proposes a novel method, Explicit Flow Matching (ExFM), for training and analyzing flow-based generative models. ExFM leverages a theoretically grounded loss function, ExFM loss (a tractable form of Flow Matching (FM) loss), to demonstrably reduce variance during training, leading to faster convergence and more stable learning. Based on theoretical analysis of these formulas, we derived exact expressions for the vector field (and score in stochastic cases) for model examples (in particular, for separating multiple exponents), and in some simple cases, exact solutions for trajectories. In addition, we also investigated simple cases of diffusion generative models by adding a stochastic term and obtained an explicit form of the expression for score. While the paper emphasizes the theoretical underpinnings of ExFM, it also showcases its effectiveness through numerical experiments on various datasets, including high-dimensional ones. Compared to traditional FM methods, ExFM achieves superior performance in terms of both learning speed and final outcomes.

Published
2024

19. Not all reading is alike: Task modulation of magnetic evoked response to visual word

Author

Pavlova A. A., Butorina A. V., Nikolaeva A. Y., Prokofyev A. O., Ulanov M. A., and Stroganova T. A.

Subjects
visual word recognition, top-down modulations, sensorimotor transformation, speech lateralization, magnetoencephalography (MEG), Psychology, BF1-990
Abstract

Background. Previous studies have shown that brain response to a written word depends on the task: whether the word is a target in a version of lexical decision task or should be read silently. Although this effect has been interpreted as an evidence for an interaction between word recognition processes and task demands, it also may be caused by greater attention allocation to the target word. Objective. We aimed to examine the task effect on brain response evoked by non- target written words. Design. Using MEG and magnetic source imaging, we compared spatial-temporal pattern of brain response elicited by a noun cue when it was read silently either without additional task (SR) or with a requirement to produce an associated verb (VG). Results.The task demands penetrated into early (200-300 ms) and late (500-800 ms) stages of a word processing by enhancing brain response under VG versus SR condition. The cortical sources of the early response were localized to bilateral inferior occipitotemporal and anterior temporal cortex suggesting that more demanding VG task required elaborated lexical-semantic analysis. The late effect was observed in the associative auditory areas in middle and superior temporal gyri and in motor representation of articulators. Our results suggest that a remote goal plays a pivotal role in enhanced recruitment of cortical structures underlying orthographic, semantic and sensorimotor dimensions of written word perception from the early processing stages. Surprisingly, we found that to fulfil a more challenging goal the brain progressively engaged resources of the right hemisphere throughout all stages of silent reading. Conclusion. Our study demonstrates that a deeper processing of linguistic input amplifies activation of brain areas involved in integration of speech perception and production. This is consistent with theories that emphasize the role of sensorimotor integration in speech understanding.

Published
2017
Full Text
View/download PDF

20. Investigation of the Presence of Cyanotoxins, Nutrients and Composition of Phytoplankton Communities in the Bistritsa Dam in the Period 2017–2020

Author

Pavlova, Vera, Mitreva, Mariya, Georgieva, Vesela, Vasileva, Krasimira, Arsova, Stanimira, Rachinska, Milena, Lazarova, Antoaneta, Georgieva, Tzveta, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Dobrinkova, Nina, editor, and Fidanova, Stefka, editor

Published
2025
Full Text
View/download PDF

38. Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic

Author

Pavlova, Vera

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

In this work, we approach the problem of Qur'anic information retrieval (IR) in Arabic and English. Using the latest state-of-the-art methods in neural IR, we research what helps to tackle this task more efficiently. Training retrieval models requires a lot of data, which is difficult to obtain for training in-domain. Therefore, we commence with training on a large amount of general domain data and then continue training on in-domain data. To handle the lack of in-domain data, we employed a data augmentation technique, which considerably improved results in MRR@10 and NDCG@5 metrics, setting the state-of-the-art in Qur'anic IR for both English and Arabic. The absence of an Islamic corpus and domain-specific model for IR task in English motivated us to address this lack of resources and take preliminary steps of the Islamic corpus compilation and domain-specific language model (LM) pre-training, which helped to improve the performance of the retrieval models that use the domain-specific LM as the shared backbone. We examined several language models (LMs) in Arabic to select one that efficiently deals with the Qur'anic IR task. Besides transferring successful experiments from English to Arabic, we conducted additional experiments with retrieval task in Arabic to amortize the scarcity of general domain datasets used to train the retrieval models. Handling Qur'anic IR task combining English and Arabic allowed us to enhance the comparison and share valuable insights across models and languages.

Published
2023

39. Building Abstraction: The Role of Representation and Structural Alignment in Learning Causal System Categories

Author

Pavlova, Margarita V.

Subjects
Education, Psychology, Learning, Reasoning, Representation
Abstract

The present study examined the role of detecting the initial causal system model followed by engaging in active vs. passive structural alignment in recognizing the key causal principles in subsequent novel examples. The results echo prior research on the benefit of analogical comparison in learning relational categories: participants who were prompted to compare outperformed participants in the baseline condition. Moreover, while the accurate representation of the causal system predicted noticing the relational structure in novel examples, making more accurate relational mappings made participants more likely to notice the structure above and beyond having an accurate representation. These findings offer insight into the role of active vs. passive analogical comparison and have implications for conditions that might support learning of relational categories.

Published
2024

41. Targeting protein homeostasis with small molecules as a strategy for the development of pan-coronavirus antiviral therapies

Author

Mao, Yu-Qian, Jahanshahi, Shahrzad, Malty, Ramy, Van Ommen, David A. J., Wan, Yimei, Morey, Trevor M., Chuang, Stephanie H. W., Pavlova, Veronika, Ahmed, Choudhary, Dahal, Subha, Lin, Funing, Mangos, Maria, Nurtanto, Jocelyn, Song, Yuetong, Been, Terek, Christie-Holmes, Natasha, Gray-Owen, Scott D., Babu, Mohan, Wong, Amy P., Batey, Robert A., Attisano, Liliana, Cochrane, Alan, and Houry, Walid A.

Published
2024
Full Text
View/download PDF

42. Influence of Enhanced Synthesis of Exopolysaccharides in Rhizobium ruizarguesonis and Overproduction of Plant Receptor to these Compounds on Colonizing Activity of Rhizobia in Legume and Non-Legume Plants and Plant Resistance to Phytopathogenic Fungi

Author

Kantsurova, Elizaveta S., Bovin, Andrey D., Dymo, Alina M., Komolkina, Natalya A., Shalyakina, Alexandra A., Salnikova, Elizaveta A., Pavlova, Olga A., Yuzikhin, Oleg S., Vishnevskaya, Nadezhda A., and Dolgikh, Elena A.

Published
2024
Full Text
View/download PDF

47. A CD25-biased interleukin-2 for autoimmune therapy engineered via a semi-synthetic organism

Author

Ptacin, Jerod L., Ma, Lina, Caffaro, Carolina E., Acuff, Nicole V., Germar, Kristine, Severy, Peter, Qu, Yanyan, Vela, Jose-Luis, Cai, Xinming, San Jose, Kristine M., Aerni, Hans R., Chen, David B., Esche, Ean, Ismaili, Taylor K., Herman, Rob, Pavlova, Yelena, Pena, Michael J., Nguyen, Jasmine, Koriazova, Lilia K., Shawver, Laura K., Joseph, Ingrid B., Mooney, Jill, Peakman, Mark, and Milla, Marcos E.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results