https://orcid.org/0000-0001-7701-568X
Figures
Abstract
The task of event extraction consists of three subtasks namely entity recognition, trigger identification and argument role classification. Recent work tackles these subtasks jointly with the method of multi-task learning for better extraction performance. Despite being effective, existing attempts typically treat labels of event subtasks as uninformative and independent one-hot vectors, ignoring the potential loss of useful label information, thereby making it difficult for these models to incorporate interactive features on the label level. In this paper, we propose a joint label space framework to improve Chinese event extraction. Specifically, the model converts labels of all subtasks into a dense matrix, giving each Chinese character a shared label distribution via an incrementally refined attention mechanism. Then the learned label embeddings are also used as the weight of the output layer for each subtask, hence adjusted along with model training. In addition, we incorporate the word lexicon into the character representation in a soft probabilistic manner, hence alleviating the impact of word segmentation errors. Extensive experiments on Chinese and English benchmarks demonstrate that our model outperforms state-of-the-art methods.
Citation: Huang W, Zhang J, Ji D (2022) Extracting Chinese events with a joint label space model. PLoS ONE 17(9): e0272353. https://doi.org/10.1371/journal.pone.0272353
Editor: Fu Lee Wang, Hong Kong Metropolitan University, HONG KONG
Received: September 11, 2021; Accepted: July 19, 2022; Published: September 27, 2022
Copyright: © 2022 Huang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: Data is available at: https://github.com/zjcerwin/cnlabelattn.
Funding: This work is supported by the Natural Science Foundation of China (No. 62106179).
Competing interests: The authors have declared that no competing interests exist.
Introduction
Event extraction is a field of study that aims to generate structural knowledge with regard to particular occurred events that people care about from plain texts [1, 2]. End-to-end event extraction contains three fundamental tasks, namely entity recognition, event trigger identification and argument role classification. Entities, referred to a set of world objects (e.g. Steve Jobs, Bill Gates), consist of several consecutive tokens in the sentence with an association of a particular type (e.g. Persons, Organizations and Locations). Event triggers, generally determined by verbs or nominalizations, are keywords that can mostly evoke the corresponding events. For example, given a Chinese text:
“军警两名士兵丧生。”(Two soldiers of the military police were killed.)
In this instance, an event detection system should be able to identify that the word “丧生”(were killed) is an event trigger of type Die. At last, event arguments are entities to be connected to triggers with specific roles in the event, such as “士兵”(soldiers) plays an Victim role in the Die event triggered by “丧生”(were killed).
Traditional pipelined extraction systems treat entity, trigger and argument extractions as three separate tasks, which follow a procedure of entity recognition → trigger word identification → argument role classification [3–8]. Although these methods are flexible, they have the limitations that incorrect entity and trigger results would degrade the performance of argument role classification. These pipelined methods could lead to two issues:1) previous step errors would propagate to following steps;2)they are typically insufficient for modeling the mutual dependence among subtasks. Therefore, later approaches put more focus on building joint models to simultaneously extract entities, triggers and argument roles. Prior joint learning methods depend heavily on human-designed indicator features and pre-built syntax tools to capture most useful information for event extraction [9–11]. With the raise of deep learning models, recent studies concentrate on representation-based neural networks to automatically compose low-dimensional features, and multi-task approaches based on hard parameter sharing are applied to jointly solve information extraction tasks [12–15]. As shown in Fig 1(a), their approaches can be mainly divided into three components: (1) An embedding look-up layer with pre-tokenized words as inputs, the embedding table is usually initialized with pre-trained word vectors [16]; (2) A shared multi-layer Bi-directional recurrent neural network (BiRNN) to encode deep contextual representations, and the long-short term memory alternative (LSTM) [17] is typically adopted for handling the vanish gradient problem. (3) Independent output networks with the Softmax function are added on top for classifying specific labels.
