Razvan Bunescu
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
Razvan Bunescu has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Avinash Karanth
Ohio University
3 shared publications Cindy Marling
School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701, USA
3 shared publications- Cindy Marling
School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701, USA
3 shared publications - Quintin Fettes
Meta, Menlo Park, CA, USA
3 shared publications - Ahmed Louri
George Washington University, Washington, DC, USA
2 shared publications - Chang Liu
Ohio University, Athens, Ohio, USA
2 shared publications
Latest Publications
- Open Access
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 53-59
Can Language Models Employ the Socratic Method? Experiments with Code Debugging
When employing the Socratic method of teaching, instructors guide students toward solving a problem on their own rather than providing the solution directly. While this strategy can substantially improve learning outcomes, it is usually time-consuming and cognitively demanding. Automated Socratic conversational agents can augment human instruction and provide the necessary scale, however their development is hampered by the lack of suitable data for training and evaluation. In this paper, we introduce a manually created dataset of multi-turn Socratic advice that is aimed at helping a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of a number of language models, ranging from fine-tuning the instruction-based text-to-text transformer Flan-T5 to zero-shot and chain of thought prompting of the much larger GPT-4. The code and datasets are made freely available for research at the link below.
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 53-59
Open AccessCan Language Models Employ the Socratic Method? Experiments with Code Debugging
When employing the Socratic method of teaching, instructors guide students toward solving a problem on their own rather than providing the solution directly. While this strategy can substantially improve learning outcomes, it is usually time-consuming and cognitively demanding. Automated Socratic conversational agents can augment human instruction and provide the necessary scale, however their development is hampered by the lack of suitable data for training and evaluation. In this paper, we introduce a manually created dataset of multi-turn Socratic advice that is aimed at helping a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of a number of language models, ranging from fine-tuning the instruction-based text-to-text transformer Flan-T5 to zero-shot and chain of thought prompting of the much larger GPT-4. The code and datasets are made freely available for research at the link below.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 79-84
An Expectation-Realization Model for Metaphor Detection: Within Distribution, Out of Distribution, and Out of Pretraining
Oseremen Uduehi, Razvan Bunescu. Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 79-84
Open AccessAn Expectation-Realization Model for Metaphor Detection: Within Distribution, Out of Distribution, and Out of Pretraining
Oseremen Uduehi, Razvan Bunescu. Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024). 2024.
- Open Access
An Expectation-Realization Model for Metaphor Detection
We propose a metaphor detection architecture that is structured around two main modules: an expectation component that estimates representations of literal word expectations given a context, and a realization component that computes representations of actual word meanings in context. The overall architecture is trained to learn expectation-realization (ER) patterns that characterize metaphorical uses of words. When evaluated on three metaphor datasets for within distribution, out of distribution, and novel metaphor generalization, the proposed method is shown to obtain results that are competitive or better than state-of-the art. Further increases in metaphor detection accuracy are obtained through ensembling of ER models.
Open AccessAn Expectation-Realization Model for Metaphor Detection
We propose a metaphor detection architecture that is structured around two main modules: an expectation component that estimates representations of literal word expectations given a context, and a realization component that computes representations of actual word meanings in context. The overall architecture is trained to learn expectation-realization (ER) patterns that characterize metaphorical uses of words. When evaluated on three metaphor datasets for within distribution, out of distribution, and novel metaphor generalization, the proposed method is shown to obtain results that are competitive or better than state-of-the art. Further increases in metaphor detection accuracy are obtained through ensembling of ER models.
