Related papers: Graph-Based Decoding for Event Sequencing and Core…
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A. Our visual context tree model, dubbed VCTree, has two key…
Chain Event Graphs (CEGs) are a recent family of probabilistic graphical models - a generalisation of Bayesian Networks - providing an explicit representation of structural zeros, structural missing values and context-specific conditional…
To understand a document with multiple events, event-event relation extraction (ERE) emerges as a crucial task, aiming to discern how natural events temporally or structurally associate with each other. To achieve this goal, our work…
Building unified timelines from a collection of written news articles requires cross-document event coreference resolution and temporal relation extraction. In this paper we present an approach event coreference resolution according to: a)…
We present two architectures for multi-task learning with neural sequence models. Our approach allows the relationships between different tasks to be learned dynamically, rather than using an ad-hoc pre-defined structure as in previous…
Pretext training followed by task-specific fine-tuning has been a successful approach in vision and language domains. This paper proposes a self-supervised pretext training framework tailored to event sequence data. We introduce a novel…
In the era of graph-based retrieval-augmented generation (RAG), link prediction is a significant preprocessing step for improving the quality of fragmented or incomplete domain-specific data for the graph retrieval. Knowledge management in…
Document-level event extraction (DEE) faces two main challenges: arguments-scattering and multi-event. Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sentences during event…
Dependency trees help relation extraction models capture long-range relations between words. However, existing dependency-based models either neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively, or…
Document-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. It poses a great challenge of across-sentence reasoning without clear causal indicators. In this paper, we propose a…
Graphs or networks are a very convenient way to represent data with lots of interaction. Recently, Machine Learning on Graph data has gained a lot of traction. In particular, vertex classification and missing edge detection have very…
Event-based sensors offer high temporal resolution and low latency by generating sparse, asynchronous data. However, converting this irregular data into dense tensors for use in standard neural networks diminishes these inherent advantages,…
Event sequences often emerge in data mining. Modeling these sequences presents two main challenges: methodological and computational. Methodologically, event sequences are non-uniform and sparse, making traditional models unsuitable.…
Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a recurrent neural network. In this paper, we propose an…
This paper presents our submission to the 2022 edition of the CASE 2021 shared task 1, subtask 4. The EventGraph system adapts an end-to-end, graph-based semantic parser to the task of Protest Event Extraction and more specifically subtask…
Bi-encoder architectures for distantly-supervised relation extraction are designed to make use of the complementary information found in text and knowledge graphs (KG). However, current architectures suffer from two drawbacks. They either…
Script knowledge plays a central role in text understanding and is relevant for a variety of downstream tasks. In this paper, we consider two recent datasets which provide a rich and general representation of script events in terms of…
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph…
One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs. However, coreferent mentions usually spread far apart in an entire text, which…
Recent works have introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE), since AMR provides a useful interpretation of complex semantic structures and helps to capture long-distance…