Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
| Title: | Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages |
|---|---|
| Authors: | Ahmad, Wasi Uddin, Chakraborty, Saikat, Ray, Baishakhi, Chang, Kai-Wei |
| Publication Year: | 2022 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computation and Language, Computer Science - Programming Languages |
| More Details: | Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The target-to-source model generates noisy sources, while the source-to-target model is trained to reconstruct the targets and vice versa. Recent developments of multilingual pre-trained sequence-to-sequence models for programming languages have been very effective for a broad spectrum of downstream software engineering tasks. Hence, training them to build programming language translation systems via back-translation is compelling. However, these models cannot be further trained via back-translation since they learn to output sequences in the same language as the inputs during pre-training. As an alternative, we propose performing back-translation via code summarization and generation. In code summarization, a model learns to generate natural language (NL) summaries given code snippets. In code generation, the model learns to do the opposite. Therefore, target-to-source generation in back-translation can be viewed as a target-to-NL-to-source generation. We show that our proposed approach performs competitively with state-of-the-art methods. We have made the code publicly available. Comment: Accepted to EACL 2023 (Main) |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2205.11116 |
| Accession Number: | edsarx.2205.11116 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2205.11116 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20220523&spage=&pages=&title=Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages&atitle=Summarize%20and%20Generate%20to%20Back-translate%3A%20Unsupervised%20Translation%20of%20Programming%20Languages&aulast=Ahmad%2C%20Wasi%20Uddin&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2205.11116 RelevancyScore: 1032 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1032.37963867188 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ahmad%2C+Wasi+Uddin%22">Ahmad, Wasi Uddin</searchLink><br /><searchLink fieldCode="AR" term="%22Chakraborty%2C+Saikat%22">Chakraborty, Saikat</searchLink><br /><searchLink fieldCode="AR" term="%22Ray%2C+Baishakhi%22">Ray, Baishakhi</searchLink><br /><searchLink fieldCode="AR" term="%22Chang%2C+Kai-Wei%22">Chang, Kai-Wei</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2022 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computation+and+Language%22">Computer Science - Computation and Language</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Programming+Languages%22">Computer Science - Programming Languages</searchLink> – Name: Abstract Label: Description Group: Ab Data: Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The target-to-source model generates noisy sources, while the source-to-target model is trained to reconstruct the targets and vice versa. Recent developments of multilingual pre-trained sequence-to-sequence models for programming languages have been very effective for a broad spectrum of downstream software engineering tasks. Hence, training them to build programming language translation systems via back-translation is compelling. However, these models cannot be further trained via back-translation since they learn to output sequences in the same language as the inputs during pre-training. As an alternative, we propose performing back-translation via code summarization and generation. In code summarization, a model learns to generate natural language (NL) summaries given code snippets. In code generation, the model learns to do the opposite. Therefore, target-to-source generation in back-translation can be viewed as a target-to-NL-to-source generation. We show that our proposed approach performs competitively with state-of-the-art methods. We have made the code publicly available.<br />Comment: Accepted to EACL 2023 (Main) – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2205.11116" linkWindow="_blank">http://arxiv.org/abs/2205.11116</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2205.11116 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2205.11116 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computation and Language Type: general – SubjectFull: Computer Science - Programming Languages Type: general Titles: – TitleFull: Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ahmad, Wasi Uddin – PersonEntity: Name: NameFull: Chakraborty, Saikat – PersonEntity: Name: NameFull: Ray, Baishakhi – PersonEntity: Name: NameFull: Chang, Kai-Wei IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 05 Type: published Y: 2022 |
| ResultId | 1 |