Neural Pipeline for Zero-Shot Data-to-Text Generation
In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how to avoid finetuning the pretrained language models (PLMs) on D2T generation datasets while still taking advantage of surface realization capabilities of PLMs. Inspired by pipeline approaches, we propose to generate text by rephrasing single-item templates using a sequence of modules trained on general-domain text-based operations—ordering, aggregation, and paragraph compression. We train PLMs for performing these operations on a synthetic corpus WikiFluent which we build from English Wikipedia. Our experiments on two major triple-to-text datasets—WebNLG and E2E—show that our approach enables D2T generation from RDF triples in zero-shot settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Data-to-Text GenerationText GenerationSimilar Papers 제목 키워드 기반
Neural Pipeline for Zero-Shot Data-to-Text Generation
In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how to avoid finetuning pretrained language models (PLMs) on D2T …
Data-to-Text GenerationText GenerationA Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction
Current social science efforts automatically populate event databases of "who did what to whom?" tuples, by applying event extraction (EE) to text such as news. The event databases are used to analyze sociopolitical dyna…
Computational EfficiencyEvent ExtractionInstruction FollowingLanguage Modeling+3AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation t…
text-to-speechText to SpeechZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL
Text-to-SQL translates natural language into executable SQL queries. Few-shot in-context learning methods built upon large language models (LLMs) achieve strong performance, yet their reliance on demonstrations limits cr…
Domain GeneralizationCan Large Language Models Transform Computational Social Science?
Large Language Models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuas…
Persuasiveness