arXiv 1607.014322016-07cs.CL

Global Neural CCG Parsing with Optimality Guarantees

University of Washington（华盛顿大学）

Kenton Lee, Mike Lewis, Luke Zettlemoyer

英文摘要：

We introduce the first global recursive neural parsing model with optimality guarantees during decoding. To support global features, we give up dynamic programs and instead search directly in the space of all possible subtrees. Although this space is exponentially large in the sentence length, we show it is possible to learn an efficient A* parser. We augment existing parsing models, which have informative bounds on the outside score, with a global model that has loose bounds but only needs to model non-local phenomena. The global model is trained with a new objective that encourages the parser to explore a tiny fraction of the search space. The approach is applied to CCG parsing, improving state-of-the-art accuracy by 0.4 F1. The parser finds the optimal parse for 99.9% of held-out sentences, exploring on average only 190 subtrees.

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

A* CCG Parsing with a Supertag and Dependency Factored Model

Graduate School of Information and Science（信息与科学研究生院）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）

We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the precomputation of all probabilities and runs very efficiently, while modeling sentence structures explicitly via dependencies. Our model achieves the state-of-the-art results on English and Japanese CCG parsing.

2017-04-23cs.CL

Something Old, Something New: Grammar-based CCG Parsing with Transformer Models

Cambridge Quantum Computing（剑桥量子计算）

This report describes the parsing problem for Combinatory Categorial Grammar (CCG), showing how a combination of Transformer-based neural models and a symbolic CCG grammar can lead to substantial gains over existing approaches. The report also documents a 20-year research program, showing how NLP methods have evolved over this time. The staggering accuracy improvements provided by neural models for CCG parsing can be seen as a reflection of the improvements seen in NLP more generally. The report provides a minimal introduction to CCG and CCG parsing, with many pointers to the relevant literatu…

2021-09-28cs.CL

On the Complexity of CCG Parsing

Linköping University（林雪平大学）；University of Padua（帕多瓦大学）

We study the parsing complexity of Combinatory Categorial Grammar (CCG) in the formalism of Vijay-Shanker and Weir (1994). As our main result, we prove that any parsing algorithm for this formalism will take in the worst case exponential time when the size of the grammar, and not only the length of the input sentence, is included in the analysis. This sets the formalism of Vijay-Shanker and Weir (1994) apart from weakly equivalent formalisms such as Tree-Adjoining Grammar (TAG), for which parsing can be performed in time polynomial in the combined size of grammar and input sentence. Our result…

2018-05-04cs.CL

CCG Parsing and Multiword Expressions

University of Edinburgh（爱丁堡大学）

This thesis presents a study about the integration of information about Multiword Expressions (MWEs) into parsing with Combinatory Categorial Grammar (CCG). We build on previous work which has shown the benefit of adding information about MWEs to syntactic parsing by implementing a similar pipeline with CCG parsing. More specifically, we collapse MWEs to one token in training and test data in CCGbank, a corpus which contains sentences annotated with CCG derivations. Our collapsing algorithm however can only deal with MWEs when they form a constituent in the data which is one of the limitations…

2015-05-17cs.CL

Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning

Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Ochanomizu University（御茶之水女子大学）；Artificial Intelligence Research Center, AIST（日本产业技术综合研究所人工智能研究中心）

In formal logic-based approaches to Recognizing Textual Entailment (RTE), a Combinatory Categorial Grammar (CCG) parser is used to parse input premises and hypotheses to obtain their logical formulas. Here, it is important that the parser processes the sentences consistently; failing to recognize a similar syntactic structure results in inconsistent predicate argument structures among them, in which case the succeeding theorem proving is doomed to failure. In this work, we present a simple method to extend an existing CCG parser to parse a set of sentences consistently, which is achieved with …

2018-04-19cs.CL

An Improved Approach for Semantic Graph Composition with CCG

Georgetown University（乔治城大学）

This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysi…

2019-04-10cs.CL

更多相关论文收起更多论文

用CCG解析和大语言模型建模大脑中的结构构建

Modeling structure-building in the brain with CCG parsing and large language models

本文比较了CCG与CFG在fMRI神经信号上的建模效果，发现CCG的结构构建测量在左侧后颞叶对神经信号的拟合优于CFG，且该效应与可预测性效应在空间上可分离。

2023-04-16cs.CL

Evaluating Induced CCG Parsers on Grounded Semantic Parsing

University of Southern California（南加州大学）；University of Edinburgh（爱丁堡大学）；Google（谷歌）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

We compare the effectiveness of four different syntactic CCG parsers for a semantic slot-filling task to explore how much syntactic supervision is required for downstream semantic analysis. This extrinsic, task-based evaluation provides a unique window to explore the strengths and weaknesses of semantics captured by unsupervised grammar induction systems. We release a new Freebase semantic parsing dataset called SPADES (Semantic PArsing of DEclarative Sentences) containing 93K cloze-style questions paired with answers. We evaluate all our models on this dataset. Our code and data are available…

2017-01-31cs.AIcs.CL

Automatic Generation of High Quality CCGbanks for Parser Domain Adaptation

Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）；Ochanomizu University（御茶水女子大学）

We propose a new domain adaptation method for Combinatory Categorial Grammar (CCG) parsing, based on the idea of automatic generation of CCG corpora exploiting cheaper resources of dependency trees. Our solution is conceptually simple, and not relying on a specific parser architecture, making it applicable to the current best-performing parsers. We conduct extensive parsing experiments with detailed discussion; on top of existing benchmark datasets on (1) biomedical texts and (2) question sentences, we create experimental datasets of (3) speech conversation and (4) math problems. When applied …

