paper-with-me

Papers

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Event extraction is typically modeled as a multi-class classification problem where both event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We propose a novel event extraction framework that takes both event types and argument roles as natural language queries to extract candidate triggers and arguments from the input text. With the rich semantics in the queries, our framework benefits from the attention mechanisms to better capture the semantic correlation between the event types or argument roles and the input text. Furthermore, the query-and-extract formulation allows our approach to leverage all available event annotations from various ontologies as a unified model. Experiments on two public benchmark datasets, ACE and ERE, demonstrate that our approach achieves the state-of-the-art performance on each dataset and significantly outperforms existing methods on zero-shot event extraction. We will make all the programs publicly available once the paper is accepted.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Event ExtractionMulti-class ClassificationNatural Language QueriesVocal Bursts Type PredictionZero-shot Event Extraction

Similar Papers 제목 키워드 기반

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding

2021-10-14 · Findings (ACL) 2022 5 · Sijia Wang, Mo Yu, Shiyu Chang, Lichao Sun 외

Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols. These approaches are usually limited to a set of pre-defined types. We pro…

Event ExtractionMulti-class ClassificationNatural Language QueriesVocal Bursts Type Prediction+1

Towards Few-Shot Event Mention Retrieval: An Evaluation Framework and A Siamese Network Approach

2020-05-01 · LREC 2020 5 · Bonan Min, Yee Seng Chan, Lingjun Zhao

Automatically analyzing events in a large amount of text is crucial for situation awareness and decision making. Previous approaches treat event extraction as {``}one size fits all{''} with an ontology defined a priori. …

Decision MakingEvent ExtractionRetrieval

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

2020-10-21 · Rui Feng, Jie Yuan, Chao Zhang

We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervi…

Event DetectionEvent ExtractionNatural Language InferenceReading Comprehension

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples

2026-06-03 · Mengao Zhang, Xiang Yang, Chang Liu, Tianhui Tan 외 arxiv

Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimi…

Question Answering

Joint Modeling for Query Expansion and Information Extraction with Reinforcement Learning

2018-11-01 · WS 2018 11 · Motoki Taniguchi, Yasuhide Miura, Tomoko Ohkuma

Information extraction about an event can be improved by incorporating external evidence. In this study, we propose a joint model for pseudo-relevance feedback based query expansion and information extraction with reinfo…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1