Automatic classification of medical questions is of great significance in improving the quality and efficiency of online medical services, and belongs to the task of intent recognition. Joint entity recognition and intent recognition perform better than single task models. Currently, most publicly available medical text intent recognition datasets lack entity annotation, and manual annotation of these entities requires a lot of time and manpower. To solve this problem, this paper proposes a medical text classification model, bidirectional encoder representation based on transformer-recurrent convolutional neural network-entity-label-semantics (BRELS), which integrates medical entity label semantics. This model firstly utilizes an adaptive fusion mechanism to absorb prior knowledge of medical entity labels, achieving local feature enhancement. Then in global feature extraction, a lightweight recurrent convolutional neural network (LRCNN) is used to suppress parameter growth while preserving the original semantics of the text. The ablation and comparison experiments are conducted on three public medical text intent recognition datasets to validate the performance of the model. The results show that F1 score reaches 87.34%, 81.71%, and 77.74% on each dataset, respectively. The results show that the BRELS model can effectively identify and understand medical terminology, thereby effectively identifying users' intentions, which can improve the quality and efficiency of online medical services.

Information on age-related differences in affective meanings of words is widely used by researchers to study emotions, word recognition, attention, memory, and text-based sentiment analysis. To date, no Chinese affective norms for older adults are available although Chinese as a spoken language has the largest population in the world. This article presents the first large-scale age-related affective norms for 2,061 four-character Chinese words (AANC). Each word in this database has rating values in the four dimensions, namely, valence, arousal, dominance, and familiarity. We found that older adults tended to perceive positive words as more arousing and less controllable and evaluate negative words as less arousing and more controllable than younger adults did. This indicates that the positivity effect is reliable for older adults who show a processing bias toward positive vs. negative words. Our AANC database supplies valuable information for researchers to study how emotional characteristics of words influence the cognitive processes and how this influence evolves with age. This age-related difference study on affective norms not only provides a tool for cognitive science, gerontology, and psychology in experimental studies but also serves as a valuable resource for affective analysis in various natural language processing applications.

Audio-driven talking face has attracted broad interest from academia and industry recently. However, data acquisition and labeling in audio-driven talking face are labor-intensive and costly. The lack of data resource results in poor synthesis effect. To alleviate this issue, we propose to use TTS (Text-To-Speech) for data augmentation to improve few-shot ability of the talking face system. The misalignment problem brought by the TTS audio is solved with the introduction of soft-DTW, which is first adopted in the talking face task. Moreover, features extracted by HuBERT are explored to utilize underlying information of audio, and found to be superior over other features. The proposed method achieves 17%, 14%, 38% dominance on MSE score, DTW score and user study preference repectively over the baseline model, which shows the effectiveness of improving few-shot learning for talking face system with TTS augmentation.

The arterial blood pressure (BP) response is augmented during walking in patients with peripheral artery disease (PAD) and in simulated PAD animal models during static exercise. The exercise pressor response (EPR) is a contributor to the exaggerated BP response and heating treatment is effective to attenuate exaggeration of the EPR. However, the underlying mechanisms leading to the inhibitory effects of heat treatment on the EPR, especially on the essential alteration originating within the ischemic skeletal muscles of PAD, is poorly understood.

Attention models are proposed in sentiment analysis and other classification tasks because some words are more important than others to train the attention models.However, most existing methods either use local context based information, affective lexicons, or user preference information.In this work, we propose a novel attention model trained by cognition grounded eye-tracking data.First,a reading prediction model is built using eye-tracking data as dependent data and other features in the context as independent data.The predicted reading time is then used to build a cognition grounded attention layer for neural sentiment analysis.Our model can capture attentions in context both in terms of words at sentence level as well as sentences at document level.Other attention mechanisms can also be incorporated together to capture other aspects of attentions, such as local attention, and affective lexicons.Results of our work include two parts.The first part compares our proposed cognition ground attention model with other state-of-the-art sentiment analysis models.The second part compares our model with an attention model based on other lexicon based sentiment resources.Evaluations show that sentiment analysis using cognition grounded attention model outperforms the state-of-the-art sentiment analysis methods significantly.Comparisons to affective lexicons also indicate that using cognition grounded eye-tracking data has advantages over other sentiment resources by considering both word information and context information.This work brings insight to how cognition grounded data can be integrated into natural language processing (NLP) tasks.

In this contribution, we describe the system presented by the PolyU CBS-Comp Team at the Task 1 of SemEval 2021, where the goal was the estimation of the complexity of words in a given sentence context. Our top system, based on a combination of lexical, syntactic, word embeddings and Transformers-derived features and on a Gradient Boosting Regressor, achieves a top correlation score of 0.754 on the subtask 1 for single words and 0.659 on the subtask 2 for multiword expressions.

Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part‐of‐speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic‐based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution‐based data augmentation methods, one of which is thesaurus‐based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST‐2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM‐AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well‐designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms.

Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part-of-speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic-based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution-based data augmentation methods, one of which is thesaurus-based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST-2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM-AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well-designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms.

Sentiment analysis is helpful to bestow ability of understanding human’s attitude in texts on artificial intelligence systems. In this area, text sentiment is usually signaled by a few indicative words that convey affective meanings and arouse readers’ collective emotions. However, most existing sentiment analysis models have predominantly featured through neural network architectures with end-to-end training manner and limited awareness of affective knowledge, which, as a result, often fails to pinpoint the essential features for sentiment prediction. In this work, we present a novel approach for sentiment analysis by fusing external affective knowledge into neural networks. The affective knowledge is distilled from two sentiment lexicons grounded by two psychological theories, e.g., the Affect Control Theory and word affections in terms of Valence, Arousal, and Dominance. To examine the effects of affective knowledge over sentiment analysis, we conduct cross-dataset and cross-model experiments along with a detailed ablation analysis. Results show that our proposed method outperforms trendy neural networks in all the five benchmarks with consistent and significant improvement (1.4% Accuracy in average). Further discussions demonstrate that all affective attributes exhibit positive effects to model enhancement and our model is robust to the change of lexicon size.

This paper presents our work on using part-of-speech focused lexical substitution for data augmentation (PLSDA) to enhance the prediction capabilities and the performance of deep learning models. This paper explains how PLSDA uses part-of-speech information to identify words and make use of different augmentation strategies to find semantically related substitutions to generate new instances for training. Evaluations of PLSDA is conducted on a variety of datasets across different text classification tasks. When PLSDA is applied to four deep learning models, results show that classifiers trained with PLSDA achieve 1.3% accuracy improvement on average.

Automatic Chinese irony detection is a challenging task, and it has a strong impact on linguistic research. However, Chinese irony detection often lacks labeled benchmark datasets. In this paper, we introduce Ciron, the first Chinese benchmark dataset available for irony detection for machine learning models. Ciron includes more than 8.7K posts, collected from Weibo, a micro blogging platform. Most importantly, Ciron is collected with no pre-conditions to ensure a much wider coverage. Evaluation on seven different machine learning classifiers proves the usefulness of Ciron as an important resource for Chinese irony detection.

Informal short texts on the web are rich in emotions as they often reflect unfiltered immediate reactions to breaking news events. The emotion density, however, stands in contrast to its poverty of linguistic contexts and features for emotion classification. This paper tackles that challenge by proposing orthographic features based on orthographic code mixing and code-switching for both non-ML and ML approaches. Our results show that orthographic features routinely outperform grammatical features for emotion classification for short texts in all approaches as expected. Orthographic features were also shown to make more significant contributions, especially in terms of precision and in formal texts when state of the art deep learning algorithms are applied. This result confirms the effectiveness of the orthographic change feature to the task of emotion classification. These results are argued to be applicable to all languages because of the common code-shifting in languages with non-Latin orthographies, and the use of non-letter symbols in all languages.

Collecting modality exclusivity norms for lexical items has recently become a common practice in psycholinguistics and cognitive research. However, these norms are available only for a relatively small number of languages and often involve a costly and time-consuming collection of ratings. In this work, we aim at learning a mapping between word embeddings and modality norms. Our experiments focused on crosslingual word embeddings, in order to predict modality association scores by training on a high-resource language and testing on a low-resource one. We ran two experiments, one in a monolingual and the other one in a crosslingual setting. Results show that modality prediction using off-the-shelf crosslingual embeddings indeed has moderate-to-high correlations with human ratings even when regression algorithms are trained on an English resource and tested on a completely unseen language.

Class noise, as know as the mislabeled data in training set, can lead to poor accuracy in classification no matter what machine learning methods are used. A reasonable estimation of class noise has a significant impact on the performance of learning methods. However, the error in existing estimation is inevitable theoretically and infer the performance of optimal classifier trained on noisy data. Instead of seeking a single optimal classifier on noisy data, in this work, we use a set of weak classifiers, which are caused by negative impacts of noisy data, to learn an ensemble strong classifier which is based on the training error and estimation of class noise. By this strategy, the proposed ensemble with estimation method overcomes the gap between the estimation and true distribution of class noise. Our proposed method does not require any a priori knowledge about class noises. We prove that the optimal ensemble classifier on the noisy distribution can approximate the optimal classifier on the clean distribution when the training set grows. Comparisons with existing algorithms show that our methods outperform state-of-the-art approaches on a large number of benchmark datasets in different domains. Both the theoretical analysis and the experimental result reveal that our method can improve the performance, works well on clean data and is robust on the algorithm parameter.

