Causality extraction based on self-attentive BiLSTM-CRF with transferred embeddings
Reads0
Chats0
TLDR
This paper formulate causality extraction as a sequence labeling problem based on a novel causality tagging scheme, and proposes a neural causality extractor with the BiLSTM-CRF model as the backbone, named SCITE (Self-attentive BiL STM- CRF wIth Transferred Embeddings), which can directly extract cause and effect without extracting candidate causal pairs and identifying their relations separately.About:
This article is published in Neurocomputing.The article was published on 2021-01-29 and is currently open access. It has received 80 citations till now. The article focuses on the topics: Causality (physics) & Sequence labeling.read more
Citations
More filters
Proceedings ArticleDOI
CauseNet: Towards a Causality Graph Extracted from the Web
TL;DR: CauseNet is compiled, a large-scale knowledge base of claimed causal relations between causal concepts and the first large- scale and open-domain causality graph is constructed, to gain insights about causal beliefs expressed on the web.
Posted Content
Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning
TL;DR: A new dataset of 1,500 scientific abstracts from the biomedical domain with expert annotations for each sentence indicating whether the sentence presents a scientific claim is introduced, and a new model for claim extraction is introduced and compared to several baseline models including rule-based and deep learning techniques.
Posted Content
A Survey on Extraction of Causal Relations from Natural Language Text.
TL;DR: The authors conducted a comprehensive survey of causality extraction techniques, including knowledge-based, statistical machine learning (ML)-based, and deep learning-based approaches, and highlighted existing open challenges with their potential directions.
Book ChapterDOI
Inter-sentence and Implicit Causality Extraction from Chinese Corpus.
TL;DR: Cascaded multi-Structure Neural Network (CSNN) is proposed, a novel and unified model that extract inter-sentence or implicit causal relations from Chinese Corpus, without relying on external knowledge.
Posted Content
A Multi-level Neural Network for Implicit Causality Detection in Web Texts.
TL;DR: A neural causality detection model, namely Multi-level Causality Detection Network (MCDN), which adopts multi-head self-attention to acquire semantic feature at word level and integrates a novel Relation Network to infer causality at segment level.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.