Greg Durrett

Greg Durrett

Auto-generated profile, based on publicly available information

Greg Durrett

The University of Texas at Austin

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 April 2022 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
BMBenjamin Mariano
Benjamin Mariano
YCYanju Chen
Yanju Chen
YFYu Feng
Yu Feng
GDGreg Durrett
Greg Durrett
IDIşil Dillig
Işil Dillig
While many mainstream languages such as Java, Python, and C# increasingly incorporate functional APIs to simplify programming and improve parallelization/performance, there are no effective techniques that can be used to automatically translate existing imperative code to functional variants using these APIs. Motivated by this problem, this paper presents a transpilation approach based on inductive program synthesis for modernizing existing code. Our method is based on the observation that the overwhelming majority of source/target programs in this setting satisfy an assumption that we call trace-compatibility: not only do the programs share syntactically identical low-level expressions, but these expressions also take the same values in corresponding execution traces. Our method leverages this observation to design a new neural-guided synthesis algorithm that (1) uses a novel neural architecture called cognate grammar network (CGN) and (2) leverages a form of concolic execution to prune partial programs based on intermediate values that arise during a computation. We have implemented our approach in a tool called NGST2 and use it to translate imperative Java and Python code to functional variants that use the Stream and functools APIs respectively. Our experiments show that NGST2 significantly outperforms several baselines and that our proposed neural architecture and pruning techniques are vital for achieving good results.

16 October 2023 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
QCQiaochu Chen
Qiaochu Chen
ABArko Banerjee
Arko Banerjee
ÇDÇağatay Demiralp
Çağatay Demiralp
GDGreg Durrett
Greg Durrett
IDIşıl Dillig
Işıl Dillig
Many data extraction tasks of practical relevance require not only syntactic pattern matching but also semantic reasoning about the content of the underlying text. While regular expressions are very well suited for tasks that require only syntactic pattern matching, they fall short for data extraction tasks that involve both a syntactic and semantic component. To address this issue, we introduce semantic regexes, a generalization of regular expressions that facilitates combined syntactic and semantic reasoning about textual data. We also propose a novel learning algorithm that can synthesize semantic regexes from a small number of positive and negative examples. Our proposed learning algorithm uses a combination of neural sketch generation and compositional type-directed synthesis for fast and effective generalization from a small number of examples. We have implemented these ideas in a new tool called Smore and evaluated it on representative data extraction tasks involving several textual datasets. Our evaluation shows that semantic regexes can better support complex data extraction tasks than standard regular expressions and that our learning algorithm significantly outperforms existing tools, including state-of-the-art neural networks and program synthesis tools.

31 October 2022 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
QCQiaochu Chen
Qiaochu Chen
SPShankara Pailoor
Shankara Pailoor
CBCeleste Barnaby
Celeste Barnaby
ACAbby Criswell
Abby Criswell
CWChenglong Wang
Chenglong Wang
IDIşil Dillig
Işil Dillig
We propose a new technique based on program synthesis for automatically generating visualizations from natural language queries. Our method parses the natural language query into a refinement type specification using the intents-and-slots paradigm and leverages type-directed synthesis to generate a set of visualization programs that are most likely to meet the user's intent. Our refinement type system captures useful hints present in the natural language query and allows the synthesis algorithm to reject visualizations that violate well-established design guidelines for the input data set. We have implemented our ideas in a tool called Graphy and evaluated it on NLVCorpus, which consists of 3 popular datasets and over 700 real-world natural language queries. Our experiments show that Graphy significantly outperforms state-of-the-art natural language based visualization tools, including transformer and rule-based ones.

1 January 2019
Verified
Conference Paper
Open access
PDF file
AGAditya Gupta
Aditya Gupta
GDGreg Durrett
Greg Durrett
Aditya Gupta, Greg Durrett. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

1 January 2024
Verified
Conference Paper
Open access
PDF file
ADAbhishek Divekar
Abhishek Divekar
GDGreg Durrett
Greg Durrett
Abhishek Divekar, Greg Durrett. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

1 January 2022
Verified
Conference Paper
Open access
PDF file
ZSZayne Sprague
Zayne Sprague
KBKaj Bostrom
Kaj Bostrom
SCSwarat Chaudhuri
Swarat Chaudhuri
GDGreg Durrett
Greg Durrett
Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.