Although these neural-based joint learning methods perform better than the former, the complicated event structure still poses two challenges when applied to Chinese event extraction. First, unlike languages with explicit word boundaries (e.g. English), Chinese event extraction is more difficult since words in Chinese texts are not indicated naturally. Hence, a word segmentation procedure is often required before involving subsequent applications [18–20]. However, it is unavoidable that words are segmented incorrectly. This will result in inherent errors in the detection of entity and trigger boundaries and the prediction of their categories. Therefore, some approaches resort to performing Chinese event detection directly at the character level [21, 22]. This results in a dilemma between the choice of performing Chinese event extraction based on a fully character-level model and by first segment text into words. Second, traditional multi-task models that are based on hard parameter sharing rely on implicit network weights to capture correlations among tasks [13, 23–26], treating event labels as meaningless and independent one-hot vectors, which cause a loss of potential label information. However, this is inconsistent with the process of the human annotation of an event mention. For instance, for a trigger with event type e.g. Divorce, a human will only connect PERSON entities to the trigger as argument roles based on the fact that it is impossible for non-human beings to divorce.
Previously, we have presented a transition-based method [27] that approaches the joint learning in a left-to-right decoding order, which has been proven to be better than simple shared-private models. However, it suffers from two limitations: 1) The elaborate modification to the standard LSTM hinders the computation of multiple sentence in a batch and not all lexicons that related to a character are used; 2) The interactive semantics of all task labels have not been fully explored, in the sense that the event label information has not been introduced into the shared representations.
In this work, we introduce a novel Multi-layer Label Attentive framework to improve Chinese Event Extraction (MLAEE). For the above first issue, there have been studies showing that integrating lexicon features into character-based networks could lead to better entity recognition performance [28, 29]. Inspired by these methods, we propose to perform event extraction based on characters and enhance character representations by introducing the word lexicon, which is presented in Fig 1(b). In contrast to modifying LSTM interior to incorporate word embeddings in hidden layers [28], we propose to make use of a simple and effective method [30] that turns the lexicon matching results to the BMES encoding scheme, which bypass the need for a complicated model architecture. For the second issue, we propose a joint label space for all the entity and event types, thereby allowing correlated-type information to incorporate into the network representations. In particular, we map labels of each subtask into low-dimensional semantic vectors, similar to word embeddings [16]. By stacking all label types of events as a matrix, we let each character hidden state performs attention over it for deriving a label importance distribution, and share the label parameters with the output layers. By doing this, label embeddings can be viewed as a semantic bridge that enables interactions between the encoding and decoding stage, leading to a novel joint learning approach.
We conduct sets of experiments on a standard benchmark dataset for event extraction. With comprehensive comparisons with existing advanced methods, our model achieves state-of-the-art results on the Chinese ACE2005 dataset. To demonstrate that our joint label space model is applicable across different languages and tasks, we make two additional experiments: 1)event extraction on the English ACE2005 dataset; 2)using entity relation extraction as an auxiliary task to boost event performance. Results show that our approach is also effective on both the English dataset and incorporating relation labels. Furthermore, we make an ablation analysis to show the contribution of each proposed module and visualization results indicate that label embeddings can indeed capture semantic correlations among entities, triggers and argument roles.
Task definition
Formally, given an input sentence represented as a sequence of characters C = c1, c2, …cn, we extract a set of entities E, event triggers T and event arguments A. In particular, each token ci will be determined to be an entity span ei. Then ci will be differentiated to be a part of a positive or negative trigger word and will be further categorized to an event subtype label ti if ci is a positive trigger word. Further, for each trigger ti and entity ei pair in the same sentence, an argument role aij is required to be predicted. Following [9, 13, 25], we prepare argument candidates using predicted entity mentions.
Methodology
In this section, we will detail our proposed MLAEE model. As Fig 2 illustrates, MLAEE extract event outputs from an input Chinese text in three steps: input representation layer, label attentive encoding layer and event identification layer.
During event decoding, we use two separate sequence taggers to obtain entity and event trigger results, respectively. Then for each entity-trigger pair, we assign it with an event relationship under the definition of argument role types designated by ACE2005 https://catalog.ldc.upenn.edu/ldc2006t06. Note that the weights of entity, trigger and argument role output networks are stacked as one label embedding matrix, which will be used at the encoding layer.
