Selecting Optimal Context Sentences for Event-Event Relation Extraction

Abstract

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 relation extraction. Our method seeks to identify the most important context sentences for a given entity mention pair in a document and pack them into shorter documents to be consume entirely by transformer-based language models for representation learning. The REINFORCE algorithm is employed to train models where novel reward functions are presented to capture model performance, and context-based and knowledge-based similarity between sentences for our problem. Extensive experiments demonstrate the effectiveness of the proposed method with state-of-the-art performance on benchmark datasets.

Extracting Temporal Relationships of Chinese Events Based on Graph Representation Learning

“…Early studies on event temporal relation extraction (Chambers et al, 2007) primarily focused on dependency parsing within sentences and various linguistic features such as part-of-speech tags, tense, and other features. Subsequent work (Man et al, 2022) combined reinforcement learning with deep learning. They used reinforcement learning to select important sentences in a document that had a relatively significant impact on predictions.…”

A Novel Scheme for Generating Context-Aware Images Using Generative Artificial Intelligence

“…Recently, with the increased prevalence of artificial intelligence applications, there has been a surge in studies focusing on understanding context through artificial intelligence. Reference [13] conducted a study incorporating optimal sentences containing context within multiple sentences to identify correlations between events. In [13], the objective was not to extract individual contexts from multiple sentences but to extract contexts that represent the entirety of multiple sentences.…”

“…Reference [13] conducted a study incorporating optimal sentences containing context within multiple sentences to identify correlations between events. In [13], the objective was not to extract individual contexts from multiple sentences but to extract contexts that represent the entirety of multiple sentences. This study has the potential to complement our research.…”

“…When dealing with a vast number of input sentences, generating images for each might be inefficient. In such cases, [13] could offer an efficient approach. Similarly, [14] is a related study.…”

Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction

“…BEFORE and AFTER that follow the arrows denote the extracted TEMPREL's from the sentences by . advanced learning and inference techniques such as structured prediction (Ning et al, 2017(Ning et al, , 2018bHan et al, 2019;Tan et al, 2021), graph representation (Mathur et al, 2021;Zhang et al, 2022), data augmentation (Ballesteros et al, 2020;Trong et al, 2022), and indirect supervision (Zhao et al, 2021;. These models are prevalently built upon pretrained language models (PLMs) and fine-tuned on a small set of annotated documents, e.g., TimeBank-Dense (Cassidy et al, 2014), MATRES (Ning et al, 2018c), and TDDiscourse (Naik et al, 2019).…”