Knowledge Enhanced LSTM for Coreference Resolution on Biomedical Texts

2021 ◽  
Author(s):  
Yufei Li ◽  
Xiaoyong Ma ◽  
Xiangyu Zhou ◽  
Pengzhen Cheng ◽  
Kai He ◽  
...  
Keyword(s):  
Information Integration ◽  
Short Term Memory ◽  
Superior Performance ◽  
Supplementary Information ◽  
Specific Information ◽  
Coreference Resolution ◽  
Fine Grained ◽  
Domain Specific ◽  
Memory Network ◽  
Biomedical Texts

Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this paper, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Context-Aware Feature Attention Model for Coreference Resolution on Biomedical Texts

2021 ◽  
Author(s):  
Yufei Li ◽  
Xiangyu Zhou ◽  
Jie Ma ◽  
Xiaoyong Ma ◽  
Chen Li
Keyword(s):  
Information Integration ◽  
Superior Performance ◽  
Specific Information ◽  
Coreference Resolution ◽  
Context Aware ◽  
Attention Model ◽  
Fine Grained ◽  
Domain Specific ◽  
Feature Attention ◽  
Biomedical Texts

Abstract Background: Bio-entity Coreference resolution is an important task to gain a complete understanding of biomedical texts automatically. Previous neural network-based studies on this topic are domain system based methods which rely on some domain-specific information integration. However, for the identical mentions, this may lead to misleading information, as the model tends to get similar or even identical representations, which further leads to wrongful predictions. Results: we propose a new context-aware Feature Attention model to distinguish identical mentions effectively to better resolve coreference. The new model can represent identical mentions based on different contexts by adaptively exploiting features effectively. The proposed model substantially outperforms the state-of-the-art baselines on the BioNLP dataset with a 64.0% F1 score and further demonstrates superior performance on the differential representation and coreferential link of identical mentions. Conclusion: The context-aware Feature Attention model adaptively exploit features and represent identical mentions according to different contexts, which significantly makes the system obtain semantic information effectively and make more accurate predictions. Considering that this approach is still limited when context information is insufficient, we expect to utilize such information more fine-grained with the help of the external knowledge base in coreference resolution.

scholarly journals Context awareness and embedding for biomedical event extraction

2019 ◽  
Author(s):  
Shankai Yan ◽  
Ka-Chun Wong
Keyword(s):  
Short Term Memory ◽  
Event Extraction ◽  
Supplementary Information ◽  
Short Term ◽  
Biomedical Knowledge ◽  
Biomedical Event Extraction ◽  
Training Event ◽  
Memory Network ◽  
Long Short Term Memory ◽  
Massive Information

Abstract Motivation Biomedical event extraction is fundamental for information extraction in molecular biology and biomedical research. The detected events form the central basis for comprehensive biomedical knowledge fusion, facilitating the digestion of massive information influx from the literature. Limited by the event context, the existing event detection models are mostly applicable for a single task. A general and scalable computational model is desiderated for biomedical knowledge management. Results We consider and propose a bottom-up detection framework to identify the events from recognized arguments. To capture the relations between the arguments, we trained a bidirectional long short-term memory network to model their context embedding. Leveraging the compositional attributes, we further derived the candidate samples for training event classifiers. We built our models on the datasets from BioNLP Shared Task for evaluations. Our method achieved the average F-scores of 0.81 and 0.92 on BioNLPST-BGI and BioNLPST-BB datasets, respectively. Comparing with seven state-of-the-art methods, our method nearly doubled the existing F-score performance (0.92 versus 0.56) on the BioNLPST-BB dataset. Case studies were conducted to reveal the underlying reasons. Availability and implementation https://github.com/cskyan/evntextrc. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Stock Trend Prediction Using Deep Learning Approach on Technical Indicator and Industrial Specific Information

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 250
Author(s):  
Kittisak Prachyachuwong ◽  
Peerapon Vateekul
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Model Performance ◽  
Specific Information ◽  
Trend Prediction ◽  
Textual Information ◽  
Economic News ◽  
Technical Indicator ◽  
Memory Network

