arXiv 1804.079762018-04cs.CL

Neural-Davidsonian Semantic Proto-role Labeling

Rachel Rudinger, Adam Teichert, Ryan Culkin, Sheng Zhang, Benjamin Van Durme

备注：: Accepted to EMNLP 2018; errata corrected in Appendix Tables 7 and 8

英文摘要：

We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call "Neural-Davidsonian": predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence. We demonstrate: (1) state-of-the-art results in SPRL, and (2) that our network naturally shares parameters between attributes, allowing for learning new attribute types with limited added supervision.

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

An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling

Leibniz ScienceCampus “Empirical Linguistics and Computational Language Modeling”（莱布尼茨科学园区“实证语言学与计算语言建模”）

Semantic proto-role labeling (SPRL) is an alternative to semantic role labeling (SRL) that moves beyond a categorical definition of roles, following Dowty's feature-based view of proto-roles. This theory determines agenthood vs. patienthood based on a participant's instantiation of more or less typical agent vs. patient properties, such as, for example, volition in an event. To perform SPRL, we develop an ensemble of hierarchical models with self-attention and concurrently learned predicate-argument-markers. Our method is competitive with the state-of-the art, overall outperforming previous wo…

2019-04-12cs.CL

Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling

Columbia University（哥伦比亚大学）；University of Gothenburg（哥德堡大学）；University of Washington（华盛顿大学）

We put forward an end-to-end multi-step machine learning model which jointly labels semantic roles and the proto-roles of Dowty (1991), given a sentence and the predicates therein. Our best architecture first learns argument spans followed by learning the argument's syntactic heads. This information is shared with the next steps for predicting the semantic roles and proto-roles. We also experiment with transfer learning from argument and head prediction to role and proto-role labeling. We compare using static and contextual embeddings for words, arguments, and sentences. Unlike previous work, …

2022-10-13cs.CL

通过分层架构耦合局部上下文和全局语义原型以实现修辞角色标注

Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling

Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004（南特大学，中央理工学院，CNRS，LS2N，UMR 6004）；University of Lorraine（洛林大学）

本文提出两种基于原型的方法，结合局部上下文和全局语义，通过SCOTUS-Law数据集验证在法律、医学和科学领域修辞角色标注任务中的有效性。

2026-03-04cs.CL

关注你的邻居：利用类比实例进行法律文书的修辞角色标注

Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents

School of Computation, Information, and Technology（计算、信息与技术学院）；Technical University of Munich（慕尼黑工业大学）

本文针对法律判决书修辞角色标注中标注数据有限和标签不平衡等挑战，提出利用语义相似邻居实例的推理插值与原型对比学习方法，显著提升宏观F1并验证了跨法律领域的迁移能力。

2024-03-31cs.CL

Computational linking theory

Johns Hopkins University（约翰斯·霍普金斯大学）

A linking theory explains how verbs' semantic arguments are mapped to their syntactic arguments---the inverse of the Semantic Role Labeling task from the shallow semantic parsing literature. In this paper, we develop the Computational Linking Theory framework as a method for implementing and testing linking theories proposed in the theoretical literature. We deploy this framework to assess two cross-cutting types of linking theory: local v. global models and categorical v. featural models. To further investigate the behavior of these models, we develop a measurement model in the spirit of prev…

2016-10-08cs.CL