事件驱动的自动标题生成模型

200 浏览量更新于2024-08-29 收藏 179KB PDF 举报

"事件驱动的标题生成是自然语言处理领域的一种技术，主要应用于新闻标题的自动生成。该模型基于事件驱动的思路，通过识别输入文档中的关键事件链来生成具有概括性的标题。研究由Rui Sun、Yue Zhang、Meishan Zhang和Donghong Ji等人提出，分别来自武汉大学计算机学院和新加坡科技设计大学。在该模型中，系统首先通过提取一系列结构性事件来识别出文档的关键事件链，这些事件能够描述文档的主要内容。接着，采用一种创新的多句压缩算法，将提取到的事件融合，以此生成文档的标题。这种模型可以看作是提取式和抽象式标题生成方法的新型结合，它利用事件结构同时吸取两种方法的优点。标准的评估结果显示，相较于之前最先进的系统，该事件驱动模型的表现最佳。这表明在新闻标题生成任务中，基于事件的处理方式能更有效地捕捉文档核心，生成准确且有吸引力的标题。尽管论文摘要并未详细展开模型的具体实现细节和算法流程，但可以推断，该模型可能涉及到了事件检测、句子理解、信息压缩和文本生成等多个自然语言处理子任务。事件驱动的标题生成技术对于新闻自动化生产、信息摘要以及提高信息传播效率等方面具有重要意义。它能够减轻人工编辑的工作负担，同时保证生成标题的质量。随着深度学习和自然语言理解技术的不断发展，未来这一领域的研究有望进一步提升自动化标题生成的准确性和自然度，从而更好地服务于新闻媒体和信息检索领域。"

3 Our Model

Similar to extractive and abstractive models, the

proposed event-driven model consists of two

steps, namely candidate extraction and headline

generation.

3.1 Candidate Extraction

We exploit events as the basic units for candidate

extraction. Here an event is a tuple (S, P, O),

where S is the subject, P is the predicate and O is

the object. For example, for the sentence “Ukraine

Delays Announcement of New Government”, the

event is (Ukraine, Delays, Announcement). This

type of event structures has been used in open

information extraction (Fader et al., 2011), and has

a range of NLP applications (Ding et al., 2014; Ng

et al., 2014).

A sentence is a well-formed structure with

complete syntactic information, but can contain

redundant information for text summarization,

which makes sentences very sparse. Phrases can

be used to avoid the sparsity problem, but with

little syntactic information between phrases, ﬂuent

headline generation is difﬁcult. Events can be

regarded as a trade-off between sentences and

phrases. They are meaningful structures without

redundant components, less sparse than sentences

and containing more syntactic information than

phrases.

In our system, candidate event extraction is

performed on a bipartite graph, where the two

types of nodes are lexical chains (Section 3.1.2)

and events (Section 3.1.1), respectively. Mutual

Reinforcement Principle (Zha, 2002) is applied

to jointly learn chain and event salience on the

bipartite graph for a given input. We obtain the

top-k candidate events by their salience measures.

3.1.1 Extracting Events

We apply an open-domain event extraction

approach. Different from traditional event

extraction, for which types and arguments are pre-

deﬁned, open event extraction does not have a

closed set of entities and relations (Fader et al.,

2011). We follow Hu’s work (Hu et al., 2013) to

extract events.

Given a text, we ﬁrst use the Stanford

dependency parser

to obtain the Stanford typed

dependency structures of the sentences (Marneffe

and Manning, 2008). Then we focus on

http://nlp.stanford.edu/software/lex-parser.shtml

DT NNPS MD VB DT NNP NNP POS NNS

the Keenans could demand the Aryan Nations ’ assets

nsubj

aux

dobj

det nn

poss

Figure 2: Dependency tree for the sentence

“the Keenans could demand the Aryan Nations’

assets”.

two relations, nsubj and dobj, for extracting

event arguments. Event arguments that have

the same predicate are merged into one event,

represented by tuple (Subject, Predicate, Object).

For example, given the sentence, “the Keenans

could demand the Aryan Nations’ assets”, Figure

2 present its partial parsing tree. Based

on the parsing results, two event arguments

are obtained: nsubj(demand, Keenans) and

dobj(demand, assets). The two event arguments

are merged into one event: (Keenans, demand,

assets).

3.1.2 Extracting Lexical Chains

Lexical chains are used to link semantically-

related words and phrases (Morris and Hirst, 1991;

Barzilay and Elhadad, 1997). A lexical chain is

analogous to a semantic synset. Compared with

words, lexical chains are less sparse for event

ranking.

Given a text, we follow Boudin and Morin

(2013) to construct lexical chains based on the

following principles:

1. All words that are identical after stemming

are treated as one word;

2. All NPs with the same head word fall into one

lexical chain;

3. A pronoun is added to the corresponding

lexical chain if it refers to a word in the chain

(The coreference resolution is performed

using the Stanford Coreference Resolution

system);

4. Lexical chains are merged if their main words

are in the same synset of WordNet.

NPs are extracted according to the dependency relations

nn and amod. As shown in Figure 2, we can extract the noun

phrase Aryan Nations according to the dependency relation

nn(Nations, Aryan).

http://nlp.stanford.edu/software/dcoref.shtml

http://wordnet.princeton.edu/

464

剩余10页未读，继续阅读

weixin_38743076

粉丝: 7
资源: 925

事件驱动的自动标题生成模型

基于深度学习的标题生成方法综述.pdf

易语言事件代码自动生成器源码

事件驱动的新闻标题生成模型

显著事件驱动的高效标题生成模型

利用Hawkes流程进行多事件驱动的情感动态生成

windriver--多种总线板卡驱动函数生成工具！

NUnitTestGenerator:一种从测试标题生成NUnit测试夹具的工具，可从逻辑上生成样板代码

ST电机驱动代码生成工具最新版发布

Linux内核驱动解析：事件管理器与设备文件生成

S7-400 CPU模块驱动程序生成教程：CFC V5.2 SP1指南

最新资源