A stock trend prediction has been in the spotlight from the past to the present. Fortunately, there is an enormous amount of information available nowadays. There were prior attempts that have tried to forecast the trend using textual information; however, it can be further improved since they relied on fixed word embedding, and it depends on the sentiment of the whole market. In this paper, we propose a deep learning model to predict the Thailand Futures Exchange (TFEX) with the ability to analyze both numerical and textual information. We have used Thai economic news headlines from various online sources. To obtain better news sentiment, we have divided the headlines into industry-specific indexes (also called “sectors”) to reflect the movement of securities of the same fundamental. The proposed method consists of Long Short-Term Memory Network (LSTM) and Bidirectional Encoder Representations from Transformers (BERT) architectures to predict daily stock market activity. We have evaluated model performance by considering predictive accuracy and the returns obtained from the simulation of buying and selling. The experimental results demonstrate that enhancing both numerical and textual information of each sector can improve prediction performance and outperform all baselines.

scholarly journals Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers

2020 ◽  
Vol 36 (16) ◽  
pp. 4458-4465 ◽  
Author(s):  
Ruichu Cai ◽  
Xuexin Chen ◽  
Yuan Fang ◽  
Min Wu ◽  
Yuexing Hao
Keyword(s):  
Link Prediction ◽  
Synthetic Lethality ◽  
Gene Interaction ◽  
Superior Performance ◽  
Coarse Grained ◽  
Supplementary Information ◽  
Convolutional Network ◽  
Sparse Graphs ◽  
Fine Grained ◽  
Convolutional Networks

Abstract Motivation Synthetic lethality (SL) is a promising form of gene interaction for cancer therapy, as it is able to identify specific genes to target at cancer cells without disrupting normal cells. As high-throughput wet-lab settings are often costly and face various challenges, computational approaches have become a practical complement. In particular, predicting SLs can be formulated as a link prediction task on a graph of interacting genes. Although matrix factorization techniques have been widely adopted in link prediction, they focus on mapping genes to latent representations in isolation, without aggregating information from neighboring genes. Graph convolutional networks (GCN) can capture such neighborhood dependency in a graph. However, it is still challenging to apply GCN for SL prediction as SL interactions are extremely sparse, which is more likely to cause overfitting. Results In this article, we propose a novel dual-dropout GCN (DDGCN) for learning more robust gene representations for SL prediction. We employ both coarse-grained node dropout and fine-grained edge dropout to address the issue that standard dropout in vanilla GCN is often inadequate in reducing overfitting on sparse graphs. In particular, coarse-grained node dropout can efficiently and systematically enforce dropout at the node (gene) level, while fine-grained edge dropout can further fine-tune the dropout at the interaction (edge) level. We further present a theoretical framework to justify our model architecture. Finally, we conduct extensive experiments on human SL datasets and the results demonstrate the superior performance of our model in comparison with state-of-the-art methods. Availability and implementation DDGCN is implemented in Python 3.7, open-source and freely available at https://github.com/CXX1113/Dual-DropoutGCN. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Response Time, Visual Search Strategy, and Anticipatory Skills in Volleyball Players

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Alessandro Piras ◽  
Roberto Lobietti ◽  
Salvatore Squatrito
Keyword(s):  
Response Time ◽  
Search Strategy ◽  
Superior Performance ◽  
Specific Information ◽  
Eye Tracker ◽  
Domain Specific ◽  
Visuomotor Task ◽  
Volleyball Players ◽  
Ball Contact ◽  
Gaze Behaviour

This paper aimed at comparing expert and novice volleyball players in a visuomotor task using realistic stimuli. Videos of a volleyball setter performing offensive action were presented to participants, while their eye movements were recorded by a head-mounted video based eye tracker. Participants were asked to foresee the direction (forward or backward) of the setter’s toss by pressing one of two keys. Key-press response time, response accuracy, and gaze behaviour were measured from the first frame showing the setter’s hand-ball contact to the button pressed by the participants. Experts were faster and more accurate in predicting the direction of the setting than novices, showing accurate predictions when they used a search strategy involving fewer fixations of longer duration, as well as spending less time in fixating all display areas from which they extract critical information for the judgment. These results are consistent with the view that superior performance in experts is due to their ability to efficiently encode domain-specific information that is relevant to the task.

Sign in / Sign up

Export Citation Format

Share Document