Deep neural network models have played a critical role in sentiment analysis with promising results in the recent decade. One of the essential challenges, however, is how external sentiment knowledge can be effectively utilized. In this work, we propose a novel affection-driven approach to incorporating affective knowledge into neural network models. The affective knowledge is obtained in the form of a lexicon under the Affect Control Theory (ACT), which is represented by vectors of three-dimensional attributes in Evaluation, Potency, and Activity (EPA). The EPA vectors are mapped to an affective influence value and then integrated into Long Short-term Memory (LSTM) models to highlight affective terms. Experimental results show a consistent improvement of our approach over conventional LSTM models by 1.0% to 1.5% in accuracy on three large benchmark datasets. Evaluations across a variety of algorithms have also proven the effectiveness of leveraging affective terms for deep model enhancement.

The purpose of this study was to determine the effects of one-time acute heat treatment (HT) on the exaggerated exercise pressor reflex in a model of peripheral arterial insufficiency induced by ligation of the femoral artery and was to further examine the underlying mechanism of ATP-P2X3 signal activity during this process. The blood pressure (BP) response to static muscle contraction and muscle tendon stretch was recorded to determine the exercise pressor reflex. Also, αβ-methylene ATP (αβ-me ATP) was injected into the arterial blood supply of the hindlimb muscles to stimulate P2X3 receptors in the muscle afferent nerves. To process one-time acute HT, a heating pad was placed locally on the hindlimb and the muscle temperature (Tm) was increased by ~1.5°C and maintained for 5 min. Compared with control rats, a greater mean arterial pressure (MAP) response to muscle contraction was observed in rats with femoral occlusion in a pre-heat control session (28 ± 2 mmHg in occluded rats/n = 12 vs. 18 ± 2 mmHg in control rats/n = 9; p < 0.05). The one-time acute HT attenuated the amplification of the BP response in rats with femoral artery occlusion (MAP response: 19 ± 8 mmHg in occluded rats + HT/n = 11; p < 0.05 vs. occluded rats). In contrast, HT did not significantly attenuate amplification of MAP response to muscle stretch and αβ-me ATP injection in rats with femoral artery occlusion and controls (all p > 0.05). Our data suggest that one-time acute HT selectively attenuates the amplified pressor response induced by activation of the metabolic and mechanical components of the reflex in rats after femoral artery occlusion. The suppressing effects of acute HT on the exaggerated exercise pressor reflex are likely mediated through a reduction in metabolites (e.g., ATP) stimulating the muscle afferent nerves in contracting muscle, but unlikely through direct alteration of P2X receptors per se.

In sentiment analysis of product reviews, both user and product information are proven to be useful. Current works handle user profile and product information in a unified model which may not be able to learn salient features of users and products effectively. In this work, we propose a dual user and product memory network (DUPMN) model to learn user profiles and product information for reviews classification using separate memory networks. Then, the two representations are used jointly for sentiment analysis. The use of separate models aims to capture user profiles and product information more effectively. Comparing with state-of-the-art unified prediction models, evaluations on three benchmark datasets (IMDB, Yelp13, and Yelp14) show that our dual learning model gives performance gain of 0.6%, 1.2%, and 0.9%, respectively. The improvements are also deemed very significant measured by p-values.

Mandarin Alphabetical Word (MAW) is one indispensable component of Modern Chinese that demonstrates unique code-mixing idiosyncrasies influenced by language exchanges. Yet, this interesting phenomenon has not been properly addressed and is mostly excluded from the Chinese language system. This paper addresses the core problem of MAW identification and proposes to construct a large collection of MAWs from Sina Weibo (SMAW) using an automatic web-based technique which includes rule-based identification, informatics-based extraction, as well as Baidu search engine validation. A collection of 16,207 qualified SMAWs are obtained using this technique along with an annotated corpus of more than 200,000 sentences for linguistic research and applicable inquiries.

ge-related differences in affective meanings of words are widely used by researchers studying emotions, word recognition, attention, memory and text -based sentiment analysis. However, no Chinese affective norms for older adults are available. This article firstly presents the available large-scale Chinese affective norms for 2, 061 4-character words rated in labs by 114 older and 150 younger adults (CAN4Age) who evaluated these words on four dimensions: valence, arousal, dominance, and familiarity. We also compiled 4 lexical variables for each word, including word frequency, word complexity, character frequency and character complexity. In general, older adults tend to evaluate emotional words more extremely than younger adults do. That is, they rate positive words as more positive and negative words as more negative than younger adults do. Specifically, older adults tend to perceive positive words as more arousing and less controllable and negative words as less arousing and more controllable than that of younger adults. This age-related database will enable researchers to study how emotional characteristics of words influence their cognitive processing, and how this influence evolves with age in Chinese. This age-related difference study on affective norms not only provides insights to cognitive neuroscience, gerontology and psychology in experimental studies, but the produced affective word collection also has great value as a resource for affective analysis in natural language processing applications. These norms can be downloaded as supplemental materials with this published article.