2019-06-05cs.CL

用答案集编程解析组合范畴语法：初步报告

Parsing Combinatory Categorial Grammar with Answer Set Programming: Preliminary Report

University of Kentucky（肯塔基大学）；Technische Universität Wien（维也纳工业大学）

组合范畴语法（CCG）是一种用于自然语言分析的语法形式。CCG将结构化的词汇类别分配给单词，并使用一小组组合规则来组合这些类别以解析句子。在这项工作中，我们提出并实现了一种新的CCG解析方法，该方法依赖于突出的知识表示形式主义，即答案集编程（ASP）--一种声明性编程范式。我们制定的CCG解析的任务作为一个规划问题，并使用ASP计算工具来计算解决方案，对应于有效的解析。与其他方法相比，不需要使用这种声明性方法实现特定的解析算法。我们的方法旨在为一个给定的句子产生所有语义不同的解析树。从这一目标出发，出现了规范化和效率问题，我们通过结合和扩展现有战略来处理这些问题。我们已经实现了一个CCG解析工具包- AspCcgTk -使用ASP作为其主要的计算手段。C&C supertagger可以用作AspCcgTk中的预处理器，这使我们能够实现广泛覆盖的自然语言解析。

2011-08-29cs.AIcs.CL

Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks

University of Washington（华盛顿大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）

Supertagging is conventionally regarded as an important task for combinatory categorial grammar (CCG) parsing, where effective modeling of contextual information is highly important to this task. However, existing studies have made limited efforts to leverage contextual features except for applying powerful encoders (e.g., bi-LSTM). In this paper, we propose attentive graph convolutional networks to enhance neural CCG supertagging through a novel solution of leveraging contextual information. Specifically, we build the graph from chunks (n-grams) extracted from a lexicon and apply attention ov…

2020-11-18cs.CL

Type-Driven Incremental Semantic Parsing with Polymorphism

City University of New York（纽约市立大学）

Semantic parsing has made significant progress, but most current semantic parsers are extremely slow (CKY-based) and rather primitive in representation. We introduce three new techniques to tackle these problems. First, we design the first linear-time incremental shift-reduce-style semantic parsing algorithm which is more efficient than conventional cubic-time bottom-up semantic parsers. Second, our parser, being type-driven instead of syntax-driven, uses type-checking to decide the direction of reduction, which eliminates the need for a syntactic grammar such as CCG. Third, to fully exploit t…

2014-12-16cs.CL

一个基于心理语言学的CCG句法分析器

A Psycholinguistically Motivated Parser for CCG

考虑到人类解决句法歧义的速度，以及通过选择解释最“明智”的分析来解决句法歧义的压倒性证据，人们得出结论，解释，因此解析是递增的，几乎每个词都是如此。考虑到句法处理器理论中的简约性，人们开始探索最简单的分析器：它只表示语法定义的分析，而不表示其他信息。为了实现这一目标的一个简单的，增量解析器，我探讨的建议，能力语法是一个组合范畴语法（CCG）。我解决的问题，增殖分析，源于CCG的关联性的推导。我的解决方案包括只维护最大增量分析，并在必要时计算最大右分支分析。我使用重写系统的研究结果表明，这种计算是有效的。

1994-06-20cmp-lgcs.CL

A Survey on Semantic Parsing from the perspective of Compositionality

Indian Institute of Technology Delhi（印度理工学院德里分校）

Different from previous surveys in semantic parsing (Kamath and Das, 2018) and knowledge base question answering(KBQA)(Chakraborty et al., 2019; Zhu et al., 2019; Hoffner et al., 2017) we try to takes a different perspective on the study of semantic parsing. Specifically, we will focus on (a)meaning composition from syntactical structure(Partee, 1975), and (b) the ability of semantic parsers to handle lexical variation given the context of a knowledge base (KB). In the following section after an introduction of the field of semantic parsing and its uses in KBQA, we will describe meaning repres…

2020-09-29cs.CL

将超标签特征集成到神经非连续成分句法分析中

Integrating Supertag Features into Neural Discontinuous Constituent Parsing

Philosophische Fakultät（哲学系）；Institut für Sprache und Information（语言与信息研究所）

本研究探索将超标签特征集成到基于转移的神经非连续成分句法分析中，通过流水线和多任务两种方式引入超标签信息，并对比多种框架与序列标注任务作为辅助任务的适用性。

2024-10-11cs.AIcs.CLcs.FL

英语和法语中的音节分析

Syllable parsing in English and French

在本文中，我认为，优选理论提供了一个解释模型的音节分析在英语和法语。这一论点是基于心理语言学的事实，这些事实至今仍是个谜。这一论点进一步支持了计算实现这里开发。这种模式之所以重要，有几个原因。首先，它演示了如何在性能域中使用OT。第二，提出了音系学理论与心理语言学之间的新关系。(Code在Perl中包含，并且WWW接口在http://mayo.douglass.arizona.edu上运行。）

1995-06-02cmp-lgcs.CL

无需手写规则的SLOG结构泛化

Structural Generalization on SLOG without Hand-Written Rules

Saarland University（萨尔兰大学）

本文提出无需手写规则的结构泛化方法，基于神经细胞自动机，在SLOG基准上实现67.3%的准确率，优于AM-Parser，揭示结构泛化与CCG方向类型的关系。

2026-08-18cs.AIcs.CL