paper-with-me

Papers

A Retrieve-and-Edit Framework for Predicting Structured Outputs

2018-12-04 · NeurIPS 2018 12 · Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

For the task of generating complex outputs such as source code, editing existing outputs can be easier than generating complex outputs from scratch. With this motivation, we propose an approach that first retrieves a training example based on the input (e.g., natural language description) and then edits it to the desired output (e.g., code). Our contribution is a computationally efficient method for learning a retrieval model that embeds the input in a task-dependent way without relying on a hand-crafted metric or incurring the expense of jointly training the retriever with the editor. Our retrieve-and-edit framework can be applied on top of any base model. We show that on a new autocomplete task for GitHub Python code and the Hearthstone cards benchmark, retrieve-and-edit significantly boosts the performance of a vanilla sequence-to-sequence model on both tasks.

📄 PDF Abstract BibTeX arXiv:1812.01194

Code (1)

https://worksheets.codalab.org/worksheets/0x1ad3f387005c492ea913cf0f20c9bb89 공식 구현

Tasks

Retrieval

Similar Papers 제목 키워드 기반

EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

2023-08-26 · Jia Li, Yongmin Li, Ge Li, Xing Hu 외

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Code summarization aims to generate natura…

Code SummarizationInformativenessSource Code Summarization

Simple and Effective Retrieve-Edit-Rerank Text Generation

2020-07-01 · ACL 2020 6 · Nabil Hossain, Marjan Ghazvininejad, Luke Zettlemoyer

Retrieve-and-edit seq2seq methods typically retrieve an output from the training set and learn a model to edit it to produce the final output. We propose to extend this framework with a simple and effective post-generati…

Machine TranslationRe-RankingText GenerationTranslation

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

2026-01-22 · Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye 외 arxiv

Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independe…

Novel View Synthesis

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models

2024-09-16 · Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei 외

As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing out…

knowledge editingQuestion Answering

Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

2019-06-10 · ACL 2019 7 · Sam Wiseman, Karl Stratos

Retrieve-and-edit based approaches to structured prediction, where structures associated with retrieved neighbors are edited to form new structures, have recently attracted increased interest. However, much recent work m…

FormStructured Prediction