A transformer-based approach to irony and sarcasm detection

AbstractFigurative language (FL) seems ubiquitous in all social media discussion forums and chats, posing extra challenges to sentiment analysis endeavors. Identification of FL schemas in short texts remains largely an unresolved issue in the broader field of natural language processing, mainly due to their contradictory and metaphorical meaning content. The main FL expression forms are sarcasm, irony and metaphor. In the present paper, we employ advanced deep learning methodologies to tackle the problem of identifying the aforementioned FL forms. Significantly extending our previous work (Potamias et al., in: International conference on engineering applications of neural networks, Springer, Berlin, pp 164–175, 2019), we propose a neural network methodology that builds on a recently proposed pre-trained transformer-based network architecture which is further enhanced with the employment and devise of a recurrent convolutional neural network. With this setup, data preprocessing is kept in minimum. The performance of the devised hybrid neural architecture is tested on four benchmark datasets, and contrasted with other relevant state-of-the-art methodologies and systems. Results demonstrate that the proposed methodology achieves state-of-the-art performance under all benchmark datasets, outperforming, even by a large margin, all other methodologies and published studies.

Download Full-text

Learning Multi-Level Dependencies for Robust Word Recognition

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6463 ◽

2020 ◽

Vol 34 (05) ◽

pp. 9250-9257

Author(s):

Zhiwei Wang ◽

Hui Liu ◽

Jiliang Tang ◽

Songfan Yang ◽

Gale Yan Huang ◽

...

Keyword(s):

Neural Network ◽

Word Recognition ◽

Language Processing ◽

State Of The Art ◽

Learning Models ◽

Large Margin ◽

Sequential Dependencies ◽

Word Level ◽

Multi Level ◽

Machine Learning Models

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a robust word recognition framework that captures multi-level sequential dependencies in noised sentences. The proposed framework employs a sequence-to-sequence model over characters of each word, whose output is given to a word-level bi-directional recurrent neural network. We conduct extensive experiments to verify the effectiveness of the framework. The results show that the proposed framework outperforms state-of-the-art methods by a large margin and they also suggest that character-level dependencies can play an important role in word recognition. The code of the proposed framework and the major experiments are publicly available1.

Download Full-text

Drug-Drug Interaction Predicting by Neural Network Using Integrated Similarity

Scientific Reports ◽

10.1038/s41598-019-50121-3 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 10

Author(s):

Narjes Rohani ◽

Changiz Eslahchi

Keyword(s):

Neural Network ◽

Drug Interaction ◽

Side Effect ◽

Network Architecture ◽

Selection Process ◽

Superior Performance ◽

Multiple Drug ◽

Interaction Prediction ◽

Benchmark Datasets ◽

Drug Drug Interaction

Abstract Drug-Drug Interaction (DDI) prediction is one of the most critical issues in drug development and health. Proposing appropriate computational methods for predicting unknown DDI with high precision is challenging. We proposed "NDD: Neural network-based method for drug-drug interaction prediction" for predicting unknown DDIs using various information about drugs. Multiple drug similarities based on drug substructure, target, side effect, off-label side effect, pathway, transporter, and indication data are calculated. At first, NDD uses a heuristic similarity selection process and then integrates the selected similarities with a nonlinear similarity fusion method to achieve high-level features. Afterward, it uses a neural network for interaction prediction. The similarity selection and similarity integration parts of NDD have been proposed in previous studies of other problems. Our novelty is to combine these parts with new neural network architecture and apply these approaches in the context of DDI prediction. We compared NDD with six machine learning classifiers and six state-of-the-art graph-based methods on three benchmark datasets. NDD achieved superior performance in cross-validation with AUPR ranging from 0.830 to 0.947, AUC from 0.954 to 0.994 and F-measure from 0.772 to 0.902. Moreover, cumulative evidence in case studies on numerous drug pairs, further confirm the ability of NDD to predict unknown DDIs. The evaluations corroborate that NDD is an efficient method for predicting unknown DDIs. The data and implementation of NDD are available at https://github.com/nrohani/NDD.

Download Full-text

SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

ACM Transactions on Graphics ◽

10.1145/3450284 ◽

2021 ◽

Vol 40 (3) ◽

pp. 1-13

Author(s):

Lumin Yang ◽

Jiajie Zhuang ◽

Hongbo Fu ◽

Xiangzhi Wei ◽

Kun Zhou ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Large Scale ◽

State Of The Art ◽

Semantic Segmentation ◽

Structure Information ◽

Graph Neural Networks ◽

Node Labels ◽

Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Download Full-text

Towards corpus and model: Hierarchical structured-attention-based features for Indonesian named entity recognition

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-202286 ◽

2021 ◽

pp. 1-12

Author(s):

Yingwen Fu ◽

Nankai Lin ◽

Xiaotian Lin ◽

Shengyi Jiang

Keyword(s):