Input embedding
At input embedding layer, a hybrid approach that both character-level and word-level features are used for input representations. In particular, for an input Chinese sequence consisting of n characters C = c1, c2, …cn, we transform the one-hot vectors into the distributed representations with a deep transformer layer. Its weight is pre-trained on a large amount of raw text with the object of the masked bi-directional language model [31]. To be consistent with BERT pre-training, we add two special tokens [CLS] and [SEP] at the front and end of C, respectively, before obtaining Ec. These contextualized embeddings have been proved to be better than static word embeddings [31], e.g. Word2Vec, Glove in many natural language tasks, due to dynamic embeddings are more similar to the diverse nature in human languages in the sense that the meaning of a word is changed along with its surrounding words.
Soft lexicon features
A flaw of the merely character-based event extraction approach is that the word information can not be utilized correspondingly. In this work, we investigate a SoftLexicon approach [30] that simply augments current character representation ci with all matching word embeddings in a soft probabilistic manner. In particular, as presented in Fig 2 (bottom right), SoftLexicon first extract all words that contain character ci in a lexicon and only keep the words that can be found in the input sequence. Then based on the location of ci in a matched word wi, which can be in the Begin, Middle, End of wi or a Single-character word, wi is categorized and marked as one of the four segmentation labels K = {B, M, E, S}. For example, the character c7 (“丧”) in Fig 2 appears in the start of the word (“丧失”) and c8 (“生”) appears in the end of the word. Accordingly, their corresponding segmentation categories are {B} and {E}, respectively. Note that if a segmentation label set is empty for ci, we add “NULL” to the set to maintain a consistent input vector size. After categorization, words that belongs to the same segmentation label are condensed into a fixed-dimensional vector, which is formally calculated as:
(1)
where vw denotes the word embedding lookup table, z(wi) denote the frequency that a matched word wi occurs in the in-domain statistical data. Z is the weight normalization term in the four segmentation sets:
(2)
In addition, we do not increase the frequency of wi if it has been counted by another sub-sequence that matches the word, thus preventing the longer words always have high frequency than the shorter words.
With Eq 2, we can obtain the combined representation of four word sets into one distributed vector as:
(3)
where ⊕ indicates concatenation operation.
Finally, a character ci is represented by concatenating its contextualized character embedding and its BMES style soft word vector
as:
(4)
Encoder layer
After the word semantic information is incorporated, we then feed the character representations into the sequence encoding layer to capture context-sensitive features, which is implemented by stacking multi-layer bidirectional long-short term memory networks(Bi-LSTMs) [17]. This enables the preservation of the historical and future information in forward and reverse directions.
The forward and backward representations are concatenated to obtain one layer bi-directional representation of a character i as . We use matrix H = [h1;h2;…;hn] to denote stacked hidden states for input sequence C.
Multi-head label attention layer
To incorporate joint label information into Bi-LSTMs, we propose to let each character‘s hidden representation hi to interact with all subtask labels through the multi-head attention mechanism [32].
Formally, given a set of candidate output labels L = l1, l2, …, lM, we represent each label lm using an low-dimensional vector:
(5)
where vl denotes a label embedding lookup table.
We can thus obtain label embedding matrices ,
,
for entities, triggers and argument roles, respectively by feeding their one-hot categorical labels to Eq 5.
is denoted as a concatenation of all label matrices
, which will then be used for calculating the label importance distribution to update input character embeddings.
Label embeddings can be randomly initialized and adjusted along with model training, or loaded more informatively with descriptive words of the label type. For example, a BE-BORN event is defined with coarse type “Life” and fine-grained type “Be born”. Hence, for a label lm, we collect all descriptive words Sm and average pre-trained word embeddings in Sm as the label type initial vector:
(6)
To jointly encode features from the character subspace hi and the concatenated label subspace , we apply a scaled dot-product attention:
(7)
(8)
where dh is the dimension of the Bi-LSTM outputs H used for forming a soft norm in the attention distribution. WQ, Wk and Wv are model parameters.