- Open Access
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 933-939
Topic-Level Bayesian Surprise and Serendipity for Recommender Systems
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 933-939
Open AccessTopic-Level Bayesian Surprise and Serendipity for Recommender Systems
- Open Access
- 17 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Flumen: Dynamic Processing in the Photonic Interconnect
In chiplet-based heterogeneous architectures, electrical network-on-package (NoP) designs are typically over-provisioned with routers and channels to provide sufficient bandwidth during periods of high network load. Observing that there are significant periods of low/idle network utilization, prior work has proposed modified network-on-chip (NoC) architectures to enable in-network compute, especially for compute-intensive operations (e.g. linear algebra). However, electrical package-level interconnects impose fundamental energy and bandwidth scaling issues for future chiplet architectures. This paper proposes Flumen, a dual-purpose photonic interconnect that provides communication at the package-level while also doubling as an accelerator, performing parallel linear computation when network load is low. The proposed architecture utilizes the inherent parallelism of light to create energy-efficient interconnects that support en route computation with minimal changes to the network. By dynamically adjusting the topology, Flumen can change the communication and compute sections of the architecture to adapt to workload fluctuations. Performance evaluation on linear algebra applications shows that Flumen achieves a 2.5× reduction in energy, a 3.6× speedup improvement, and a 9.3× reduction in energy-delay product on average when compared to an electrical mesh network that is used exclusively for communication.
- 17 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessFlumen: Dynamic Processing in the Photonic Interconnect
In chiplet-based heterogeneous architectures, electrical network-on-package (NoP) designs are typically over-provisioned with routers and channels to provide sufficient bandwidth during periods of high network load. Observing that there are significant periods of low/idle network utilization, prior work has proposed modified network-on-chip (NoC) architectures to enable in-network compute, especially for compute-intensive operations (e.g. linear algebra). However, electrical package-level interconnects impose fundamental energy and bandwidth scaling issues for future chiplet architectures. This paper proposes Flumen, a dual-purpose photonic interconnect that provides communication at the package-level while also doubling as an accelerator, performing parallel linear computation when network load is low. The proposed architecture utilizes the inherent parallelism of light to create energy-efficient interconnects that support en route computation with minimal changes to the network. By dynamically adjusting the topology, Flumen can change the communication and compute sections of the architecture to adapt to workload fluctuations. Performance evaluation on linear algebra applications shows that Flumen achieves a 2.5× reduction in energy, a 3.6× speedup improvement, and a 9.3× reduction in energy-delay product on average when compared to an electrical mesh network that is used exclusively for communication.
- Open Access
Reclaimer: A Reinforcement Learning Approach to Dynamic Resource Allocation for Cloud Microservices
Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development, modularity, and isolation. However, dependencies among microservices with uneven execution time may result in longer queues, idle resources, or Quality-of-Service (QoS) violations. In this paper we introduce Reclaimer, a deep reinforcement learning model that adapts to runtime changes in the number and behavior of microservices in order to minimize CPU core allocation while meeting QoS requirements. When evaluated with two benchmark microservice-based applications, Reclaimer reduces the mean CPU core allocation by 38.4% to 74.4% relative to the industry-standard scaling solution, and by 27.5% to 58.1% relative to a current state-of-the art method.
Open AccessReclaimer: A Reinforcement Learning Approach to Dynamic Resource Allocation for Cloud Microservices
Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development, modularity, and isolation. However, dependencies among microservices with uneven execution time may result in longer queues, idle resources, or Quality-of-Service (QoS) violations. In this paper we introduce Reclaimer, a deep reinforcement learning model that adapts to runtime changes in the number and behavior of microservices in order to minimize CPU core allocation while meeting QoS requirements. When evaluated with two benchmark microservice-based applications, Reclaimer reduces the mean CPU core allocation by 38.4% to 74.4% relative to the industry-standard scaling solution, and by 27.5% to 58.1% relative to a current state-of-the art method.
- Open Access
Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
The ever-growing complexity of mathematical proofs makes their manual verification by mathematicians very cognitively demanding. Autoformalization seeks to address this by translating proofs written in natural language into a formal representation that is computer-verifiable via interactive theorem provers. In this paper, we introduce a semantic parsing approach, based on the Universal Transformer architecture, that translates elementary mathematical proofs into an equivalent formalization in the language of the Coq interactive theorem prover. The same architecture is also trained to translate simple imperative code decorated with Hoare triples into formally verifiable proofs of correctness in Coq. Experiments on a limited domain of artificial and human-written proofs show that the models generalize well to intermediate lengths not seen during training and variations in natural language.
