Multi-modal synthesis of regular expressions
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
In this paper, we propose a multi-modal synthesis technique for automatically constructing regular expressions (regexes) from a combination of examples and natural language. Using multiple modalities is useful in this context because natural language alone is often highly ambiguous, whereas examples in isolation are often not sufficient for conveying user intent. Our proposed technique first parses the English description into a so-called hierarchical sketch that guides our programming-by-example (PBE) engine. Since the hierarchical sketch captures crucial hints, the PBE engine can leverage this information to both prioritize the search as well as make useful deductions for pruning the search space.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
de Moura, L., & Bjørner, N. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-78800-3_24 · Cited by 6,595 · cited 1×
“. First, our semantic parser is built on top of the SEMPRE framework [7] and leverages its existing functionalities, such as the linguistic pre-processor. Second, Regel makes use of the Z3 SMT solver [12] for inferring possible values of the symbolic integers (recall Section5.2). Finally, Regel uses the Brics automato…”
MethodAutomating string processing in spreadsheets using input-output examples
Gulwani, S. (2011) · ACM SIGPLAN Notices · doi:10.1145/1925844.1926423 · Cited by 581
Program synthesis using conflict-driven learning
Feng, Y., Martins, R., Bastani, O., & Dillig, I. (2018) · Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3192366.3192382 · Cited by 111 · cited 1×
“PBE and sketching Similar to this work, several recent PBE techniques combine top-down enumerative search with lightweight deductive reasoning to significantly prune the search space [3, 13–15, 26, 36, 46].”
MethodSelf-citation
Cited by
Jiang, E., Toh, E., Molina, A., Olson, K., Kayacik, C., Donsbach, A., Cai, C. J., & Terry, M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501870 · Cited by 79
“Programming-by-example is also a form of inductive specifcation in which users defne a function by providing input-output examples (e.g., [19, 39, 42]).”
BackgroundTop-Down Synthesis for Library Learning
Bowers, M., Olausson, T. X., Wong, L., Grand, G., Tenenbaum, J. B., Ellis, K., & Solar-Lezama, A. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3571234 · Cited by 33
“2016], over- and underapproximations of the behaviors of holes [Chen et al. 2020; Lee et al. 2016], and probabilistic techniques to heuristically guide the search [Balog et al.”
Petridis, S., Wedin, B. D., Wexler, J., Pushkarna, M., Donsbach, A., Goyal, N., Cai, C. J., & Terry, M. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645144 · Cited by 31
Metadata
- Authors
- Chen, Q., Wang, X., Ye, X., Durrett, G., & Dillig, I.
- Venue
- Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation
- Publisher
- ACM
- Published
- 2020-06-11
- Pages
- 487-502
- ISSN
- 1531-7102 (ISSN-L)
- OpenAlex
- W3033889389
- Cited by
- 79
- References
- 3
- FWCI
- 5.34
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.