Structural Transfer Learning in NL-to-Bash Semantic Parsers
Large-scale pre-training has made progress in many fields of natural language processing, though little is understood about the design of pre-training datasets. We propose a methodology for obtaining a quantitative understanding of structural overlap between machine translation tasks. We apply our methodology to the natural language to Bash semantic parsing task (NLBash) and show that it is largely reducible to lexical alignment. We also find that there is strong structural overlap between NLBash and natural language to SQL. Additionally, we perform a study varying compute expended during pre-training on the English to German machine translation task and find that more compute expended during pre-training does not always correspond semantic representations with stronger transfer to NLBash.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSemantic ParsingTransfer LearningTranslationSimilar Papers 제목 키워드 기반
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
We present new data and semantic parsing methods for the problem of mapping English sentences to Bash commands (NL2Bash). Our long-term goal is to enable any user to perform operations such as file manipulation, search, …
Semantic ParsingSubliminal Transfer of Unsafe Behaviors in AI Agent Distillation
Recent work on subliminal learning demonstrates that language models can transmit semantic traits through data that is semantically unrelated to those traits. However, it remains unclear whether behavioral traits can tra…
Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer
Strong and affordable in-domain data is a desirable asset when transferring trained semantic parsers to novel domains. As previous methods for semi-automatically constructing such data cannot handle the complexity of rea…
Text to SQLText-To-SQLError Detection for Text-to-SQL Semantic Parsing
Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. Specifically, modern text-to-SQL parsers based on deep learning are often over-c…
Language ModelingLanguage ModellingSemantic ParsingText to SQL+1Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing
The availability of corpora has led to significant advances in training semantic parsers in English. Unfortunately, for languages other than English, annotated data is limited and so is the performance of the developed p…
Cross-Lingual TransferPOSSemantic ParsingZero-Shot Cross-Lingual Transfer