Open AccessTowards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
The ever-growing complexity of mathematical proofs makes their manual verification by mathematicians very cognitively demanding. Autoformalization seeks to address this by translating proofs written in natural language into a formal representation that is computer-verifiable via interactive theorem provers. In this paper, we introduce a semantic parsing approach, based on the Universal Transformer architecture, that translates elementary mathematical proofs into an equivalent formalization in the language of the Coq interactive theorem prover. The same architecture is also trained to translate simple imperative code decorated with Hoare triples into formally verifiable proofs of correctness in Coq. Experiments on a limited domain of artificial and human-written proofs show that the models generalize well to intermediate lengths not seen during training and variations in natural language.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 709-726
Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations
Erfan Al-Hossami, Razvan Bunescu, Ryan Teehan, Laurel Powell, Khyati Mahajan, Mohsen Dorodchi. Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 709-726
Top Cited PapersOpen AccessSocratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations
Erfan Al-Hossami, Razvan Bunescu, Ryan Teehan, Laurel Powell, Khyati Mahajan, Mohsen Dorodchi. Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023). 2023.
- Open Access
- 29 October 2021
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (3) , 769-793
A semantic parsing pipeline for context-dependent question answering over temporally structured data
We propose a new setting for question answering (QA) in which users can query the system using both natural language and direct interactions within a graphical user interface that displays multiple time series associated with an entity of interest. The user interacts with the interface in order to understand the entity’s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We describe a pipeline implementation where spoken questions are first transcribed into text which is then semantically parsed into logical forms that can be used to automatically extract the answer from the underlying database. The speech recognition module is implemented by adapting a pre-trained long short-term memory (LSTM)-based architecture to the user’s speech, whereas for the semantic parsing component we introduce an LSTM-based encoder–decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When evaluated separately, with and without data augmentation, both models are shown to substantially outperform several strong baselines. Furthermore, the full pipeline evaluation shows only a small degradation in semantic parsing accuracy, demonstrating that the semantic parser is robust to mistakes in the speech recognition output. The new QA paradigm proposed in this paper has the potential to improve the presentation and navigation of the large amounts of sensor data and life events that are generated in many areas of medicine.
- 29 October 2021
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 29 (3) , 769-793
Open AccessA semantic parsing pipeline for context-dependent question answering over temporally structured data
We propose a new setting for question answering (QA) in which users can query the system using both natural language and direct interactions within a graphical user interface that displays multiple time series associated with an entity of interest. The user interacts with the interface in order to understand the entity’s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We describe a pipeline implementation where spoken questions are first transcribed into text which is then semantically parsed into logical forms that can be used to automatically extract the answer from the underlying database. The speech recognition module is implemented by adapting a pre-trained long short-term memory (LSTM)-based architecture to the user’s speech, whereas for the semantic parsing component we introduce an LSTM-based encoder–decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When evaluated separately, with and without data augmentation, both models are shown to substantially outperform several strong baselines. Furthermore, the full pipeline evaluation shows only a small degradation in semantic parsing accuracy, demonstrating that the semantic parser is robust to mistakes in the speech recognition output. The new QA paradigm proposed in this paper has the potential to improve the presentation and navigation of the large amounts of sensor data and life events that are generated in many areas of medicine.
- 1 July 2021
- Published by Elsevier in Information Processing & Management
- Vol. 58 (4)
Changing the narrative perspective: From deictic to anaphoric point of view
- 1 July 2021
- Published by Elsevier in Information Processing & Management
- Vol. 58 (4)
Changing the narrative perspective: From deictic to anaphoric point of view