Event GDR: Event-Centric Generative Document Retrieval
- URL: http://arxiv.org/abs/2405.06886v1
- Date: Sat, 11 May 2024 02:55:11 GMT
- Title: Event GDR: Event-Centric Generative Document Retrieval
- Authors: Yong Guan, Dingxiao Liu, Jinchen Ma, Hao Peng, Xiaozhi Wang, Lei Hou, Ru Li,
- Abstract summary: We propose Event GDR, an event-centric generative document retrieval model.
We employ events and relations to model the document to guarantee the comprehensiveness and inner-content correlation.
For identifier construction, we map the events to well-defined event taxonomy to construct the identifiers with explicit semantic structure.
- Score: 37.53593254200252
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1) neglecting inner-content correlation during document representation; (2) lacking explicit semantic structure during identifier construction. Nonetheless, events have enriched relations and well-defined taxonomy, which could facilitate addressing the above two challenges. Inspired by this, we propose Event GDR, an event-centric generative document retrieval model, integrating event knowledge into this task. Specifically, we utilize an exchange-then-reflection method based on multi-agents for event knowledge extraction. For document representation, we employ events and relations to model the document to guarantee the comprehensiveness and inner-content correlation. For identifier construction, we map the events to well-defined event taxonomy to construct the identifiers with explicit semantic structure. Our method achieves significant improvement over the baselines on two datasets, and also hopes to provide insights for future research.
Related papers
- Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information [33.21818213257603]
Cross-document event coreference resolution models can only compute mention similarity directly or enhance mention representation by extracting event arguments.
We propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents.
We have developed a large-scale Chinese cross-document event coreference dataset to fill this gap.
arXiv Detail & Related papers (2024-06-23T02:54:48Z) - 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) - CAPSTONE: Curriculum Sampling for Dense Retrieval with Document
Expansion [68.19934563919192]
We propose a curriculum sampling strategy that utilizes pseudo queries during training and progressively enhances the relevance between the generated query and the real query.
Experimental results on both in-domain and out-of-domain datasets demonstrate that our approach outperforms previous dense retrieval models.
arXiv Detail & Related papers (2022-12-18T15:57:46Z) - Cross-document Event Coreference Search: Task, Dataset and Modeling [26.36068336169796]
We propose an appealing, and often more applicable, complementary set up for the task - Cross-document Coreference Search.
To support research on this task, we create a corresponding dataset, which is derived from Wikipedia.
We present a novel model that integrates a powerful coreference scoring scheme into the DPR architecture, yielding improved performance.
arXiv Detail & Related papers (2022-10-23T08:21:25Z) - RAAT: Relation-Augmented Attention Transformer for Relation Modeling in
Document-Level Event Extraction [16.87868728956481]
We propose a new DEE framework which can model the relation dependencies, called Relation-augmented Document-level Event Extraction (ReDEE)
To further leverage relation information, we introduce a separate event relation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance.
arXiv Detail & Related papers (2022-06-07T15:11:42Z) - EA$^2$E: Improving Consistency with Event Awareness for Document-Level
Argument Extraction [52.43978926985928]
We introduce the Event-Aware Argument Extraction (EA$2$E) model with augmented context for training and inference.
Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$2$E.
arXiv Detail & Related papers (2022-05-30T04:33:51Z) - Augmenting Document Representations for Dense Retrieval with
Interpolation and Perturbation [49.940525611640346]
Document Augmentation for dense Retrieval (DAR) framework augments the representations of documents with their Dense Augmentation and perturbations.
We validate the performance of DAR on retrieval tasks with two benchmark datasets, showing that the proposed DAR significantly outperforms relevant baselines on the dense retrieval of both the labeled and unlabeled documents.
arXiv Detail & Related papers (2022-03-15T09:07:38Z) - Cross-document Event Identity via Dense Annotation [9.163142877146512]
We study the identity of textual events from different documents.
We propose a dense annotation approach for cross-document event coreference.
We present an open-access dataset for cross-document event coreference.
arXiv Detail & Related papers (2021-09-14T03:57:58Z) - Detecting Ongoing Events Using Contextual Word and Sentence Embeddings [110.83289076967895]
This paper introduces the Ongoing Event Detection (OED) task.
The goal is to detect ongoing event mentions only, as opposed to historical, future, hypothetical, or other forms or events that are neither fresh nor current.
Any application that needs to extract structured information about ongoing events from unstructured texts can take advantage of an OED system.
arXiv Detail & Related papers (2020-07-02T20:44:05Z)
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.