For m-head attentions, we concatenate m subspaces to form the final representation of ci:
(9)
The output of the label attention layer is the concatenation of the i-th step BiLSTM hidden state hi and normalized label vector ai:
(10)
As illustrated in Fig 2, we then apply the second layer Bi-LSTM on top of the 0-th label-informed hidden states to obtain high-level
, leading to a K layers hierarchical refined representations. Note that the k-th
will be fed to subsequent event decoding layer.
Decoder layer
Entity and trigger identification.
Given an input sequence C, we predict its entity tags Se and trigger tags St by applying two feed-forward networks (FFN) with Relu activation:
(11)
(12)
where
and
are entity and trigger label embedding weights from section, respectively.
After that, two softmax output layers are applied to obtain the entity and trigger label probabilities:
(13)
(14)
The training objective is to minimize the negative log-probability of logP(Se|C) and logP(St|C).
Argument classification.
To obtain the argument probabilities for the entity ep with regard to the event trigger tq, we combine their hidden representations from and feed the concatenated vector to a softmax feed-forward layer for argument role decoding:
(15)
where
and
are selected hidden states from
for the predicted entity cp and the trigger cq by Eq 14,
is the gold argument role annotation. To cope with the cases where
or
is a span that contains multiple consecutive tokens, we summarize their embeddings via average-pooling for the consideration of keeping token order information. For model training, we minimize the negative the log-probability of
, which is similar to the entity and trigger classification.
Joint training strategy.
Following the work [33], entity identification, trigger extraction and argument role classification are treated as subtasks of end-to-end event extraction, and are optimized jointly via a multi-task learning setting. A cross-entory loss is used as the object function and the log-likelihoods of all the tasks in a sentence are summarized:
(16)
During the testing stage where the gold-standard entities and trigger are not available, we predict their sequence labels by choosing the output with the highest score by Eq 14 and then convert the BILOU tags to the corresponding spans and types. We next pair every entity and trigger spans to extract argument roles by Eq 15.
Experiments
Experimental settings
Dataset.
To examine the effectiveness of various models on three subtasks of event extraction, we conduct experiments on a multilingual training corpus, Automatic Content Extraction (ACE) 2005 dataset [1]. The dataset contains documents mainly collected from Newswires (NW), Broadcast News (BN), Weblog (WL) fields. Following [24]‘s experiment setup, we conduct tests on the Chinese dataset (ACE-CN) and the English dataset (ACE-EN). There are totally 7914 sentences in ACE-CN and 17172 in ACE-EN, respectively. We divide the training/developing/testing set accordingly. Note that we use entity types with 7 categories, event subtypes with 33 categories, and 22 argument role relations to be consistent with the pre-processing step of [24]. We follow [34] and use automatically segmented Chinese Giga-Word as the matching dictionary. Our dataset and data will be released at https://gitee.com/zjcerwin/cn_labelattn upon the paper acceptance.
Evaluation metrics.
We use Precision (P), Recall (R) and F-Measure (F1) scores to evaluate the performances of different approaches with respect to entity recognition, event trigger detection and argument role classification by following [14, 23, 24]: Entity: An entity is considered correct if we can identify its start and end locations as well as the entity type correctly. Trigger: An event trigger is treated as correct if its start and end offsets as well as its event subtype are all matched (Trig-C). Argument: An argument role is determined as correct when its entity offset, relation role type and the connected triggers are all identified correctly (Arg-C).
Pre-processing.
To represent input Chinese sentences, we use the bert-base-multilingual-cased model https://huggingface.co/transformers/pretrained_models.html for characters, and word embeddings with [35], which are pretrained on Chinese Gigaword corpus using the skip-gram model [36]. For English, we use an improved roberta-base-cased model for word pieces encoding in addition to the traditional 100-dimensional GloVe http://nlp.stanford.edu/projects/glove/ embeddings. Note that we fine-tune all the static embeddings during training and keep contextualized models fixed to keep relatively low GPU memory usage.
Hyper-parameter settings.
