paper-with-me

Papers

Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs

2022-10-21 · Prafulla Kumar Choubey, Ruihong Huang

We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. Our key observation is that the functional roles of sentences used for profiling news discourse signify different time frames relevant to a news story and can, therefore, help to recover the global temporal structure of a document. Our analyses and experiments with the widely used knowledge distillation technique show that discourse profiling effectively identifies distant inter-sentence event and (or) time expression pairs that are temporally related and otherwise difficult to locate.

📄 PDF Abstract BibTeX arXiv:2210.11787

Code (1)

prafulla77/discourse_tdg_aacl2022 공식 구현 pytorch

Tasks

Knowledge DistillationSentence

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Combining Temporal Information and Topic Modeling for Cross-Document Event Ordering

2015-06-10 · Borja Navarro-Colorado, Estela Saquete

Building unified timelines from a collection of written news articles requires cross-document event coreference resolution and temporal relation extraction. In this paper we present an approach event coreference resoluti…

Articlescoreference-resolutionCoreference ResolutionEvent Coreference Resolution+2

Modeling Document-level Causal Structures for Event Causal Relation Identification

2019-06-01 · NAACL 2019 6 · Lei Gao, Prafulla Kumar Choubey, Ruihong Huang

We aim to comprehensively identify all the event causal relations in a document, both within a sentence and across sentences, which is important for reconstructing pivotal event structures. The challenges we identified a…

RelationSentence

Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification

2021-01-08 · Xiaonan Jing, Julia Taylor Rayz

Graph structures are powerful tools for modeling the relationships between textual elements. Graph-of-Words (GoW) has been adopted in many Natural Language tasks to encode the association between terms. However, GoW prov…

Word Embeddings

Real-time 3D human action recognition based on Hyperpoint sequence

2021-11-16 · Xing Li, Qian Huang, Zhijian Wang, Zhenjie Hou 외

Real-time 3D human action recognition has broad industrial applications, such as surveillance, human-computer interaction, and healthcare monitoring. By relying on complex spatio-temporal local encoding, most existing po…

3D Action RecognitionAction RecognitionTemporal Action Localization

TIMERS: Document-level Temporal Relation Extraction

2021-08-01 · ACL 2021 5 · Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu 외

We present TIMERS - a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language. Our proposed method leverages rhetorical discourse features and temporal argum…

RelationRelation ClassificationRelation ExtractionTemporal Relation Classification+1