arXiv 1808.048652018-08-14cs.CL

Top-Down Tree Structured Text Generation

Fudan University（复旦大学）；New York University Shanghai（上海纽约大学）

Qipeng Guo, Xipeng Qiu, Xiangyang Xue, Zheng Zhang

英文摘要：

Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures. This paper advocates a simple approach that treats sentence generation as a tree-generation task. By explicitly modelling syntactic structures in a constituent syntactic tree and performing top-down, breadth-first tree generation, our model fixes dependencies appropriately and performs implicit global planning. This is in contrast to transition-based depth-first generation process, which has difficulty dealing with incomplete texts when parsing and also does not incorporate future contexts in planning. Our preliminary results on two generation tasks and one parsing task demonstrate that this is an effective strategy.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

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。

继续探索

相关论文

Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance

The University of Tokyo（东京大学）；RIKEN（理化学研究所）；University of Liverpool（利物浦大学）

This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys generic content, and the leaf sentences describe specific topics. Expe…

2021-06-15cs.AIcs.CLcs.LG

让烹饪失败：用于结构化食谱生成的拓扑最优传输

Losses that Cook: Topological Optimal Transport for Structured Recipe Generation

Trustpilot；Politecnico di Torino（托里诺理工学院）

本文提出拓扑损失用于生成结构化食谱，提升食材和步骤的准确性，同时改进时间与温度的精确度，实验表明模型在多个指标上表现优异。

2026-04-16cs.AIcs.CL

Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing

Simon Fraser University（西蒙弗雷泽大学）

The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure. We exploit a top-down tree-structured model called DRNN (Doubly-Recurrent Neural Networks) first proposed by Alvarez-Melis and Jaakola (2017) to create an NMT model called Seq2DRNN that combines a sequential encoder with tree-structured decoding augmented with a syntax-aware attention model. Unlike previous approaches to syntax-based NMT which use dependency…

2018-09-06cs.CL

Generating Summaries with Topic Templates and Structured Convolutional Decoders

Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）

Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.

2019-06-11cs.CL

LexGenie：面向欧洲人权法院判例法的结构化报告自动生成

LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law

School of Computation, Information, and Technology（计算、信息与技术学院；慕尼黑工业大学）；Technical University of Munich（国际与发展研究研究生院）；Graduate Institute of International and Development Studies

针对法律判例多案件结构化报告自动生成的空白，提出基于LLM的自动化流水线LexGenie，通过检索、聚类和组织相关段落生成欧洲人权法院判例法的结构化报告，专家评估证明其能有效提升法律分析效率与可扩展性。

2025-03-05cs.CL

Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats

Microsoft Corporation（微软公司）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；University of Maryland（马里兰大学）

Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentation often focus on segmentation of structured texts. In this paper, we comprehensively analyze the generalization capabilities of state-of-the-art topic segmentation models on unstructured texts. We find that: (a) Current strategies of pre-training on a large corpus of structured text such as Wiki-727K do not help in transferability to unstructured texts. (b) …

2022-11-27cs.AIcs.CL

更多相关论文收起更多论文

最简文法的概率自顶向下分析器

A probabilistic top-down parser for minimalist grammars

UCLA（加州大学洛杉矶分校）；ENS（巴黎高等师范学院）

本文描述了一个概率自顶向下的最简文法分析器。自顶向下的解析器有一个很大的优势，在解析过程中有一定的预测能力，这发生在一个从左到右阅读的句子。这样的解析器已经在上下文无关文法的情况下得到了很好的实现和研究，它已经是自上而下的，但这些很难适应自下而上生成句子的极简主义文法。我在这里提出了一种重写最简文法作为线性上下文无关重写系统的方法，允许轻松地创建自顶向下的解析器。这种重写还允许在这些语法上放置概率字段，这可以用于加速解析器。最后，我提出了一种方法，通过使用数据压缩中使用的算法来细化概率场。

