Decomposing and Recomposing Event Structure

• URL: http://arxiv.org/abs/2103.10387v1
• Date: Thu, 18 Mar 2021 17:16:43 GMT
• Title: Decomposing and Recomposing Event Structure
• Authors: William Gantt, Lelia Glass, and Aaron Steven White
• Abstract summary: We induce this jointly with role, entity type and event-level semantic graphs. We identify sets of types that align closely with previous theoretically-motivated document-level generative models.
• Score: 4.270553193574436
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present an event structure ontology empirically derived from inferential properties annotated on sentence- and document-level semantic graphs. We induce this ontology jointly with semantic role, entity type, and event-event relation ontologies using a document-level generative model, identifying sets of types that align closely with previous theoretically-motivated taxonomies.

Related papers

• An Encoding of Abstract Dialectical Frameworks into Higher-Order Logic [57.24311218570012]
  This approach allows for the computer-assisted analysis of abstract dialectical frameworks. Exemplary applications include the formal analysis and verification of meta-theoretical properties.
  arXiv  Detail & Related papers  (2023-12-08T09:32:26Z)
• Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization [11.168330694255404]
  This paper introduces the 'RSTformer', a novel summarization model that comprehensively incorporates both the types and uncertainty of rhetorical relations. Our RST-attention mechanism, rooted in document-level rhetorical structure, is an extension of the recently devised Longformer framework.
  arXiv  Detail & Related papers  (2023-05-26T09:51:47Z)
• Semantic Structure Enhanced Event Causality Identification [57.26259734944247]
  Event Causality Identification (ECI) aims to identify causal relations between events in unstructured texts. Existing methods underestimate two kinds of semantic structures vital to the ECI task, namely, event-centric structure and event-associated structure.
  arXiv  Detail & Related papers  (2023-05-22T07:42:35Z)
• Recognizing Entity Types via Properties [5.622134113488239]
  We introduce a property-based approach that allows recognizing etypes on the basis of the properties used to define them. The main contribution consists of a set of property-based metrics measuring the similarity between etypes and entities, and a machine learning algorithm exploiting the proposed similarity metrics.
  arXiv  Detail & Related papers  (2023-04-16T22:42:30Z)
• Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding [143.5927158318524]
  Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. We introduce a new Compositional Temporal Grounding task and construct two new dataset splits. We argue that the inherent structured semantics inside the videos and language is the crucial factor to achieve compositional generalization.
  arXiv  Detail & Related papers  (2023-01-22T08:02:23Z)
• Semantically-informed Hierarchical Event Modeling [14.00844847268286]
  We present a novel, doubly hierarchical, semi-supervised event modeling framework. Our approach consists of multiple layers of structured latent variables, where each successive layer compresses and abstracts the previous layers. We demonstrate that our approach is able to out-perform the previous state-of-the-art approaches by up to 8.5%.
  arXiv  Detail & Related papers  (2022-12-20T18:51:23Z)
• Knowledge-Aware Bayesian Deep Topic Model [50.58975785318575]
  We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling. Our proposed model efficiently integrates the prior knowledge and improves both hierarchical topic discovery and document representation.
  arXiv  Detail & Related papers  (2022-09-20T09:16:05Z)
• Improve Discourse Dependency Parsing with Contextualized Representations [28.916249926065273]
  We propose to take advantage of transformers to encode contextualized representations of units of different levels. Motivated by the observation of writing patterns commonly shared across articles, we propose a novel method that treats discourse relation identification as a sequence labelling task.
  arXiv  Detail & Related papers  (2022-05-04T14:35:38Z)
• Document Structure aware Relational Graph Convolutional Networks for Ontology Population [1.076210145983805]
  We look at the role of document structure in learning ontological relationships between concepts in any document corpus. Inspired by ideas from hypernym discovery and explainability, our method performs about 15 points more accurate than a stand-alone form of RCN model.
  arXiv  Detail & Related papers  (2021-04-27T02:50:39Z)
• Neural Deepfake Detection with Factual Structure of Text [78.30080218908849]
  We propose a graph-based model for deepfake detection of text. Our approach represents the factual structure of a given document as an entity graph. Our model can distinguish the difference in the factual structure between machine-generated text and human-written text.
  arXiv  Detail & Related papers  (2020-10-15T02:35:31Z)
• High-order Semantic Role Labeling [86.29371274587146]
  This paper introduces a high-order graph structure for the neural semantic role labeling model. It enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models.
  arXiv  Detail & Related papers  (2020-10-09T15:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.