Query and Extract: Refining Event Extraction as Type-oriented Binary
Decoding
- URL: http://arxiv.org/abs/2110.07476v1
- Date: Thu, 14 Oct 2021 15:49:40 GMT
- Title: Query and Extract: Refining Event Extraction as Type-oriented Binary
Decoding
- Authors: Sijia Wang, Mo Yu, Shiyu Chang, Lichao Sun, Lifu Huang
- Abstract summary: We propose a novel event extraction framework that takes event types and argument roles as natural language 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.
- Score: 51.57864297948228
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 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 benchmarks, ACE and ERE, demonstrate that our approach achieves
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.
Related papers
- Open Relation and Event Type Discovery with Type Abstraction [80.92395639632383]
We introduce the idea of type abstraction, where the model is prompted to generalize and name the type.
We use the similarity between inferred names to induce clusters.
Our experiments on multiple relation extraction and extraction event datasets consistently show the advantage of our type abstraction approach.
arXiv Detail & Related papers (2022-11-30T23:47:49Z) - Zero-Shot On-the-Fly Event Schema Induction [61.91468909200566]
We present a new approach in which large language models are utilized to generate source documents that allow predicting, given a high-level event definition, the specific events, arguments, and relations between them.
Using our model, complete schemas on any topic can be generated on-the-fly without any manual data collection, i.e., in a zero-shot manner.
arXiv Detail & Related papers (2022-10-12T14:37:00Z) - PILED: An Identify-and-Localize Framework for Few-Shot Event Detection [79.66042333016478]
In our study, we employ cloze prompts to elicit event-related knowledge from pretrained language models.
We minimize the number of type-specific parameters, enabling our model to quickly adapt to event detection tasks for new types.
arXiv Detail & Related papers (2022-02-15T18:01:39Z) - Corpus-based Open-Domain Event Type Induction [78.76531329136708]
This work presents a corpus-based open-domain event type induction method.
We represent each event type as a cluster of predicate sense, object head> pairs.
Our experiments, on three datasets from different domains, show our method can discover salient and high-quality event types.
arXiv Detail & Related papers (2021-09-07T20:42:44Z) - Event Extraction by Associating Event Types and Argument Roles [26.877240015683636]
Event extraction (EE) can be divided into two sub-tasks: event type classification and element extraction.
This paper proposes a novel neural association framework for the EE task.
Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks.
arXiv Detail & Related papers (2021-08-23T10:09:39Z) - Unsupervised Label-aware Event Trigger and Argument Classification [73.86358632937372]
We propose an unsupervised event extraction pipeline, which first identifies events with available tools (e.g., SRL) and then automatically maps them to pre-defined event types.
We leverage pre-trained language models to contextually represent pre-defined types for both event triggers and arguments.
We successfully map 83% of the triggers and 54% of the arguments to the correct types, almost doubling the performance of previous zero-shot approaches.
arXiv Detail & Related papers (2020-12-30T17:47:24Z) - Probing and Fine-tuning Reading Comprehension Models for Few-shot Event
Extraction [17.548548562222766]
We propose a reading comprehension framework for event extraction.
By constructing proper query templates, our approach can effectively distill rich knowledge about tasks and label semantics.
Our method achieves state-of-the-art performance on the ACE 2005 benchmark when trained with full supervision.
arXiv Detail & Related papers (2020-10-21T21:48:39Z)
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.