arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.12088cs.CL
收藏

从食谱中无监督学习图结构

Unsupervised Learning of Graph from Recipes

University College London(伦敦大学学院)

Aissatou Diallo, Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller

AI总结:

本文提出一种无监督 text-to-graph 与 graph-to-text 迭代框架,从烹饪食谱中识别实体并学习动作序列图,且在实体、文本重构和图生成质量上进行评估。

摘要:

烹饪食谱是最容易获得的程序性文本之一。它们由自然语言指令组成,而这些指令可能具有解释难度。本文提出一种模型,用于从食谱中识别相关信息,并生成图来表示食谱中的动作序列。与其他方法不同,我们采用无监督方法。我们每次处理一个序列,迭代学习图结构以及对文本进行编码的 GNN 参数(text-to-graph,文本到图);同时,通过将图解码为文本(graph-to-text,图到文本),并将生成文本与输入进行比较来提供监督。我们通过以下方式评估该方法:将识别出的实体与带标注数据集进行比较,比较输入文本与输出文本之间的差异,并将我们生成的图与最先进方法生成的图进行比较。

英文摘要:

Cooking recipes are one of the most readily available kinds of procedural text. They consist of natural language instructions that can be challenging to interpret. In this paper, we propose a model to identify relevant information from recipes and generate a graph to represent the sequence of actions in the recipe. In contrast with other approaches, we use an unsupervised approach. We iteratively learn the graph structure and the parameters of a $\mathsf{GNN}$ encoding the texts (text-to-graph) one sequence at a time while providing the supervision by decoding the graph into text (graph-to-text) and comparing the generated text to the input. We evaluate the approach by comparing the identified entities with annotated datasets, comparing the difference between the input and output texts, and comparing our generated graphs with those generated by state of the art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