Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines

• URL: http://arxiv.org/abs/2505.15874v1
• Date: Wed, 21 May 2025 15:40:53 GMT
• Title: Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines
• Authors: Yuhang Ge, Yachuan Liu, Yuren Mao, Yunjun Gao,
• Abstract summary: We introduce Text-to-Pipeline, a task that translates data preparation instructions into DP pipelines.<n>We also develop a benchmark named PARROT to support systematic evaluation.<n>Despite this improvement, there remains substantial room for progress on Text-to-Pipeline.
• Score: 23.421567721746765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data preparation (DP) transforms raw data into a form suitable for downstream applications, typically by composing operations into executable pipelines. Building such pipelines is time-consuming and requires sophisticated programming skills. If we can build the pipelines with natural language (NL), the technical barrier of DP will be significantly reduced. However, constructing DP pipelines from NL instructions remains underexplored. To fill the gap, we introduce Text-to-Pipeline, a new task that translates NL data preparation instructions into DP pipelines. Furthermore, we develop a benchmark named PARROT to support systematic evaluation. To simulate realistic DP scenarios, we mined transformation patterns from production pipelines and instantiated them on 23,009 real-world tables collected from six public sources. The resulting benchmark comprises ~18,000 pipelines covering 16 core DP operators. We evaluated cutting-edge large language models on PARROTand observed that they only solved 72.86% of the cases, revealing notable limitations in instruction understanding and multi-step reasoning. To address this, we propose Pipeline-Agent, a stronger baseline that iteratively predicts and executes operations with intermediate table feedback, achieving the best performance of 76.17%. Despite this improvement, there remains substantial room for progress on Text-to-Pipeline. Our data, codes, and evaluation tools are available at https://anonymous.4open.science/r/Text-to-Pipeline.

Related papers

• FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language [48.79534869177174]
  We introduce a new pre-training dataset curation pipeline based on FineWeb.<n>We show that our pipeline can be used to create non-English corpora that produce more performant models than prior datasets.<n>We scale our pipeline to over 1000 languages using almost 100 Common Crawl snapshots to produce FineWeb2, a new 20 terabyte (5 billion document) multilingual dataset.
  arXiv  Detail & Related papers  (2025-06-26T01:01:47Z)
• Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language [0.0]
  This article presents a pipeline for automated fact-checking leveraging publicly available Language Models and data. The pipeline consists of two main modules -- the evidence retrieval and the claim veracity evaluation. We provide open access to all data and fine-tuned models for Czech, English, Polish, and Slovak pipelines.
  arXiv  Detail & Related papers  (2023-12-15T19:43:41Z)
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines [44.772892598128784]
  We introduce DSPy, a programming model that abstracts LM pipelines as text transformation graphs. Within minutes of compiling, a few lines of DSPy allow GPT-3.5 and llama2-13b-chat to self-bootstrap pipelines.
  arXiv  Detail & Related papers  (2023-10-05T17:37:25Z)
• Deep Pipeline Embeddings for AutoML [11.168121941015015]
  AutoML is a promising direction for democratizing AI by automatically deploying Machine Learning systems with minimal human expertise. Existing Pipeline Optimization techniques fail to explore deep interactions between pipeline stages/components. This paper proposes a novel neural architecture that captures the deep interaction between the components of a Machine Learning pipeline.
  arXiv  Detail & Related papers  (2023-05-23T12:40:38Z)
• Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP [77.817293104436]
  We propose a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings.
  arXiv  Detail & Related papers  (2022-12-28T18:52:44Z)
• Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines [77.45213180689952]
  Preprocessing pipelines in deep learning aim to provide sufficient data throughput to keep the training processes busy. We introduce a new perspective on efficiently preparing datasets for end-to-end deep learning pipelines. We obtain an increased throughput of 3x to 13x compared to an untuned system.
  arXiv  Detail & Related papers  (2022-02-17T14:31:58Z)
• PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers [47.194426122333205]
  PipeTransformer is a distributed training algorithm for Transformer models. It automatically adjusts the pipelining and data parallelism by identifying and freezing some layers during the training. We evaluate PipeTransformer using Vision Transformer (ViT) on ImageNet and BERT on GLUE and SQuAD datasets.
  arXiv  Detail & Related papers  (2021-02-05T13:39:31Z)
• AutoWeka4MCPS-AVATAR: Accelerating Automated Machine Learning Pipeline Composition and Optimisation [13.116806430326513]
  We propose a novel method to evaluate the validity of ML pipelines, without their execution, using a surrogate model (AVATAR) The AVATAR generates a knowledge base by automatically learning the capabilities and effects of ML algorithms on datasets' characteristics. Instead of executing the original ML pipeline to evaluate its validity, the AVATAR evaluates its surrogate model constructed by capabilities and effects of the ML pipeline components.
  arXiv  Detail & Related papers  (2020-11-21T14:05:49Z)
• Unsupervised Parallel Corpus Mining on Web Data [53.74427402568838]
  We present a pipeline to mine the parallel corpus from the Internet in an unsupervised manner. Our system produces new state-of-the-art results, 39.81 and 38.95 BLEU scores, even compared with supervised approaches.
  arXiv  Detail & Related papers  (2020-09-18T02:38:01Z)
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training [93.79766670391618]
  We present POINTER, a novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
  arXiv  Detail & Related papers  (2020-05-01T18:11:54Z)
• AVATAR -- Machine Learning Pipeline Evaluation Using Surrogate Model [10.83607599315401]
  We propose a novel method to evaluate the validity of ML pipelines using a surrogate model (AVATAR) Our experiments show that the AVATAR is more efficient in evaluating complex pipelines in comparison with the traditional evaluation approaches requiring their execution.
  arXiv  Detail & Related papers  (2020-01-30T02:53:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.