Language Processing ◽

State Of The Art ◽

Named Entity Recognition ◽

Entity Recognition ◽

Language Models ◽

Neural Models ◽

Performance Models ◽

Named Entity ◽

High Resource ◽

Benchmark Datasets

Named entity recognition (NER) is fundamental to natural language processing (NLP). Most state-of-the-art researches on NER are based on pre-trained language models (PLMs) or classic neural models. However, these researches are mainly oriented to high-resource languages such as English. While for Indonesian, related resources (both in dataset and technology) are not yet well-developed. Besides, affix is an important word composition for Indonesian language, indicating the essentiality of character and token features for token-wise Indonesian NLP tasks. However, features extracted by currently top-performance models are insufficient. Aiming at Indonesian NER task, in this paper, we build an Indonesian NER dataset (IDNER) comprising over 50 thousand sentences (over 670 thousand tokens) to alleviate the shortage of labeled resources in Indonesian. Furthermore, we construct a hierarchical structured-attention-based model (HSA) for Indonesian NER to extract sequence features from different perspectives. Specifically, we use an enhanced convolutional structure as well as an enhanced attention structure to extract deeper features from characters and tokens. Experimental results show that HSA establishes competitive performance on IDNER and three benchmark datasets.

Download Full-text

IPOMDP-Net: A Deep Neural Network for Partially Observable Multi-Agent Planning Using Interactive POMDPs

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33016062 ◽

2019 ◽

Vol 33 ◽

pp. 6062-6069 ◽

Cited By ~ 1

Author(s):

Yanlin Han ◽

Piotr Gmytrasiewicz

Keyword(s):

Neural Network ◽

Network Architecture ◽

State Of The Art ◽

Neural Computing ◽

Neural Network Architecture ◽

Markov Decision ◽

Planning Algorithm ◽

Multi Agent ◽

Partially Observable ◽

Multi Agent Planning

This paper introduces the IPOMDP-net, a neural network architecture for multi-agent planning under partial observability. It embeds an interactive partially observable Markov decision process (I-POMDP) model and a QMDP planning algorithm that solves the model in a neural network architecture. The IPOMDP-net is fully differentiable and allows for end-to-end training. In the learning phase, we train an IPOMDP-net on various fixed and randomly generated environments in a reinforcement learning setting, assuming observable reinforcements and unknown (randomly initialized) model functions. In the planning phase, we test the trained network on new, unseen variants of the environments under the planning setting, using the trained model to plan without reinforcements. Empirical results show that our model-based IPOMDP-net outperforms the other state-of-the-art modelfree network and generalizes better to larger, unseen environments. Our approach provides a general neural computing architecture for multi-agent planning using I-POMDPs. It suggests that, in a multi-agent setting, having a model of other agents benefits our decision-making, resulting in a policy of higher quality and better generalizability.

Download Full-text

Enhancing the performance of cancer text classification model based on cancer hallmarks

IAES International Journal of Artificial Intelligence (IJ-AI) ◽

10.11591/ijai.v10.i2.pp316-323 ◽

2021 ◽

Vol 10 (2) ◽

pp. 316

Author(s):

Noha Ali ◽

Ahmed H. AbuEl-Atta ◽

Hala H. Zayed

Keyword(s):

Neural Network ◽

Language Processing ◽

Text Classification ◽

State Of The Art ◽

Classification Model ◽

Biomedical Text ◽

Cancer Hallmarks ◽

Embedding Technique ◽

Proposed Model ◽

Biomedical Text Classification

<span id="docs-internal-guid-cb130a3a-7fff-3e11-ae3d-ad2310e265f8"><span>Deep learning (DL) algorithms achieved state-of-the-art performance in computer vision, speech recognition, and natural language processing (NLP). In this paper, we enhance the convolutional neural network (CNN) algorithm to classify cancer articles according to cancer hallmarks. The model implements a recent word embedding technique in the embedding layer. This technique uses the concept of distributed phrase representation and multi-word phrases embedding. The proposed model enhances the performance of the existing model used for biomedical text classification. The result of the proposed model overcomes the previous model by achieving an F-score equal to 83.87% using an unsupervised technique that trained on PubMed abstracts called PMC vectors (PMCVec) embedding. Also, we made another experiment on the same dataset using the recurrent neural network (RNN) algorithm with two different word embeddings Google news and PMCVec which achieving F-score equal to 74.9% and 76.26%, respectively.</span></span>

Download Full-text

Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6284 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7797-7804

Author(s):

Goran Glavašš ◽

Swapna Somasundaran

Keyword(s):

State Of The Art ◽

Language Transfer ◽

Text Segmentation ◽

Word Embeddings ◽

Neural Architecture ◽

Text Coherence ◽

Sentence Level ◽

Proposed Model ◽

Benchmark Datasets ◽

Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

Download Full-text

An Experimental Analysis of Model Compression Techniques for Object Detection

10.5753/kdmile.2020.11958 ◽

2020 ◽

Author(s):

