Hierarchical Event Grounding

Theory and Applications of Categories, 2017

After two successful years of Event Nugget evaluation in the TAC KBP workshop, the third Event Nugget evaluation track for Knowledge Base Population(KBP) still attracts a lot of attention from the field. In addition to the traditional event nugget and coreference tasks, we introduce a new event sequencing task in English. The new task has brought more complex event relation reasoning to the current evaluations. In this paper we try to provide an overview on the task definition, data annotation, evaluation and trending research methods. We further discuss our efforts in creating the new event sequencing task and interesting research problems related to it.

Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), 2021

This paper studies the problem of crossdocument event coreference resolution (CDECR) that seeks to determine if event mentions across multiple documents refer to the same real-world events. Prior work has demonstrated the benefits of the predicateargument information and document context for resolving the coreference of event mentions. However, such information has not been captured effectively in prior work for CDECR. To address these limitations, we propose a novel deep learning model for CDECR that introduces hierarchical graph convolutional neural networks (GCN) to jointly resolve entity and event mentions. As such, sentencelevel GCNs enable the encoding of important context words for event mentions and their arguments while the document-level GCN leverages the interaction structures of event mentions and arguments to compute document representations to perform CDECR. Extensive experiments are conducted to demonstrate the effectiveness of the proposed model.

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains. Among event mentions in the same chain, we distinguish within-and cross-document event coreference links by using two distinct pairwise classifiers, trained separately to capture differences in feature distributions of within-and crossdocument event clusters. Our event coreference approach alternates between WD and CD clustering and combines arguments from both event clusters after every merge, continuing till no more merge can be made. And then it performs further merging between event chains that are both closely related to a set of other chains of events. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods in joint task of WD and CD event coreference resolution.

Advances in Knowledge Discovery and Data Mining, 2021

Event Argument Extraction (EAE) is the task of identifying roles of entity mentions/arguments in events evoked by trigger words. Most existing works have focused on sentence-level EAE, leaving documentlevel EAE (i.e., event triggers and arguments belong to different sentences in documents) an under-studied problem in the literature. This paper introduces a new deep learning model for document-level EAE where document structures/graphs are utilized to represent input documents and aid the representation learning. Our model employs different types of interactions between important context words in documents (i.e., syntax, semantic, and discourse) to enhance document representations. Extensive experiments are conducted to demonstrate the effectiveness of the proposed model, leading to the state-of-the-art performance for document-level EAE.

Lecture Notes in Computer Science, 2011

Many attempts have been made to extract structured data from Web resources, exposing them as RDF triples and interlinking them with other RDF datasets: in this way it is possible to create clouds of highly integrated Semantic Web data collections. In this paper we describe an approach to enhance the extraction of semantic contents from unstructured textual documents, in particular considering Wikipedia articles and focusing on event mining. Starting from the deep parsing of a set of English Wikipedia articles, we produce a semantic annotation compliant with the Knowledge Annotation Format (KAF). We extract events from the KAF semantic annotation and then we structure each event as a set of RDF triples linked to both DBpedia and WordNet. We point out examples of automatically mined events, providing some general evaluation of how our approach may discover new events and link them to existing contents.

Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with ACL 2016 (LAW-X 2016), 2016

We propose a new task of extracting eventevent relations across documents. We present our efforts at designing an annotation schema and building a corpus for this task. Our schema includes five main types of relations: Inheritance, Expansion, Contingency, Comparison and Temporality, along with 21 subtypes. We also lay out the main challenges based on detailed inter-annotator disagreement and error analysis. We hope these resources can serve as a benchmark to encourage research on this new problem.

Proceedings of the AAAI Conference on Artificial Intelligence

Understanding events entails recognizing the structural and temporal orders between event mentions to build event structures/graphs for input documents. To achieve this goal, our work addresses the problems of subevent relation extraction (SRE) and temporal event relation extraction (TRE) that aim to predict subevent and temporal relations between two given event mentions/triggers in texts. Recent state-of-the-art methods for such problems have employed transformer-based language models (e.g., BERT) to induce effective contextual representations for input event mention pairs. However, a major limitation of existing transformer-based models for SRE and TRE is that they can only encode input texts of limited length (i.e., up to 512 sub-tokens in BERT), thus unable to effectively capture important context sentences that are farther away in the documents. In this work, we introduce a novel method to better model document-level context with important context sentences for event-event rel...

2020

Event extraction (EE) is one of the core information extraction tasks, whose purpose is to automatically identify and extract information about incidents and their actors from texts. This may be beneficial to several domains such as knowledge bases, question answering, information retrieval and summarization tasks, to name a few. The problem of extracting event information from texts is longstanding and usually relies on elaborately designed lexical and syntactic features, which, however, take a large amount of human effort and lack generalization. More recently, deep neural network approaches have been adopted as a means to learn underlying features automatically. However, existing networks do not make full use of syntactic features, which play a fundamental role in capturing very long-range dependencies. Also, most approaches extract each argument of an event separately without considering associations between arguments which ultimately leads to low efficiency, especially in sente...

2022

We present a task of multilingual linking of events to a knowledge base. We automatically compile a large-scale dataset for this task, comprising of 1.8M mentions across 44 languages referring to over 10.9K events from Wikidata. We propose two variants of the event linking task: 1) multilingual, where event descriptions are from the same language as the mention, and 2) crosslingual, where all event descriptions are in English. On the two proposed tasks, we compare multiple event linking systems including BM25+ (Lv and Zhai, 2011a) and multilingual adaptations of the biencoder and crossencoder architectures from BLINK . In our experiments on the two task variants, we find both biencoder and crossencoder models significantly outperform the BM25+ baseline. Our results also indicate that the crosslingual task is in general more challenging than the multilingual task. To test the out-of-domain generalization of the proposed linking systems, we additionally create a Wikinews-based evaluation set. We present qualitative analysis highlighting various aspects captured by the proposed dataset, including the need for temporal reasoning over context and tackling diverse event descriptions across languages. 1

arXiv (Cornell University), 2021

In this paper, we study the identity of textual events from different documents. While the complex nature of event identity is previously studied , the case of events across documents is unclear. Prior work on cross-document event coreference has two main drawbacks. First, they restrict the annotations to a limited set of event types. Second, they insufficiently tackle the concept of event identity. Such annotation setup reduces the pool of event mentions and prevents one from considering the possibility of quasiidentity relations. We propose a dense annotation approach for cross-document event coreference, comprising a rich source of event mentions and a dense annotation effort between related document pairs. To this end, we design a new annotation workflow with careful quality control and an easy-to-use annotation interface. In addition to the links, we further collect overlapping event contexts, including time, location, and participants, to shed some light on the relation between identity decisions and context. We present an open-access dataset for cross-document event coreference, CDEC-WN, collected from English Wikinews and open-source our annotation toolkit to encourage further research on cross-document tasks. 1