A Sequence-to-Sequence Model for Semantic Role Labeling

机译：语义角色标记的序列到序列模型

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We explore a novel approach for Semantic Role Labeling (SRL) by casting it as a sequence-to-sequence process. We employ an attention-based model enriched with a copying mechanism to ensure faithful regeneration of the input sequence, while enabling interleaved generation of argument role labels. Here, we apply this model in a monolingual setting, performing PropBank SRL on English language data. The constrained sequence generation set-up enforced with the copying mechanism allows us to analyze the performance and special properties of the model on manually labeled data and benchmarking against state-of-the-art sequence labeling models. We show that our model is able to solve the SRL argument labeling task on English data, yet further structural decoding constraints will need to be added to make the model truly competitive. Our work represents a first step towards more advanced, generative SRL labeling setups.

机译：我们通过将语义角色标记（SRL）转换为序列到序列过程，探索了一种新颖的方法。我们采用了基于注意力的模型，该模型带有复制机制，可确保输入序列的真实再生，同时能够交错生成论点角色标签。在这里，我们以单语设置应用该模型，对英语数据执行PropBank SRL。通过复制机制执行的受限序列生成设置使我们能够分析模型在手动标记数据上的性能和特殊属性，并根据最新的序列标记模型进行基准测试。我们证明了我们的模型能够解决英文数据上的SRL参数标注任务，但是还需要添加更多的结构解码约束以使模型真正具有竞争力。我们的工作代表了朝着更高级的，生成性SRL标签设置迈出的第一步。

著录项

来源
《3rd workshop on representation learning for NLP 2018》|2018年|207-216|共10页
会议地点 Melbourne(AU)
作者
Angel Daza; Anette Frank;
展开▼
作者单位

Leibniz ScienceCampus "Empirical Linguistics and Computational Language Modeling" Department of Computational Linguistics Heidelberg University 69120 Heidelberg, Germany;

Leibniz ScienceCampus "Empirical Linguistics and Computational Language Modeling" Department of Computational Linguistics Heidelberg University 69120 Heidelberg, Germany;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Character-Level Syntax Infusion in Pre-Trained Models for Chinese Semantic Role Labeling [J] . Wang Yuxuan, Lei Zhilin, Che Wanxiang International journal of machine learning and cybernetics . 2021,第12期

机译：用于中文语义角色标记的预训练模型中的字符级语法输注
2. Improvement of Prosody Modeling Using Semantic Role Labeling, Hybrid Feature Selection and BPSO-PSO-Optimized RNN [J] . Sheikhan Mansour National Academy Science Letters . 2017,第3期

机译：使用语义作用标记，混合特征选择和BPSO-PSO优化的RNN改进韵律建模
3. Jointly Part-of-Speech Tagging and Semantic Role Labeling Using Auxiliary Deep Neural Network Model [J] . Yatian Shen, Yubo Mai, Xiajiong Shen, Computers, Materials & Continua . 2020,第1期

机译：使用辅助深神经网络模型联合言语标记和语义角色标记
4. A Sequence-to-Sequence Model for Semantic Role Labeling [C] . Angel Daza, Anette Frank Annual meeting of the Association for Computational Linguistics . 2018

机译：语义角色标记的序列到序列模型
5. Neural Models for Large-Scale Semantic Role Labelling [D] . FitzGerald, Nicholas. 2018

机译：大规模语义角色标记的神经模型
6. BIOSMILE: A semantic role labeling system for biomedical verbs using a maximum-entropy model with automatically generated template features [O] . Richard Tzong-Han Tsai, Wen-Chi Chou, Ying-Shan Su, 2007

机译：BIOSMILE：生物医学动词的语义角色标记系统使用具有最大熵模型和自动生成的模板特征的生物医学动词
7. A Sequence-to-Sequence Model for Semantic Role Labeling [O] . Angel Daza, Anette Frank 2018

机译：语义角色标记的序列到序列模型

A Sequence-to-Sequence Model for Semantic Role Labeling

摘要

著录项

相似文献

相关主题

期刊订阅