All the model hyper-parameters are selected by taking the evaluation results on the developing set with the early stopping strategy. Specifically, dropout technique is adopted to prevent overfitting, which is set to 0.33 on input embeddings and hidden states. Adam optimizer is applied to adjust the network weights, with an initial learning rate of 0.01 and a decay rate of 0.85 for every five epochs. The hidden state size of stacked BiLSTM and label attention layer are employed both with 200, and the layer number is set to 2. We test the batch size in [16, 32, 64] and set the maximum epoch numbers to 150. And to verify the superiority of the proposed method is not caused by noise in the data or other random factors, we use the pairwise t-test for measuring significance. For a fair comparison, we conduct all experiments on a machine with Intel Quad core CPU (I7-6700k, 4.0GHz) and GeForce GTX 1080 GPU with 8 GB graphic memory.
Results
Baselines.
With regard to prior work that considers the three subtasks, we construct baselines on word-level and character level, where word-based approaches use Jieba tokenizer https://github.com/fxsjy/jieba for segmentation, which includes:
- Word-Tree-Joint [12] is a typical shared-private model, which recognizes entities on top of shared Bi-LSTM representations and then extracts relations between entity pairs using tree-LSTM over dependency parsers.
- Word-NP-pipeline [8] is a two-stage word-based method that first pick NP nodes from a constitute parser as candidate entities, then enable triggers and arguments interactions with attention.
Character-based methods include:
- Char-GRU-Joint [37] is a multitask neural method considering the three subtasks by sharing Bi-GRU hidden representations.
- Char-BERT-pipeline [31] is a pipelined method that shares low-level BERT embeddings. To predict event mentions, we simply add a softmax transformation layer on top of the BERT encoder.
There are methods not only consider event subtasks but also involve semantic relation extraction:
- Char-Span-Joint [23] is a top-performed end-to-end information extraction model, all possible spans in a sentence are considered to construct information graphs.
- Char-Global-Joint [24] is the state-of-the-art information extraction framework that introduces indicative global features at the decoding stage to capture the cross-subtask and cross-instance interactions.
- Transition-Joint [27] is a recent state-of-the-art joint decoding method based on the transition system. They use a hybrid approach to incorporate character and word features [28]. For the English dataset, only word inputs are used.
To testify the effectiveness of the proposed methods, we construct two modifications:
- Lattice: A multi-task event extraction model with soft lexicon features replaced by lattice LSTM [28]. Note that the proposed joint label attention mechanism is not used.
- SoftLexicon: Using soft lexicon features and also without the label attention.
- MLAEE + REL: Using all techniques introduced in this work and additionally learns relation extraction with an extra FFN output layer. We use “+ REL” to indicate models involving entity relation annotations.
Main result.
The comparison results of entity, trigger and argument extractions are shown in Table 1. We can observe that: 1) character-based methods perform better than word-based counterparts. One possible reason is that incorrect word segments would severely hurt event results; 2) Purely character-based approaches underperform word lexicon enhanced ones Lattice and SoftLexicon, demonstrating the semantic units of Chinese words are helpful for event extraction. But instead of modifying LSTM extensively to introduce word features Lattice, a simplified encoding scheme SoftLexicon is enough and effective; 3)Compared to Transition-Joint, our Lattice give 3.5% better F-scores on argument classification. This result indicates that the joint label information is more effective than the left-to-right decoding in introducing interactive knowledge at the decoding stage, particularly for argument roles. 4) When equipped with label attention, MLAEE is 2.4% higher than current SOTA [24] on argument F-scores, verifying the effectiveness of the joint label information coupled with character representations. In addition, we evaluate the proposed framework on ACE05-EN (Table 2). The results show that MLAEE also performs well on English data, justifying the usefulness of label embedding across languages. On the other hand, there have been frameworks that jointly perform relation and event extractions [23, 24, 27]. To have a fair comparison with these models, we also integrate relation annotations into our model, denoted as “MLAEE+REL”. As can be seen from Tabels 1 and 2, our MLAEE+REL can still outperform the current state-of-the-art method Char-Global-Joint in event trigger and argument role classification, without the particular design of relation and event communications. This result further demonstrates that our label attentive model is effective across different structural prediction tasks.
Ablation study.
To examine the influence of several key model components, we conduct ablation tests on ACE-CN. Table 3 shows the results, it can be observed that without BiLSTM, MLAEE presents a moderate drop of performances. By removing SoftLexicon or Label embedding, both trigger and argument classification degrades significantly, indicating their importance in the network. Not surprisingly, the BERT embedding brings the most performance improvements, which is consistent with the experiments in [23, 25].
Visualization.
To understand information learned in the label embeddings, we visualize label types of entities, triggers and arguments by deducing the 200D embedding matrix into a 2D map with t-SNE after 3, 10, 40 training epochs, respectively. As shown in Fig 3, the locations of label types are increasingly more informative as training proceeds. At the initial epoch, the vectors locate randomly in the reduction space. After 10 epochs, we can observe that there are small clusters emerge, such as “Attack” event and “Attacker” argument. As training goes, we find groups start to absorb more semantic related labels, likewise “weapon”, “vehicle” entity types and “victim”, “target” argument roles closely surround “Attack” event. It confirms that the refined joint learning mechanism can indeed capture the label interactions among event subtasks.
(a) 3 epochs, (b) 10 epochs, and (c) 40 epochs.
Case study.
We make a case study by comparing our MLAEE model with the previous best model Char-Global-Joint, on two representative Chinese event instances. As shown in Table 4, there are two Attack triggers “开” and “丢” in the first case, “枪” is the Instrument argument of “开” and “汽油弹” is the Instrument argument of “丢”, respectively. It can be observed that Char-Global-Joint fail to identify that “丢” triggers the Attack event and falsely connect “汽油弹” to “开”, while our MLAEE model can recognize two event mentions correctly. The reason is that the joint entity and event label space can incorporate correlated-type information into the network representations, leading to a positive tendency toward the recalled of event recognition. In the second case, there is much ambiguity around the phrase “向前来”. The Char-Global-Joint yields the event trigger “向前” given that “向前” occurs more frequently than “前来” in the training set. Due to the lack of word unit semantics, it is challenging for the character-level model to infer the correct trigger and argument boundary in this case. In contrast, with the help of the soft lexicon knowledge, the MLAEE model detects the Transport trigger “前来” and Destination argument “日本” correctly.
Gold Ci indicates the standard annotation. Words in bold and italics are correct triggers and arguments, respectively, while the underlined ones are incorrect.
Related work
Our work mainly follows the line of event extraction and label embedding.
English event extraction. Identify events in English texts is a heated topic in information extraction field [3, 12–15]. Feature-based methods [4–6, 11] and recent neural-based models [26, 37–39] have been used to promote the extraction performance continually. To improve model performance, some studies put focus on leveraging syntax information into neural networks, which include adding shortcut arcs in LSTM [8] or using Graph Convolutional Networks (GCNs) [26, 33, 37, 40, 41]. There has been work found that incorrect entity results would hurt argument role classifications significantly [9, 11, 37]. Subsequently, the transition based framework is devised [25] to jointly consider entity and events. Further, studies also learn relations together with events [15, 23, 24]. However, they all treat task labels as uninformative and categorical numbers. In contrast, our models map labels of event extraction tasks into semantic vectors and provide a way to realize joint learning with the interaction between the encoding and decoding stage.
Chinese event extraction. For Chinese, a word segmentation procedure is often required before applying event systems, despite kernel-based methods [18, 42], feature-based methods [18–20] or neural network methods [21, 24, 27, 43] are used. Instead of relying on existing segmentors, which suffer from the potential issue of error propagation we take characters as the basic units and integrate word lexicon with the input encoding scheme [28, 30].
Label embedding. In computer vision, research has demonstrated the importance of label embeddings, including text recognition [44] and image classification [45]. Later, work [46] shows that label embedding can benefit text classification, where text descriptions are used to generate initial label vectors. Inspired by them, [47] proposes to denoise relation instances with the help of Knowledge Graphs and entity related label embeddings. Inspired by the recent work of label attention network [48], we propose a joint label space across event subtasks, enhancing network hidden representations with global task label information. To our knowledge, we are the first to apply it for joint entity and event extraction.
Conclusion
We present a multi-level label attentive multitask network for Chinese end-to-end event extraction. With a hierarchical refined attention mechanism, the label importance distribution is incorporated into each character’s hidden state and further shares label embeddings with output layers resulting in joint learning in both the encoding and decoding stage. Results on a multi-lingual benchmark show the superiority of our model over various advanced baselines.
Acknowledgments
We would like to thank the anonymous reviewers for their many valuable comments and suggestions.
References
- 1. Walker C, Strassel S, Medero J, Maeda K. ACE 2005 multilingual training corpus. Linguistic Data Consortium, Philadelphia. 2006;57:45.
- 2. Xiang W, Wang B. A Survey of Event Extraction From Text. IEEE Access. 2019;7:173111–173137.
- 3. Rau LF, Jacobs PS, Zernik U. Information extraction and text summarization using linguistic knowledge acquisition. Information Processing … Management. 1989;25(4):419–428.
- 4. Ji H, Grishman R. Refining event extraction through cross-document inference. ACL-08. 2008;.
- 5.
Liao S, Grishman R. Using document level cross-event inference to improve event extraction. In: ACL; 2010.
- 6.
McClosky D, Surdeanu M, Manning CD. Event extraction as dependency parsing. In: ACL; 2011.
- 7.
Veyseh APB, Nguyen TN, Nguyen TH. Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction. In: Proc. of EMNLP; 2020. p. 3651–3661.
- 8.
Sha L, Qian F, Chang B, Sui Z. Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction. In: AAAI; 2018.
- 9.
Yang B, Mitchell T. Joint Extraction of Events and Entities within a Document Context. In: NAACL-HLT; 2016.
- 10.
Li Q, Ji H, Yu H, Li S. Constructing information networks using one single model. In: EMNLP; 2014.
- 11.
Li Q, Ji H, Huang L. Joint event extraction via structured prediction with global features. In: ACL; 2013.
- 12.
Miwa M, Bansal M. End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures. In: Proceedings of the 54th ACL; 2016. p. 1105–1116.
- 13.
Nguyen TM, Nguyen TH. One for All: Neural Joint Modeling of Entities and Events. In: AAAI; 2019.
- 14. Zhang T, Ji H, Sil A. Joint entity and event extraction with generative adversarial imitation learning. Data Intelligence. 2019;1(2):99–120.
- 15. Zhang J, Hong Y, Zhou W, Yao J, Zhang M. Interactive learning for joint event and relation extraction. International Journal of Machine Learning and Cybernetics. 2020;11(2):449–461.
- 16.
Pennington J, Socher R, Manning C. Glove: Global vectors for word representation. In: EMNLP; 2014.
- 17. Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997;9(8):1735–1780. pmid:9377276
- 18.
Zhang J, Ouyang Y, Li W, Hou Y. A novel composite kernel approach to Chinese entity relation extraction. In: International Conference on Computer Processing of Oriental Languages. Springer; 2009. p. 236–247.
- 19.
Li P, Zhu Q, Diao H, Zhou G. Joint modeling of trigger identification and event type determination in Chinese event extraction. In: Proceedings of COLING 2012; 2012. p. 1635–1652.
- 20.
Li P, Zhou G. Employing morphological structures and sememes for Chinese event extraction. In: Proceedings of COLING 2012; 2012. p. 1619–1634.
- 21.
Zeng Y, Yang H, Feng Y, Wang Z, Zhao D. A convolution BiLSTM neural network model for Chinese event extraction. In: Natural Language Understanding and Intelligent Applications. Springer; 2016. p. 275–287.
- 22.
Zheng S, Cao W, Xu W, Bian J. Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction. In: Proceedings of EMNLP; 2019. p. 337–346.
- 23.
Wadden D, Wennberg U, Luan Y, Hajishirzi H. Entity, Relation, and Event Extraction with Contextualized Span Representations. In: Proceedings of EMNLP; 2019. p. 5788–5793.
- 24.
Lin Y, Ji H, Huang F, Wu L. A Joint Neural Model for Information Extraction with Global Features. In: Proceedings of ACL; 2020. p. 7999–8009.
- 25.
Zhang J, Qin Y, Zhang Y, Liu M, Ji D. Extracting entities and events as a single task using a transition-based neural model. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press; 2019. p. 5422–5428.
- 26.
Liu X, Luo Z, Huang H. Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation. In: EMNLP; 2018.
- 27. Huang W, Zhang J, Ji D. A transition-based neural framework for Chinese information extraction. Plos one. 2020;15(7):e0235796. pmid:32667950
- 28.
Zhang Y, Yang J. Chinese NER Using Lattice LSTM. In: Proceedings of the 56th ACL; 2018. p. 1554–1564.
- 29.
Sui D, Chen Y, Liu K, Zhao J, Liu S. Leverage lexical knowledge for chinese named entity recognition via collaborative graph network. In: Proceedings of EMNLP; 2019. p. 3821–3831.
- 30.
Ma R, Peng M, Zhang Q, Wei Z, Huang X. Simplify the Usage of Lexicon in Chinese NER. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. ACL;.
- 31.
Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:181004805. 2018;.
- 32.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Advances in neural information processing systems; 2017. p. 5998–6008.
- 33. Zhang J, He Q, Zhang Y. Syntax grounded graph convolutional network for joint entity and event extraction. Neurocomputing. 2020;422:118–128.
- 34.
Zhang L, Moldovan D. Chinese relation classification using long short term memory networks. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018); 2018.
- 35.
Zhang M, Zhang Y, Fu G. Transition-based neural word segmentation. In: Proceedings of the 54th ACL; 2016. p. 421–431.
- 36.
Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. arXiv preprint arXiv:13013781. 2013;.
- 37.
Nguyen TH, Grishman R. Graph convolutional networks with argument-aware pooling for event detection. In: AAAI; 2018.
- 38.
Chen Y, Xu L, Liu K, Zeng D, Zhao J. Event extraction via dynamic multi-pooling convolutional neural networks. In: ACL; 2015.
- 39.
Nguyen TH, Cho K, Grishman R. Joint event extraction via recurrent neural networks. In: NAACL; 2016.
- 40.
Lai VD, Nguyen TN, Nguyen TH. Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks. In: Proc. of EMNLP; 2020. p. 5405–5411.
- 41. Li L, Jin L, Zhang Z, Liu Q, Sun X, Wang H. Graph Convolution Over Multiple Latent Context-Aware Graph Structures for Event Detection. IEEE Access. 2020;8:171435–171446.
- 42. Zelenko D, Aone C, Richardella A. Kernel methods for relation extraction. Journal of machine learning research. 2003;3(Feb):1083–1106.
- 43. Chen Y, Zheng DQ, Zhao TJ. Chinese relation extraction based on deep belief nets. Ruanjian Xuebao/Journal of Software. 2012;23(10):2572–2585.
- 44. Rodriguez-Serrano JA, Gordo A, Perronnin F. Label embedding: A frugal baseline for text recognition. International Journal of Computer Vision. 2015;113(3):193–207.
- 45. Akata Z, Perronnin F, Harchaoui Z, Schmid C. Label-embedding for image classification. IEEE transactions on pattern analysis and machine intelligence. 2015;38(7):1425–1438. pmid:26452251
- 46.
Wang G, Li C, Wang W, Zhang Y, Shen D, Zhang X, et al. Joint Embedding of Words and Labels for Text Classification. In: Proceedings of the 56th ACL; 2018. p. 2321–2331.
- 47.
Hu L, Zhang L, Shi C, Nie L, Guan W, Yang C. Improving Distantly-Supervised Relation Extraction with Joint Label Embedding. In: Proceedings of EMNLP; 2019. p. 3812–3820.
- 48. Cui L, Li Y, Zhang Y. Label Attention Network for Structured Prediction. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2022;30:1235–1248.