2010-10-09cs.CL

高效的概率自顶向下和左角分析

Efficient probabilistic top-down and left-corner parsing

本文探讨了高效的预测广泛覆盖的分析，没有动态规划。与自下而上的方法不同，深度优先自上而下的解析产生的部分解析是跨越整个左上下文的完全连接的树，原则上可以从中读取任何类型的非局部依赖或部分语义解释。我们对比了两种预测分析方法，自顶向下和左角分析，并发现两者都是可行的。此外，我们发现，增强与非本地信息不仅提高了解析器的准确性，但也大大提高了搜索效率。

2000-08-21cs.CL

Top-down Discourse Parsing via Sequence Labelling

School of Computing and Information Systems（计算与信息系统学院）；The University of Melbourne（墨尔本大学）

We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space for splitting points. We explore both traditional recurrent models and modern pre-trained transformer models for the task, and additionally introduce a novel dynamic oracle for top-down parsing. Based on the Full metric, our proposed LSTM model se…

2021-04-05cs.CL

自顶向下语法分析的记忆化

Memoization of Top Down Parsing

本文讨论了自上而下记忆识别器和图表分析器之间的关系。它提出了一个版本的memoization适合于连续传递风格的程序。当应用于自顶向下识别器的简单形式化时，它会产生一个终止解析器。

1995-04-25cmp-lgcs.CL

使用语言模型对半结构化和非结构化对话数据集进行主题分割

Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models

Microsoft Corp.（微软公司）；University Of Massachusetts（马萨诸塞大学）；University of Maryland（马里兰大学）

本文研究非结构化对话的主题分割，发现结构化文本预训练迁移效果有限，而使用目标领域小数据集从头训练并采用 Focal Loss 能显著提升分割性能。

2023-10-26cs.AIcs.CLcs.LG

基于统一系统的自顶向下约束最大化

Maximizing Top-down Constraints for Unification-based Systems

一个左上角的解析算法与自顶向下过滤已被报道，以显示非常有效的性能为基础的统一系统。然而，由于左递归语法分析的不终止性，自顶向下的约束必须被削弱。本文提出了一种最大化自顶向下约束的一般方法。该方法提供了一个程序来动态计算 * 限制器 *，一个最小的功能集，参与一个无限循环的每个传播路径，从而自上而下的约束最大限度地传播。

1996-06-20cmp-lgcs.CL

大规模半结构化文档的标签加权主题模型

Tag-Weighted Topic Model For Large-scale Semi-Structured Documents

到目前为止，在互联网的发展过程中已经出现了大量的半结构化文档（SSD）。这些SSD包含非结构化功能（例如，纯文本）和元数据（例如，标签）。以往的工作主要集中在非结构化文本的建模，最近，已经提出了一些其他的方法来建模的非结构化文本与特定的标签。建立一个通用的SSD模型仍然是一个重要的问题，无论是模型的适应性和效率。我们提出了一种新的方法来建模的SSD的所谓的标签加权主题模型（TWTM）。TWTM是一个利用标签和单词信息的框架，不仅可以学习文档主题和主题词分布，还可以推断文本挖掘任务的标签主题分布。我们提出了一个有效的变分推理方法与EM算法估计模型参数。同时，在MapReduce分布式计算平台下，提出了三种大规模SSD建模方案。实验结果表明，该模型的有效性，效率和鲁棒性，通过比较与国家的最先进的方法在文档建模，标签预测和文本分类。我们还展示了三种分布式解决方案在文档建模的时间和准确性方面的性能。

2015-07-30cs.CLcs.IRcs.LG

Attentive Tree-structured Network for Monotonicity Reasoning

Rose-Hulman Institute of Technology（罗斯-霍曼理工学院）

Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based long-short-term-memory network (Tree-LSTM) with soft attention. It is designed to model the syntactic parse tree information from the sentence pair of a reasoning task. A self-attentive aggregator is used for aligning the representations of the premise and the hypothesis. We present our model and evaluate it using the Monotonicity Entailment Dataset (MED). We show and attempt …

2021-01-03cs.AIcs.CL