Andrey De Aguiar Salvi ◽

Rodrigo Coelho Barros

Keyword(s):

Object Detection ◽

Experimental Analysis ◽

State Of The Art ◽

Neural Architecture ◽

Model Compression ◽

Processing Power ◽

Benchmark Datasets ◽

The Difference ◽

And Performance ◽

Consumption Constraints

Recent research on Convolutional Neural Networks focuses on how to create models with a reduced number of parameters and a smaller storage size while keeping the model’s ability to perform its task, allowing the use of the best CNN for automating tasks in limited devices, with reduced processing power, memory, or energy consumption constraints. There are many different approaches in the literature: removing parameters, reduction of the floating-point precision, creating smaller models that mimic larger models, neural architecture search (NAS), etc. With all those possibilities, it is challenging to say which approach provides a better trade-off between model reduction and performance, due to the difference between the approaches, their respective models, the benchmark datasets, or variations in training details. Therefore, this article contributes to the literature by comparing three state-of-the-art model compression approaches to reduce a well-known convolutional approach for object detection, namely YOLOv3. Our experimental analysis shows that it is possible to create a reduced version of YOLOv3 with 90% fewer parameters and still outperform the original model by pruning parameters. We also create models that require only 0.43% of the original model’s inference effort.

Download Full-text

Multi-Term Attention Networks for Skeleton-Based Action Recognition

Applied Sciences ◽

10.3390/app10155326 ◽

2020 ◽

Vol 10 (15) ◽

pp. 5326

Author(s):

Xiaolei Diao ◽

Xiaoqiang Li ◽

Chen Huang

Keyword(s):

Neural Network ◽

Time Scales ◽

Action Recognition ◽

State Of The Art ◽

Attention Networks ◽

Weighted Fusion ◽

Temporal Features ◽

Benchmark Datasets ◽

Spatio Temporal ◽

Different Time Scales

The same action takes different time in different cases. This difference will affect the accuracy of action recognition to a certain extent. We propose an end-to-end deep neural network called “Multi-Term Attention Networks” (MTANs), which solves the above problem by extracting temporal features with different time scales. The network consists of a Multi-Term Attention Recurrent Neural Network (MTA-RNN) and a Spatio-Temporal Convolutional Neural Network (ST-CNN). In MTA-RNN, a method for fusing multi-term temporal features are proposed to extract the temporal dependence of different time scales, and the weighted fusion temporal feature is recalibrated by the attention mechanism. Ablation research proves that this network has powerful spatio-temporal dynamic modeling capabilities for actions with different time scales. We perform extensive experiments on four challenging benchmark datasets, including the NTU RGB+D dataset, UT-Kinect dataset, Northwestern-UCLA dataset, and UWA3DII dataset. Our method achieves better results than the state-of-the-art benchmarks, which demonstrates the effectiveness of MTANs.

Download Full-text

Finger Gesture Spotting from Long Sequences Based on Multi-Stream Recurrent Neural Networks

Sensors ◽

10.3390/s20020528 ◽

2020 ◽

Vol 20 (2) ◽

pp. 528 ◽

Cited By ~ 1

Author(s):

Gibran Benitez-Garcia ◽

Muhammad Haris ◽

Yoshiyuki Tsuda ◽

Norimichi Ukita

Keyword(s):

Neural Network ◽

Semantic Information ◽

State Of The Art ◽

Spatial Location ◽

Depth Sensor ◽

Stream Network ◽

Neural Architecture ◽

Network Merging ◽

Automated Methods ◽

Gesture Spotting

Gesture spotting is an essential task for recognizing finger gestures used to control in-car touchless interfaces. Automated methods to achieve this task require to detect video segments where gestures are observed, to discard natural behaviors of users’ hands that may look as target gestures, and be able to work online. In this paper, we address these challenges with a recurrent neural architecture for online finger gesture spotting. We propose a multi-stream network merging hand and hand-location features, which help to discriminate target gestures from natural movements of the hand, since these may not happen in the same 3D spatial location. Our multi-stream recurrent neural network (RNN) recurrently learns semantic information, allowing to spot gestures online in long untrimmed video sequences. In order to validate our method, we collect a finger gesture dataset in an in-vehicle scenario of an autonomous car. 226 videos with more than 2100 continuous instances were captured with a depth sensor. On this dataset, our gesture spotting approach outperforms state-of-the-art methods with an improvement of about 10% and 15% of recall and precision, respectively. Furthermore, we demonstrated that by combining with an existing gesture classifier (a 3D Convolutional Neural Network), our proposal achieves better performance than previous hand gesture recognition methods.

Download Full-text