Papers with sentence-level task

4 papers
Document-Level Event Argument Extraction by Conditional Generation (2021.naacl-main)

Copied to clipboard

Challenge: Existing event extraction models have been limited to the sentence level . this formulation signifies a misalignment between the information seeking behavior and the informative seeking behavior.
Approach: They propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates.
Outcome: The proposed model achieves 7.6% F1 and 5.7% F1 over the best baseline on the document-level event extraction dataset WikiEvents and 9.3% F1 on the informative argument extraction task.
Document-level Event Factuality Identification via Machine Reading Comprehension Frameworks with Transfer Learning (2022.coling-1)

Copied to clipboard

Challenge: Document-level Event Factuality Identification (DEFI) is a fundamental and crucial task in NLP.
Approach: They propose a framework for document-level event factuality identification (DEFI) they propose to use Span-Extraction and Multiple-Choice to model DEFI as machine reading comprehension tasks .
Outcome: The proposed model outperforms state-of-the-art models on a document-based event factuality task . it uses Span-Extraction (Ext) and Multiple-Choice (Mch) knowledge to extract knowledge from large-scale MRC corpus .
Reconsidering Sentence-Level Sign Language Translation (2024.emnlp-main)

Copied to clipboard

Challenge: Historically, sign language machine translation is framed as a sentence-level task . however, there are known intersentential dependencies that are impossible to resolve in isolation.
Approach: They propose a human baseline for sign language translation that substitutes a person into the machine learning task framing instead of providing the entire document as context.
Outcome: The proposed human baseline for sign language translation shows that deaf signers can only understand key parts of the clip in light of additional discourse-level context.
Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction (2023.acl-long)

Copied to clipboard

Challenge: Document-level Event Causality Identification (DECI) is a sentence-level task that requires long-text understanding.
Approach: They propose a document-level event causality identification model (SENDIR) that uses sparse attention to capture long-distance dependence.
Outcome: The proposed model can be used to discriminate between event pairs in the same sentence or span multiple sentences.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations