Search

We present SENTiVENT, a corpus of fine-grained company-specific events in English economic news articles. The domain of event processing is highly productive and various general domain, fine-grained event extraction corpora are freely available but economically-focused resources are lacking. This work fills a large need for a manually annotated dataset for economic and financial text mining applications. A representative corpus of business news is crawled and an annotation scheme developed with an iteratively refined economic event typology. The annotations are compatible with benchmark datasets (ACE/ERE) so state-of-the-art event extraction systems can be readily applied. This results in a gold-standard dataset annotated with event triggers, participant arguments, event co-reference, and event attributes such as type, subtype, negation, and modality. An adjudicated reference test set is created for use in annotator and system evaluation. Agreement scores are substantial and annotator performance adequate, indicating that the annotation scheme produces consistent event annotations of high quality. In an event detection pilot study, satisfactory results were obtained with a macro-averaged$$F_1$$F1-score of$$59\%$$59%validating the dataset for machine learning purposes. This dataset thus provides a rich resource on events as training data for supervised machine learning for economic and financial applications. The dataset and related source code is made available athttps://osf.io/8jec2/.

Motivation: The scientific literature embeds an enormous amount of relational knowledge, encompassing interactions between biomedical entities, like proteins, drugs, and symptoms. To cope with the ever-increasing number of publications, researchers are experiencing a surge of interest in extracting valuable, structured, concise, and unambiguous information from plain texts. With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events. Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions. After being studied for years, automatic event extraction is on the road to significantly impact biology in a wide range of applications, from knowledge base enrichment to the formulation of new research hypotheses. Results: This paper provides a comprehensive and up-to-date survey on the link between event extraction and natural language understanding, focusing on the biomedical domain. First, we establish a flexible event definition, summarizing the terminological efforts conducted in various areas. Second, we present the event extraction task, the related challenges, and the available annotated corpora. Third, we deeply explore the most representative methods and present an analysis of the current state-of-the-art, accompanied by performance discussion. To help researchers navigate the avalanche of event extraction works, we provide a detailed taxonomy for classifying the contributions proposed by the community. Fourth, we compare solutions applied in biomedicine with those evaluated in other domains, identifying research opportunities and providing insights for strategies not yet explored. Finally, we discuss applications and our envisions about future perspectives, moving the needle on explainability and knowledge injection.

Event extraction is an important research direction in the field of natural language processing (NLP) applications including information retrieval (IR). Traditional event extraction is realized with two methods: the pipeline and the joint extraction methods. The pipeline method determines the event by triggering word recognition to further implement event extraction and is prone to error cascading. The joint extraction method applies deep learning to implement the completion of the trigger word and the argument role classification task. Most studies with the joint extraction method adopt the CNN or RNN network structure. However, in the case of event extraction, deeper understanding of complex contexts is required. Existing studies do not make full use of syntactic relations. This paper proposes a novel event extraction model, which is built upon a Tree-LSTM network and a Bi-GRU network and carries syntactically related information. It is illustrated that this method simultaneously uses Tree-LSTM and Bi-GRU to obtain a representation of the candidate event sentence and identify the event type, which results in a better performance compared to the ones that use chain structured LSTM, CNN or only Tree-LSTM. Finally, the hidden state of each node is used in Tree-LSTM to predict a label for candidate arguments and identify/classify all arguments of an event. Lab results show that the proposed event extraction model achieves competitive results compared to previous works.

Event is a common but non-negligible knowledge type. How to identify events from texts, extract their arguments, even analyze the relations between different events are important for many applications. This paper summaries some constructed event-centric knowledge graphs and the recent typical approaches for event and event relation extraction, besides task description, widely used evaluation datasets, and challenges. Specifically, in the event extraction task, we mainly focus on three recent important research problems: 1) how to learn the textual semantic representations for events in sentence-level event extraction; 2) how to extract relations across sentences or in a document level; 3) how to acquire or augment labeled instances for model training. In event relation extraction, we focus on the extraction approaches for three typical event relation types, including coreference, causal and temporal relations, respectively. Finally, we give out our conclusion and potential research issues in the future.

Event argument extraction, which aims to identify arguments of specific events and label their roles, is a challenging subtask of event extraction. Previous approaches solve this problem in a two-stage manner that first extracts named entities as argument candidates and then determines their roles. However, many nested entities may be missed or wrongly predicted during the argument candidate extraction procedure, which substantially affects the performance of the downstream classifier. In this paper, we propose a novel one-step question answering based framework, which performs argument candidate extraction and argument role classification simultaneously to mitigate the error propagation problem in conventional two-stage methods. Since the conventional question answering based framework cannot be applied directly to this task, we design a Q uestion A nswering based S equence L abeling (QA-SL) model to tackle inexistent argument roles and multiple argument token spans. Moreover, considering the overwhelming number of parameters in question answering based neural network models and the relatively small size of event extraction corpus, we fine-tune the pre-trained model from BERT to mitigate the data scarcity problem. Extensive experiments demonstrate the benefits of the proposed method, leading to a competitive performance compared with state-of-the-art methods. To the best of our knowledge, this is the first work to cast event argument extraction as a question answering task.

Most existing medical event extraction methods have primarily adopted a simplex model based on either pattern matching or deep learning, which ignores the distribution characteristics of entities and events in the medical corpus. They have not categorized the granularity of event elements, leading to the poor generalization ability of the model. This paper proposes a diagnosis and treatment event extraction method in the Chinese language, fusing long short-level semantic dependency of the corpus, LSLSD, for solving these problems. LSLSD can effectively capture different levels of semantic information within and between event sentences in the electronic medical record (EMR) corpus. Moreover, the event arguments are divided into short word-level and long sentence-level, with the sequence annotation and pattern matching combined to realize multi-granularity argument recognition, as well as to improve the generalization ability of the model. Finally, this paper constructs a diagnosis and treatment event data set of Chinese EMRs by proposing a semi-automatic corpus labeling method, and an enormous number of experiment results show that LSLSD can improve the F1-value of event extraction task by 7.1% compared with the several strong baselines.

Chemical patents are an important source of information about novel chemicals and chemical reactions. With the increasing volume of such patents, mining information about these chemicals and chemical reactions has become a time-intensive and laborious endeavor. In this paper, we present a system to automatically extract chemical reaction events from patents. Our approach consists of two steps: 1) Named Entity Recognition (NER) -- the automatic identification of chemical reaction parameters from the corresponding text; and 2) Event Extraction (EE) -- the automatic classifying and linking of entities based on their relationships to each other. For our NER system, we evaluate Bidirectional Long Short Term Memory (BiLSTM)-based and Bidirectional Encoder Representations from Transformers (BERT)-based methods. For our RE system, we evaluate two BERT-based, Convolutional Neural Networks (CNN)-based, and rule-based methods. We evaluate our NER and EE components separately and also as an end-to-end system, reporting the precision, recall, and F- score. From the results, we can conclude the BiLSTM-based method performed well at identifying the entities, and the CNN-based method performed well at extracting events. CNN-based and BERT-based methods performed well with the classes with more instances to train on, and the rule-based method performed well with classes with fewer instances.

In this article, we focus on the problem of social event extraction from Twitter, in which event detection, i.e., to identify which messages truly mention events of interest, is an indispensable step due to the fact that most Twitter messages, viz. tweets, are not related to any real-world event. Existing approaches to this problem often use pipelined architectures relying on some hand-crafted features derived using off-the-shelf natural language processing (NLP) tools, which may cause error propagation from the upstream component (event detection) to the downstream one (element extraction) and fail to leverage the interdependencies between them. To overcome these limitations, we propose a deep neural network based framework to Jointly Detect and Extract Events from Twitter (JDEET), which learns, as well as conducts, detection and extraction simultaneously by defining a joint loss function, a bidirectional long short-term memory (LSTM) based common representation layer, and a control gate. A conditional random field (CRF) layer is further employed to capture the strong dependencies among output labels. Experimental results show that the proposed approach outperforms the state-of-the-art ones considerably on a real-world dataset from Twitter.

Event extraction is useful for many practical applications, such as news summarization and information retrieval. However, the popular automatic context extraction (ACE) event extraction program only defines very limited and coarse event schemas, which may not be suitable for practical applications. FrameNet is a linguistic corpus that defines complete semantic frames and frame-to-frame relations. As frames in FrameNet share highly similar structures with event schemas in ACE and many frames actually express events, we propose to redefine the event schemas based on FrameNet. Specifically, we extract frames expressing event information from FrameNet and leverage the frame-to-frame relations to build a hierarchy of event schemas that are more fine-grained and have much wider coverage than ACE. Based on the new event schemas, we propose a joint event extraction approach that leverages the hierarchical structure of event schemas and frame-to-frame relations in FrameNet. The extensive experiments have verified the advantages of our hierarchical event schemas and the effectiveness of our event extraction model. We further apply the results of our event extraction model on news summarization. The results show that the summarization approach based on our event extraction model achieves significant better performance than several state-of-the-art summarization approaches, which also demonstrates that the hierarchical event schemas and event extraction model are promising to be used in the practical applications.

Chemical patents represent a valuable source of information about new chemical compounds, which is critical to the drug discovery process. Automated information extraction over chemical patents is, however, a challenging task due to the large volume of existing patents and the complex linguistic properties of chemical patents. The Cheminformatics Elsevier Melbourne University (ChEMU) evaluation lab 2020, part of the Conference and Labs of the Evaluation Forum 2020 (CLEF2020), was introduced to support the development of advanced text mining techniques for chemical patents. The ChEMU 2020 lab proposed two fundamental information extraction tasks focusing on chemical reaction processes described in chemical patents: (1)chemical named entity recognition, requiring identification of essential chemical entities and their roles in chemical reactions, as well as reaction conditions; and (2)event extraction, which aims at identification of event steps relating the entities involved in chemical reactions. The ChEMU 2020 lab received 37 team registrations and 46 runs. Overall, the performance of submissions for these tasks exceeded our expectations, with the top systems outperforming strong baselines. We further show the methods to be robust to variations in sampling of the test data. We provide a detailed overview of the ChEMU 2020 corpus and its annotation, showing that inter-annotator agreement is very strong. We also present the methods adopted by participants, provide a detailed analysis of their performance, and carefully consider the potential impact of data leakage on interpretation of the results. The ChEMU 2020 Lab has shown the viability of automated methods to support information extraction of key information in chemical patents.

A core task in information extraction is event detection that identifies event triggers in sentences that are typically classified into event types. In this study an event is considered as the unit to measure diversity and similarity in news articles in the framework of a news recommendation system. Current typology-based event detection approaches fail to handle the variety of events expressed in real-world situations. To overcome this, we aim to perform event salience classification and explore whether a transformer model is capable of classifying new information into less and more general prominence classes. After comparing a Support Vector Machine (SVM) baseline and our transformer-based classifier performances on several event span formats, we conceived multi-word event spans as syntactic clauses. Those are fed into our prominence classifier which is fine-tuned on pre-trained Dutch BERT word embeddings. On top of that we outperform a pipeline of a Conditional Random Field (CRF) approach to event-trigger word detection and the BERT-based classifier. To the best of our knowledge we present the first event extraction approach that combines an expert-based syntactic parser with a transformer-based classifier for Dutch.

Event detection involves the identification of instances of specified types of events in text and their classification into event types. Inthis paper, we approach the event detection task as a relation extraction task. In this context, we assume that the clues brought by the entities participating in an event are important and could improve the performance of event detection. Therefore, we propose to exploit entity information explicitly for detecting the event triggers by marking them at different levels while fine-tuning a pre-trained language model. The experimental results prove that our approach obtains state-of-the-art results on the ACE 2005 dataset.

Geoparser is a fundamental component of a Geographic Information Retrieval (GIR) geoparser, which performs toponym recognition, disambiguation, and geographic coordinate resolution from unstructured text domain. However, geoparsing of news articles which report several events across many place-mentions in the document are not yet adequately handled by regular geoparser, where the scope of resolution is either toponym-level or document-level. The capacity to detect multiple events and geolocate their true coordinates along with their numerical arguments is still missing from modern geoparsers, much less in Indonesian news corpora domain. We propose an event geoparser model with three stages of processing, which tightly integrates event extraction model into geoparsing and provides precise event-level resolution scope. The model casts the geotagging and event extraction as sequence labeling and uses LSTM-CRF inferencer equipped with features derived using Aggregated Topic Model from a large corpus to increase the generalizability. Throughout the proposed workflow and features, the geoparser is able to significantly improve the identification of pseudo-location entities, resulting in a 23.43% increase for weighted F1 score compared to baseline gazetteer and POS Tag features. As a side effect of event extraction, various numerical arguments are also extracted, and the output is easily projected to a rich choropleth map from a single news document.

Background Biomedical event extraction is a fundamental and in-demand technology that has attracted substantial interest from many researchers. Previous works have heavily relied on manual designed features and external NLP packages in which the feature engineering is large and complex. Additionally, most of the existing works use the pipeline process that breaks down a task into simple sub-tasks but ignores the interaction between them. To overcome these limitations, we propose a novel event combination strategy based on hybrid deep neural networks to settle the task in a joint end-to-end manner. Results We adapted our method to several annotated corpora of biomedical event extraction tasks. Our method achieved state-of-the-art performance with noticeable overall F1 score improvement compared to that of existing methods for all of these corpora. Conclusions The experimental results demonstrated that our method is effective for biomedical event extraction. The combination strategy can reconstruct complex events from the output of deep neural networks, while the deep neural networks effectively capture the feature representation from the raw text. The biomedical event extraction implementation is available online at http://www.predictor.xin/event_extraction.

BackgroundEmergency room reports pose specific challenges to natural language processing techniques. In this setting, violence episodes on women, elderly and children are often under-reported. Categorizing textual descriptions as containing violence-related injuries (V)vs. non-violence-related injuries (NV) is thus a relevant task to the ends of devising alerting mechanisms to track (and prevent) violence episodes.MethodsWe presentViDeS(so dubbed afterViolence Detection System), a system to detect episodes of violence from narrative texts in emergency room reports. It employs a deep neural network for categorizing textual ER reports data, and complements such output by making explicit which elements corroborate the interpretation of the record as reporting about violence-related injuries. To these ends we designed a novel hybrid technique for filling semantic frames that employs distributed representations of terms herein, along with syntactic and semantic information. The system has been validated on real data annotated with two sorts of information: about the presence vs. absence of violence-related injuries, and about some semantic roles that can be interpreted as major cues for violent episodes, such as the agent that committed violence, the victim, the body district involved, etc.. The employed dataset contains over 150K records annotated with class (V,NV) information, and 200 records with finer-grained information on the aforementioned semantic roles.ResultsWe used data coming from an Italian branch of the EU-Injury Database (EU-IDB) project, compiled by hospital staff. Categorization figures approach full precision and recall for negative cases and.97 precision and.94 recall on positive cases. As regards as the recognition of semantic roles, we recorded an accuracy varying from.28 to.90 according to the semantic roles involved. Moreover, the system allowed unveiling annotation errors committed by hospital staff.ConclusionsExplaining systems’ results, so to make their output more comprehensible and convincing, is today necessary for AI systems. Our proposal is to combine distributed and symbolic (frame-like) representations as a possible answer to such pressing request for interpretability. Although presently focused on the medical domain, the proposed methodology is general and, in principle, it can be extended to further application areas and categorization tasks.

2019 has been characterized by worldwide waves of protests. Each country’s protests is different but there appear to be common factors. In this paper we present two approaches for identifying protest events in news in English. Our goal is to provide political science and discourse analysis scholars with tools that may facilitate the understanding of this on-going phenomenon. We test our approaches against the ProtestNews Lab 2019 benchmark that challenges systems to perform unsupervised domain adaptation on protest events on three sub-tasks: document classification, sentence classification, and event extraction. Results indicate that developing dedicated architectures and models for each task outperforms simpler solutions based on the propagation of labels from lexical items to documents. Furthermore, we complete the description of our systems with a detailed data analysis to shed light on the limits of the methods.

Event-based automatic text simplification system.Lexical and syntactic text simplification with content reduction.No need for parallel datasets nor large set of handcrafted simplification rules.Proposed simplification system is highly competitive.Novel evaluation method based on measuring the postediting effort. Automated Text Simplification (ATS) aims to transform complex texts into their simpler variants which are easier to understand to wider audiences and easier to process with natural language processing (NLP) tools. While simplification can be applied on lexical, syntactic, and discourse level, all previously proposed ATS systems only operated on the first two levels, thus failing at simplifying texts on the discourse level. We present a semantically-motivated ATS system which is the first system that is applied on the discourse level. By exploiting the state-of-the-art event extraction system, it is the first ATS system able to eliminate large portions of irrelevant information from texts, by maintaining only those parts of the original text that belong to factual event mentions. A few handcrafted rules ensure that the output of the system is syntactically simple, by placing each factual event mention in a separate short sentence, while the state-of-the-art unsupervised lexical simplification module, based on using word embeddings, replaces complex and infrequent words with their simpler variants. We perform a thorough evaluation, both automatic and manual, showing that our system produces more readable and simpler texts than the state-of-the-art ATS systems. Our newly proposed post-editing evaluation further reveals that our system requires less human effort for correcting grammaticality and meaning preservation on news articles than the state-of-the-art ATS system.

Narratives are comprised of stories that provide insight into social processes. Tofacilitate the analysis of narratives in a more ecient manner, natural languageprocessing (NLP) methods have been employed in order to automatically extractinformation from textual sources, e.g., newspaper articles. Existing workon automatic narrative extraction, however, has ignored the nested characterof narratives. In this work, we argue that a narrative may contain multiple accounts given by dierent actors. Each individual account provides insight intothe beliefs and desires underpinning an actor's actions. We present a pipeline forautomatically extracting accounts, consisting of NLP methods for: (1) namedentity recognition, (2) event extraction, and (3) attribution extraction. Machinelearning-based models for named entity recognition were trained based ona state-of-the-art neural network architecture for sequence labelling. For eventextraction, we developed a hybrid approach combining the use of semantic rolelabelling tools, the FrameNet repository of semantic frames, and a lexicon ofevent nouns. Meanwhile, attribution extraction was addressed with the aid of adependency parser and Levin's verb classes. To facilitate the development andevaluation of these methods, we constructed a new corpus of news articles, inwhich named entities, events and attributions have been manually marked upfollowing a novel annotation scheme that covers over 20 event types relating tosocio-economic phenomena. Evaluation results show that relative to a baselinemethod underpinned solely by semantic role labelling tools, our event extractionapproach optimises recall by 12.22-14.20 percentage points (reaching as high as 92.60% on one data set). Meanwhile, the use of Levin's verb classes in attribution extraction obtains optimal performance in terms of F-score, outperforming a baseline method by 7.64-11.96 percentage points. Our proposed approach was applied on news articles focused on industrial regeneration cases. This facilitated the generation of accounts of events that are attributed to specic actors.

We present an overview of the CLEF-2019 Lab ProtestNews on Extracting Protests from News in the context of generalizable natural language processing. The lab consists of document, sentence, and token level information classification and extraction tasks that were referred as task 1, task 2, and task 3 respectively in the scope of this lab. The tasks required the participants to identify protest relevant information from English local news at one or more aforementioned levels in a cross-context setting, which is cross-country in the scope of this lab. The training and development data were collected from India and test data was collected from India and China. The lab attracted 58 teams to participate in the lab. 12 and 9 of these teams submitted results and working notes respectively. We have observed neural networks yield the best results and the performance drops significantly for majority of the submissions in the cross-country setting, which is China., European Research Council (ERC) Starting Grant; European Union (European Union); Horizon 2020

In this article, we describe a system that reads news articles in four different languages and detects what happened, who is involved, where and when. This event-centric information is represented as episodic situational knowledge on individuals in an interoperable RDF format that allows for reasoning on the implications of the events. Our system covers the complete path from unstructured text to structured knowledge, for which we defined a formal model that links interpreted textual mentions of things to their representation as instances. The model forms the skeleton for interoperable interpretation across different sources and languages. The real content, however, is defined using multilingual and cross-lingual knowledge resources, both semantic and episodic. We explain how these knowledge resources are used for the processing of text and ultimately define the actual content of the episodic situational knowledge that is reported in the news. The knowledge and model in our system can be seen as an example how the Semantic Web helps NLP. However, our systems also generate massive episodic knowledge of the same type as the Semantic Web is built on. We thus envision a cycle of knowledge acquisition and NLP improvement on a massive scale. This article reports on the details of the system but also on the performance of various high-level components. We demonstrate that our system performs at state-of-the-art level for various subtasks in the four languages of the project, but that we also consider the full integration of these tasks in an overall system with the purpose of reading text. We applied our system to millions of news articles, generating billions of triples expressing formal semantic properties. This shows the capacity of the system to perform at an unprecedented scale.

Chinese event extraction uses word embedding to capture similarity, but suffers when handling previously unseen or rare words. From the test, we know that characters may provide some information that we cannot obtain in words, so we propose a novel architecture for combining word representations: character&ndash, word embedding based on attention and semantic features. By using an attention mechanism, our method is able to dynamically decide how much information to use from word or character level embedding. With the semantic feature, we can obtain some more information about a word from the sentence. We evaluate different methods on the CEC Corpus, and this method is found to improve performance.

This paper reports on a set of experiments with different word embeddings to initialize a state-of-the-art Bi-LSTM-CRF network for event detection and classification in Italian, following the EVENTI evaluation exercise. The net- work obtains a new state-of-the-art result by improving the F1 score for detection of 1.3 points, and of 6.5 points for classification, by using a single step approach. The results also provide further evidence that embeddings have a major impact on the performance of such architectures., to appear at CLiC-it 2018

BackgroundFor automated reading of scientific publications to extract useful information about molecular mechanisms it is critical that genes, proteins and other entities be correctly associated with uniform identifiers, a process known as named entity linking or “grounding.” Correct grounding is essential for resolving relationships among mined information, curated interaction databases, and biological datasets. The accuracy of this process is largely dependent on the availability of machine-readable resources associating synonyms and abbreviations commonly found in biomedical literature with uniform identifiers.ResultsIn a task involving automated reading of ∼215,000 articles using the REACH event extraction software we found that grounding was disproportionately inaccurate for multi-protein families (e.g., “AKT”) and complexes with multiple subunits (e.g.”NF-κB”). To address this problem we constructed FamPlex, a manually curated resource defining protein families and complexes as they are commonly encountered in biomedical text. In FamPlex the gene-level constituents of families and complexes are defined in a flexible format allowing for multi-level, hierarchical membership. To create FamPlex, text strings corresponding to entities were identified empirically from literature and linked manually to uniform identifiers; these identifiers were also mapped to equivalent entries in multiple related databases. FamPlex also includes curated prefix and suffix patterns that improve named entity recognition and event extraction. Evaluation of REACH extractions on a test corpus of ∼54,000 articles showed that FamPlex significantly increased grounding accuracy for families and complexes (from 15% to 71%). The hierarchical organization of entities in FamPlex also made it possible to integrate otherwise unconnected mechanistic information across families, subfamilies, and individual proteins. Applications of FamPlex to the TRIPS/DRUM reading system and the Biocreative VI Bioentity Normalization Task dataset demonstrated the utility of FamPlex in other settings.ConclusionFamPlex is an effective resource for improving named entity recognition, grounding, and relationship resolution in automated reading of biomedical text. The content in FamPlex is available in both tabular and Open Biomedical Ontology formats at https://github.com/sorgerlab/famplex under the Creative Commons CC0 license and has been integrated into the TRIPS/DRUM and REACH reading systems.

A formal machine reader is a tool able to transform natural language text into formal structured knowledge so as the latter can be interpreted by machines, according to a shared semantics. FRED is a formal machine reader for the semantic web: its output is a RDF/OWL graph, whose design is based onframe semantics. FRED’s graph are domain- and task-independent, making the tool suitable to be used as a semantic middleware for domain- or task-specific applications. To serve this purpose, it is available both as REST service and as Python library. This paper provides details about FRED’s capabilities, design issues, implementation and evaluation.

Will reading different stories about the same event in the world result in a similar image of the world? Will reading the same story by different people result in a similar proxy for experiencing the story? The answer to both questions is no because language is abstract by definition and relies on our episodic experience to turn a story into a more concrete mental movie. Since our episodic knowledge differs, also the mental movie will be different. Language leaves out details, and this becomes specifically clear when building machines that read texts to represent events and to establish event relations across mentions, such as co-reference, causality, subevents, scripts, timelines, and storylines. There is a lot of information and knowledge on the event that is not in the text but is needed to reconstruct these relations and understand the story. Machines lack this knowledge and experience and likewise make explicit what it takes to understand stories from text. In this paper, we report on experiments to automatically model event descriptions and instances across different news articles. We will show that event information is scattered over the text but also varies a lot in the degree it abstracts from details, which makes establishing event identity and relations extremely difficult. The variation in granularity of event descriptions seems to vary with pragmatic communicative strategies and defines the problem at different levels of complexity.

With the number of documents describing real-world events and event-oriented information needs rapidly growing on a daily basis, the need for efficient retrieval and concise presentation of event-related information is becoming apparent. Nonetheless, the majority of information retrieval and text summarization methods rely on shallow document representations that do not account for the semantics of events. In this article, we present event graphs, a novel event-based document representation model that filters and structures the information about events described in text. To construct the event graphs, we combine machine learning and rule-based models to extract sentence-level event mentions and determine the temporal relations between them. Building on event graphs, we present novel models for information retrieval and multi-document summarization. The information retrieval model measures the similarity between queries and documents by computing graph kernels over event graphs. The extractive multi-document summarization model selects sentences based on the relevance of the individual event mentions and the temporal structure of events. Experimental evaluation shows that our retrieval model significantly outperforms well-established retrieval models on event-oriented test collections, while the summarization model outperforms competitive models from shared multi-document summarization tasks.

Background Biomedical event extraction is one of the key tasks in biomedical text mining, supporting various applications such as database curation and hypothesis generation. Several systems, some of which have been applied at a large scale, have been introduced to solve this task. Past studies have shown that the identification of the phrases describing biological processes, also known as trigger detection, is a crucial part of event extraction, and notable overall performance gains can be obtained by solely focusing on this sub-task. In this paper we propose a novel approach for filtering falsely identified triggers from large-scale event databases, thus improving the quality of knowledge extraction. Methods Our method relies on state-of-the-art word embeddings, event statistics gathered from the whole biomedical literature, and both supervised and unsupervised machine learning techniques. We focus on EVEX, an event database covering the whole PubMed and PubMed Central Open Access literature containing more than 40 million extracted events. The top most frequent EVEX trigger words are hierarchically clustered, and the resulting cluster tree is pruned to identify words that can never act as triggers regardless of their context. For rarely occurring trigger words we introduce a supervised approach trained on the combination of trigger word classification produced by the unsupervised clustering method and manual annotation. Results The method is evaluated on the official test set of BioNLP Shared Task on Event Extraction. The evaluation shows that the method can be used to improve the performance of the state-of-the-art event extraction systems. This successful effort also translates into removing 1,338,075 of potentially incorrect events from EVEX, thus greatly improving the quality of the data. The method is not solely bound to the EVEX resource and can be thus used to improve the quality of any event extraction system or database. Availability The data and source code for this work are available at: http://bionlp-www.utu.fi/trigger-clustering/. Electronic supplementary material The online version of this article (doi:10.1186/s13326-016-0070-4) contains supplementary material, which is available to authorized users.

Event extraction, a specialized stream of information extraction rooted back into the 1980s, has greatly gained in popularity due to the advent of big data and the developments in the related fields of text mining and natural language processing. However, up to this date, an overview of this particular field remains elusive. Therefore, we give a summarization of event extraction techniques for textual data, distinguishing between data-driven, knowledge-driven, and hybrid methods, and present a qualitative evaluation of these. Moreover, we discuss common decision support applications of event extraction from text corpora. Last, we elaborate on the evaluation of event extraction systems and identify current research issues. We identify data-driven, knowledge-driven, and hybrid event extraction approaches.A wide variety of decision support applications can benefit from event extraction.Pressing research issues to be addressed are scalability and domain dependencies.Evaluation with annotated data from standard benchmarks or crowdsourcing is advised.

Events play an important role in natural language processing and information retrieval due to numerous event-oriented texts and information needs. Many natural language processing and information retrieval applications could benefit from a structured event-oriented document representation. In this paper, we proposeevent graphsas a novel way of structuring event-based information from text. Nodes in event graphs represent the individual mentions of events, whereas edges represent the temporal and coreference relations between mentions. Contrary to previous natural language processing research, which has mainly focused on individual event extraction tasks, we describe a complete end-to-end system for event graph extraction from text. Our system is a three-stage pipeline that performs anchor extraction, argument extraction, and relation extraction (temporal relation extraction and event coreference resolution), each at a performance level comparable with the state of the art. We presentEvExtra, a large newspaper corpus annotated with event mentions and event graphs, on which we train and evaluate our models. To measure the overall quality of the constructed event graphs, we propose two metrics based on the tensor product between automatically and manually constructed graphs. Finally, we evaluate the overall quality of event graphs with the proposed evaluation metrics and perform a headroom analysis of the system.

Conference of 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 ; Conference Date: 25 October 2014 Through 29 October 2014; Conference Code:111414; International audience; The efficiency of Information Extraction systems is known to be heavily influenced by domain-specific knowledge but the cost of developing such systems is considerably high. In this article, we consider the problem of event extraction and show that learning word representations from unlabeled domain-specific data and using them for representing event roles enable to outperform previous state-of-the-art event extraction models on the MUC-4 data set.

Because event mentions in text may be referentially ambiguous, event coreferentiality often involves uncertainty. In this paper we consider event coreference uncertainty and explore how it is affected by the context. We develop a supervised event coreference resolution model based on the comparison of generically extracted event mentions. We analyse event coreference uncertainty in both human annotations and predictions of the model, and in both within- document and cross-document setting. We frame event coreference as a classification task when full context is available and no uncertainty is involved, and a regression task in a limited context setting that involves uncertainty. We show how a rich set of features based on argument comparison can be utilized in both settings. Experimental results on English data suggest that our approach is especially suitable for resolving cross-document event coreference. Results also suggest that modelling human coreference uncertainty in the case of limited context is feasible.

BackgroundBio-molecular event extraction from literature is recognized as an important task of bio text mining and, as such, many relevant systems have been developed and made available during the last decade. While such systems provide useful services individually, there is a need for a meta-service to enable comparison and ensemble of such services, offering optimal solutions for various purposes.ResultsWe have integrated nine event extraction systems in the U-Compare framework, making them inter-compatible and interoperable with other U-Compare components. The U-Compare event meta-service provides various meta-level features for comparison and ensemble of multiple event extraction systems. Experimental results show that the performance improvements achieved by the ensemble are significant. ConclusionsWhile individual event extraction systems themselves provide useful features for bio text mining, the U-Compare meta-service is expected to improve the accessibility to the individual systems, and to enable meta-level uses over multiple event extraction systems such as comparison and ensemble., This research was partially supported by KAKENHI 18002007 [YK, MM, JDK, SP, TO, JT]; JST PRESTO and KAKENHI 21500130 [YK]; the Academy of Finland and computational resources were provided by CSC -- IT Center for Science Ltd [JB, FG]; the Research Foundation Flanders (FWO) [SVL]; UK Biotechnology and Biological Sciences, Research Council (BBSRC project BB/G013160/1 Automated Biological Event Extraction from the Literature for Drug Discovery) and JISC, National Centre for Text Mining [SA]; the Spanish grant BIO2010-17527 [MN, APM]; NIH Grant U54 DA021519 [AO, DRR]

Background The Turku Event Extraction System (TEES) is a text mining program developed for the extraction of events, complex biomedical relationships, from scientific literature. Based on a graph-generation approach, the system detects events with the use of a rich feature set built via dependency parsing. The TEES system has achieved record performance in several of the shared tasks of its domain, and continues to be used in a variety of biomedical text mining tasks. Results The TEES system was quickly adapted to the BioNLP'13 Shared Task in order to provide a public baseline for derived systems. An automated approach was developed for learning the underlying annotation rules of event type, allowing immediate adaptation to the various subtasks, and leading to a first place in four out of eight tasks. The system for the automated learning of annotation rules is further enhanced in this paper to the point of requiring no manual adaptation to any of the BioNLP'13 tasks. Further, the scikit-learn machine learning library is integrated into the system, bringing a wide variety of machine learning methods usable with TEES in addition to the default SVM. A scikit-learn ensemble method is also used to analyze the importances of the features in the TEES feature sets. Conclusions The TEES system was introduced for the BioNLP'09 Shared Task and has since then demonstrated good performance in several other shared tasks. By applying the current TEES 2.2 system to multiple corpora from these past shared tasks an overarching analysis of the most promising methods and possible pitfalls in the evolving field of biomedical event extraction are presented.

Background Modern methods for mining biomolecular interactions from literature typically make predictions based solely on the immediate textual context, in effect a single sentence. No prior work has been published on extending this context to the information automatically gathered from the whole biomedical literature. Thus, our motivation for this study is to explore whether mutually supporting evidence, aggregated across several documents can be utilized to improve the performance of the state-of-the-art event extraction systems. In this paper, we describe our participation in the latest BioNLP Shared Task using the large-scale text mining resource EVEX. We participated in the Genia Event Extraction (GE) and Gene Regulation Network (GRN) tasks with two separate systems. In the GE task, we implemented a re-ranking approach to improve the precision of an existing event extraction system, incorporating features from the EVEX resource. In the GRN task, our system relied solely on the EVEX resource and utilized a rule-based conversion algorithm between the EVEX and GRN formats. Results In the GE task, our re-ranking approach led to a modest performance increase and resulted in the first rank of the official Shared Task results with 50.97% F-score. Additionally, in this paper we explore and evaluate the usage of distributed vector representations for this challenge. In the GRN task, we ranked fifth in the official results with a strict/relaxed SER score of 0.92/0.81 respectively. To try and improve upon these results, we have implemented a novel machine learning based conversion system and benchmarked its performance against the original rule-based system. Conclusions For the GRN task, we were able to produce a gene regulatory network from the EVEX data, warranting the use of such generic large-scale text mining data in network biology settings. A detailed performance and error analysis provides more insight into the relatively low recall rates. In the GE task we demonstrate that both the re-ranking approach and the word vectors can provide slight performance improvement. A manual evaluation of the re-ranking results pinpoints some of the challenges faced in applying large-scale text mining knowledge to event extraction.