Closed-domain event extraction uses predefined event schema to discover and extract desired events of particular type from text. An event schema contains several event types and their corresponding event structures. We use the ACE terminologies to introduce an event structure as follows:
D.Ahn [the stages of event extraction] first proposed to divide the ACE event extraction task into four subtasks: trigger detection, event/trigger type identification, event argument detection, and argument role identification.
Without predefined event schemas, open-domain event extraction aims at detecting events from texts and in most cases, also clustering similar events via extracted event key-words. Event keywords refer to those words/phrases mostly describing an event, and sometimes keywords are further divided into triggers and arguments.
The first two tasks mainly focus on event detection; and the rest three tasks are for event clustering. While the relation between the five tasks is evident, each requires a distinct evaluation process and encourages different approaches to address the particular problem.
<ahref="https://arxiv.org/pdf/2008.00364.pdf">An Overview of Event Extraction from Text，2019</a> by<i>Frederik Hogenboom, Flavius Frasincar, Uzay Kaymak, Franciska de Jong:
</a></summary><blockquote><palign="justify">
One common application of text mining is event extraction,which encompasses deducing specific knowledge concerning incidents re-ferred to in texts. Event extraction can be applied to various types ofwritten text, e.g., (online) news messages, blogs, and manuscripts. Thisliterature survey reviews text mining techniques that are employed forvarious event extraction purposes. It provides general guidelines on howto choose a particular event extraction technique depending on the user,the available content, and the scenario of use.
<ahref="https://arxiv.org/pdf/2008.00364.pdf">A Survey of Event Extraction from Text，2019</a> by<i>Wei Xiang, Bang Wang </a></summary><blockquote><palign="justify">
<ahref="https://arxiv.org/pdf/2008.00364.pdf">A Survey of Textual Event Extraction from Social Networks，2017</a> by<i>Mohamed Mejri, Jalel Akaichi </a></summary><blockquote><palign="justify">
<ahref="https://arxiv.org/pdf/2008.00364.pdf">A Survey of event extraction methods from text for decision support systems，2016</a> by<i>Frederik Hogenboom, Flavius Frasincar, Uzay Kaymak, Franciska de Jong, Emiel Caron </a></summary><blockquote><palign="justify">
<ahref="https://arxiv.org/pdf/2008.00364.pdf">A Survey of Textual Event Extraction from Social Networks，2014</a> by<i>Vera DanilovaMikhail AlexandrovXavier Blanco </a></summary><blockquote><palign="justify">
<ahref="https://transacl.org/ojs/index.php/tacl/article/view/1853">Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection, WSDM2020(<ahref="https://link.zhihu.com/?target=https%3A//github.com/231sm/Low_Resource_KBP">Github</a>)</summary><blockquote><palign="justify">
Event detection (ED), a sub-task of event extraction, involves identifying triggers and categorizing event mentions. Existing methods primarily rely upon supervised learning and require large-scale labeled event datasets which are unfortunately not readily available in many real-life applications. In this paper, we consider and reformulate the ED task with limited labeled data as a Few-Shot Learning problem. We propose a Dynamic-Memory-Based Prototypical Network (DMB-PN), which exploits Dynamic Memory Network (DMN) to not only learn better prototypes for event types, but also produce more robust sentence encodings for event mentions. Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs. The experiments show that DMB-PN not only deals with sample scarcity better than a series of baseline models but also performs more robustly when the variety of event types is relatively large and the instance quantity is extremely small.
<ahref="https://openreview.net/forum?id=H1eA7AEtvS">Exploiting the Matching Information in the Support Set for Few Shot Event Classification, PAKDD2020 (<ahref="https://github.com/">Github</a>)</summary><blockquote><palign="justify">
The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types. Few-shot learninghas not been investigated in this area although it enables EC models toextend their operation to unobserved event types. To fill in this gap, inthis work, we investigate event classification under the few-shot learningsetting. We propose a novel training method for this problem that exten-sively exploit the support set during the training process of a few-shotlearning model. In particular, in addition to matching the query exam-ple with those in the support set for training, we seek to further matchthe examples within the support set themselves. This method providesmore training signals for the models and can be applied to every metric-learning-based few-shot learning methods. Our extensive experiments ontwo benchmark EC datasets show that the proposed method can improvethe best reported few-shot learning models by up to 10% on accuracyfor event classification.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="http://papers.nips.cc/paper/8812-xlnet-generalized-autoregressive-pretraining-for-language-understanding">Cross-lingual Structure Transfer for Relation and Event Extraction(<ahref="https://github.com/zihangdai/xlnet">Github</a>)</summary><blockquote><palign="justify">
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages. We investigate the suitability of cross-lingual structure transfer techniques for these tasks. We exploit relation- and event-relevant language-universal features, leveraging both symbolic (including part-of-speech and dependency path) and distributional (including type representation and contextualized representation) information. By representing all entity mentions, event triggers, and contexts into this complex and structured multilingual common space, using graph convolutional networks, we can train a relation or event extractor from source language annotations and apply it to the target language. Extensive experiments on cross-lingual relation and event transfer among English, Chinese, and Arabic demonstrate that our approach achieves performance comparable to state-of-the-art supervised models trained on up to 3,000 manually annotated mentions: up to 62.6% F-score for Relation Extraction, and 63.1% F-score for Event Argument Role Labeling. The event argument role labeling model transferred from English to Chinese achieves similar performance as the model trained from Chinese. We thus find that language-universal symbolic and distributional representations are complementary for cross-lingual structure transfer.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
</p></blockquote></details>
###Few-shot or zero-shot
#### 2019
<details/>
<summary/>
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<ahref="https://arxiv.org/abs/1907.11692">Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP2019(<ahref="https://github.com/pytorch/fairseq">Github</a>)</summary><blockquote><palign="justify">
The scarcity in annotated data poses a great challenge for event detection (ED). Cross-lingual ED aims to tackle this challenge by transferring knowledge between different languages to boost performance. However, previous cross-lingual methods for ED demonstrated a heavy dependency on parallel resources, which might limit their applicability. In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources. Specifically, to construct a lexical mapping between different languages, we devise a context-dependent translation method; to treat the word order difference problem, we propose a shared syntactic order event detector for multilingual co-training. The efficiency of our method is studied through extensive experiments on two standard datasets. Empirical results indicate that our method is effective in 1) performing cross-lingual transfer concerning different directions and 2) tackling the extremely annotation-poor scenario.
<summary/><ahref="https://catalog.ldc.upenn.edu/LDC2006T06">ACE2005 English Corpus</a></summary><blockquote><palign="justify">
ACE 2005 Multilingual Training Corpus contains the complete set of English, Arabic and Chinese training data for the 2005 Automatic Content Extraction (ACE) technology evaluation. The corpus consists of data of various types annotated for entities, relations and events by the Linguistic Data Consortium (LDC) with support from the ACE Program and additional assistance from LDC.
