Efficient Zero-shot Event Extraction with Context-Definition Alignment
- URL: http://arxiv.org/abs/2211.05156v1
- Date: Wed, 9 Nov 2022 19:06:22 GMT
- Title: Efficient Zero-shot Event Extraction with Context-Definition Alignment
- Authors: Hongming Zhang, Wenlin Yao, Dong Yu
- Abstract summary: Event extraction (EE) is the task of identifying interested event mentions from text.
We argue that using the static embedding of the event type name might not be enough because a single word could be ambiguous.
We name our approach Zero-shot Event extraction with Definition (ZED)
- Score: 50.15061819297237
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Event extraction (EE) is the task of identifying interested event mentions
from text. Conventional efforts mainly focus on the supervised setting.
However, these supervised models cannot generalize to event types out of the
pre-defined ontology. To fill this gap, many efforts have been devoted to the
zero-shot EE problem. This paper follows the trend of modeling event-type
semantics but moves one step further. We argue that using the static embedding
of the event type name might not be enough because a single word could be
ambiguous, and we need a sentence to define the type semantics accurately. To
model the definition semantics, we use two separate transformer models to
project the contextualized event mentions and corresponding definitions into
the same embedding space and then minimize their embedding distance via
contrastive learning. On top of that, we also propose a warming phase to help
the model learn the minor difference between similar definitions. We name our
approach Zero-shot Event extraction with Definition (ZED). Experiments on the
MAVEN dataset show that our model significantly outperforms all previous
zero-shot EE methods with fast inference speed due to the disjoint design.
Further experiments also show that ZED can be easily applied to the few-shot
setting when the annotation is available and consistently outperforms baseline
supervised methods.
Related papers
- Improving Event Definition Following For Zero-Shot Event Detection [66.27883872707523]
Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types.
We aim to improve zero-shot event detection by training models to better follow event definitions.
arXiv Detail & Related papers (2024-03-05T01:46:50Z) - Continual Event Extraction with Semantic Confusion Rectification [50.59450741139265]
We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting.
We observe that the semantic confusion on event types stems from the annotations of the same text being updated over time.
This paper proposes a novel continual event extraction model with semantic confusion rectification.
arXiv Detail & Related papers (2023-10-24T02:48:50Z) - Semantic Pivoting Model for Effective Event Detection [19.205550116466604]
Event Detection aims to identify and classify mentions of event instances from unstructured articles.
Existing techniques for event detection only use homogeneous one-hot vectors to represent the event type classes, ignoring the fact that the semantic meaning of the types is important to the task.
We propose a Semantic Pivoting Model for Effective Event Detection (SPEED), which explicitly incorporates prior information during training and captures semantically meaningful correlations between input and events.
arXiv Detail & Related papers (2022-11-01T19:20:34Z) - OneEE: A One-Stage Framework for Fast Overlapping and Nested Event
Extraction [40.353446897312196]
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text.
We design a simple yet effective tagging scheme and model to formulate EE as word-word relation recognition, called OneEE.
Experiments on 3 overlapped and nested EE benchmarks, namely FewFC, Genia11, and Genia13, show that OneEE achieves the state-of-the-art (SOTA) results.
arXiv Detail & Related papers (2022-09-06T17:59:55Z) - Suspected Object Matters: Rethinking Model's Prediction for One-stage
Visual Grounding [93.82542533426766]
We propose a Suspected Object Transformation mechanism (SOT) to encourage the target object selection among the suspected ones.
SOT can be seamlessly integrated into existing CNN and Transformer-based one-stage visual grounders.
Extensive experiments demonstrate the effectiveness of our proposed method.
arXiv Detail & Related papers (2022-03-10T06:41:07Z) - 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) - Connect-the-Dots: Bridging Semantics between Words and Definitions via
Aligning Word Sense Inventories [47.03271152494389]
Word Sense Disambiguation aims to automatically identify the exact meaning of one word according to its context.
Existing supervised models struggle to make correct predictions on rare word senses due to limited training data.
We propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge.
arXiv Detail & Related papers (2021-10-27T00:04:33Z) - Event Extraction as Natural Language Generation [42.081626647997616]
Event extraction is usually formulated as a classification or structured prediction problem.
We propose GenEE, a model that not only captures complex dependencies within an event but also generalizes well to unseen or rare event types.
Empirical results show that our model achieves strong performance on event extraction tasks under all zero-shot, few-shot, and high-resource scenarios.
arXiv Detail & Related papers (2021-08-29T00:27:31Z) - 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)
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.