KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision

  title={KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision},
  author={Xinyu Zuo and Yubo Chen and Kang Liu and Jun Zhao},
Modern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora. However, hand-labeled training data is expensive to produce, low coverage of causal expressions, and limited in size, which makes supervised methods hard to detect causal relations between events. To solve this data lacking problem, we investigate a data augmentation framework for ECD, dubbed as Knowledge Enhanced Distant Data Augmentation (KnowDis). Experimental results on… 

Figures and Tables from this paper

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

This work introduces a new approach to augment training data for event causality identification, by iteratively generating new examples and classifyingevent causality in a dual learning framework, which can leverage existing knowledge bases to generate well-formed new sentences.

Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement

This work proposes a novel approach, shortly named CauSeRL, which leverages external causal statements for event causality identification by designing a self-supervised framework and adopting a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model.

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

This work proposes a novel Latent Structure Induction Network (LSIN) to incorporate the external structural knowledge into this task and devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge.

Event Causality Identification via Generation of Important Context Words

This work considers the words along the dependency path between the two event mentions in the dependency tree as the important context words for ECI and proposes to use the REINFORCE algorithm to train the generative model.

Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures

This work develops a novel deep learning model for document-level ECI (DECI) to accept inter-sentence event mention pairs, and proposes a graph-based model that constructs interaction graphs to capture relevant connections between important objects for DECI in input documents.

Towards Event-level Causal Relation Identification

This work proposes a model that achieves the best performance under both mention- and event-level settings, outperforming a number of strong baselines by at least 2.8% on F1 score.

ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification

A novel ERGO framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects and seamlessly integrates event-pair relation classification and global inference, which leverages a Relational Graph Transformer (RGT) to capture the potential causal chain.

A survey of the extraction and applications of causal relations

A comprehensive survey of the work on the extraction of causal relations and their applications, while also discussing the nature of causation and its representation in text.

Data Augmentation Approaches in Natural Language Processing: A Survey



Automatically Labeled Data Generation for Large Scale Event Extraction

This work proposes to automatically label training data for event extraction via world knowledge and linguistic knowledge, which can detect key arguments and trigger words for each event type and employ them to label events in texts automatically.

Logic-Guided Data Augmentation and Regularization for Consistent Question Answering

This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models by leveraging logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model.

Toward Future Scenario Generation: Extracting Event Causality Exploiting Semantic Relation, Context, and Association Features

A supervised method of extracting event causalities like conduct slash-and-burn agriculture! exacerbate desertification from the web using semantic relation, context, and association features, which outperforms baselines that are based on state-of-the-art methods.

Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths

This work borrows a state-of-the-art method in relation extraction by adopting bidirectional long short-term memory along dependency paths (DP), and makes a “common root” assumption to extend DP representations of cross-sentence links.

Towards Causal Explanation Detection with Pyramid Salient-Aware Network

A Pyramid Salient-Aware Network (PSAN) is designed to detect causal explanations on messages and can modify the dominance of discourses via a top attention-based discourse-level salient network to enhance explanatory semantics of messages.

CATENA: CAusal and TEmporal relation extraction from NAtural language texts

We present CATENA, a sieve-based system to perform temporal and causal relation extraction and classification from English texts, exploiting the interaction between the temporal and the causal model.

Distant supervision for relation extraction without labeled data

This work investigates an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size.

The Event StoryLine Corpus: A New Benchmark for Causal and Temporal Relation Extraction

This paper reports on the Event StoryLine Corpus (ESC) v1.0, a new benchmark dataset for the temporal and causal relation detection, and reports on three baselines systems whose results show the complexity of the task and suggest directions for the development of more robust systems.

Commonsense Causal Reasoning between Short Texts

A framework that automatically harvests a network of causal-effect terms from a large web corpus is proposed that outperforms all previously reported results in the standard SE-MEVAL COPA task by substantial margins.

Multi-Column Convolutional Neural Networks with Causality-Attention for Why-Question Answering

This work improves why-QA based on the following two ideas: implicitly expressed causalities in one text might be expressed in other texts with explicit cues, and the causes of similar events tend to be described with a similar set of words that appear in the explicitly expressed cause of a similar event.