Domain-specific Tasks Research Articles

AlphaPept: a modern and open framework for MS-based proteomics

In common with other omics technologies, mass spectrometry (MS)-based proteomics produces ever-increasing amounts of raw data, making efficient analysis a principal challenge. A plethora of different computational tools can process the MS data to derive peptide and protein identification and quantification. However, during the last years there has been dramatic progress in computer science, including collaboration tools that have transformed research and industry. To leverage these advances, we develop AlphaPept, a Python-based open-source framework for efficient processing of large high-resolution MS data sets. Numba for just-in-time compilation on CPU and GPU achieves hundred-fold speed improvements. AlphaPept uses the Python scientific stack of highly optimized packages, reducing the code base to domain-specific tasks while accessing the latest advances. We provide an easy on-ramp for community contributions through the concept of literate programming, implemented in Jupyter Notebooks. Large datasets can rapidly be processed as shown by the analysis of hundreds of proteomes in minutes per file, many-fold faster than acquisition. AlphaPept can be used to build automated processing pipelines with web-serving functionality and compatibility with downstream analysis tools. It provides easy access via one-click installation, a modular Python library for advanced users, and via an open GitHub repository for developers.

Few-shot code translation via task-adapted prompt learning

Pre-trained models such as CodeT5 and TransCoder have achieved impressive progress in software engineering. However, fine-tuning PLMs for code translation is confronted with significant challenges owing to the scarce availability of parallel code. Large language models such as ChatGPT have exhibited considerable promise in few-shot learning where only a small number of demonstration examples are given to the LLM. Yet they have not been specifically optimized for domain-specific tasks, and their use often entails significant manual effort in manually curating prompts. In this paper, we propose FSCTrans, a novel parameter-efficient tuning approach for code translation when furnished with only a few demonstration examples. (1) to efficiently reuse prior knowledge during pre-training, FSCTrans employs task-adapted prompt tuning, which freezes the pre-trained CodeT5 while merely updating parameters in a small prompt module; (2) to enable parameter efficient tuning on only a small number of examples, FSCTrans bridges pre-training to the translation task through a new pre-training objective of code-to-code generation. We evaluate FSCTrans on Java↔Python and Java↔C# datasets from both real-world projects and online judge problems. The evaluation results show that FSCTrans is remarkably effective in few-shot code translation: on average, it improves CodeT5 by 54.61% and 31.59% in terms of BLEU-4 and CodeBLEU; notably, FSCTrans demonstrates 14.42% and 18.36% superior performance in Java → C# translations in terms of BLEU-4 and CodeBLEU compared to ChatGPT.

Fine-Tuned Large Language Model for Visualization System: A Study on Self-Regulated Learning in Education.

Large Language Models (LLMs) have shown great potential in intelligent visualization systems, especially for domainspecific applications. Integrating LLMs into visualization systems presents challenges, and we categorize these challenges into three alignments: domain problems with LLMs, visualization with LLMs, and interaction with LLMs. To achieve these alignments, we propose a framework and outline a workflow to guide the application of fine-tuned LLMs to enhance visual interactions for domain-specific tasks. These alignment challenges are critical in education because of the need for an intelligent visualization system to support beginners' self-regulated learning. Therefore, we apply the framework to education and introduce Tailor-Mind, an interactive visualization system designed to facilitate self-regulated learning for artificial intelligence beginners. Drawing on insights from a preliminary study, we identify self-regulated learning tasks and fine-tuning objectives to guide visualization design and tuning data construction. Our focus on aligning visualization with fine-tuned LLM makes Tailor-Mind more like a personalized tutor. Tailor-Mind also supports interactive recommendations to help beginners better achieve their learning goals. Model performance evaluations and user studies confirm that Tailor-Mind improves the self-regulated learning experience, effectively validating the proposed framework.

Domain-specific knowledge and domain-general abilities in children's science problem-solving.

Problem-solving in early and middle childhood is of high relevance for cognitive developmental research and educational support. Previous research on science problem-solving has focussed on the process and strategies of children handling challenging tasks, but less on providing insights into the cognitive network that enables science problem-solving. In this study, we aimed to investigate whether performance in science problem-solving is mainly determined by domain-specific rule knowledge, by domain-general cognitive abilities or both. In our study, 215 6- to 8-year-old children completed a set of three domain-specific rule knowledge tasks and three corresponding problem-solving tasks that were content-coherent, as well as a vocabulary task, and a reasoning task. Correlational and regression analyses revealed a negligible impact of domain-specific rule knowledge on corresponding problem-solving tasks. In contrast, the associations between problem-solving performance in different domains and the associations between problem-solving performance and domain-general abilities (vocabulary and reasoning) were comparably strong. The findings suggest that science problem-solving in primary school children primarily relies on domain-general cognitive abilities. Implications of these findings are discussed with regard to cognitive theories and early science education.

Patient Information Summarization in Clinical Settings: Scoping Review.

Information overflow, a common problem in the present clinical environment, can be mitigated by summarizing clinical data. Although there are several solutions for clinical summarization, there is a lack of a complete overview of the research relevant to this field. This study aims to identify state-of-the-art solutions for clinical summarization, to analyze their capabilities, and to identify their properties. A scoping review of articles published between 2005 and 2022 was conducted. With a clinical focus, PubMed and Web of Science were queried to find an initial set of reports, later extended by articles found through a chain of citations. The included reports were analyzed to answer the questions of where, what, and how medical information is summarized; whether summarization conserves temporality, uncertainty, and medical pertinence; and how the propositions are evaluated and deployed. To answer how information is summarized, methods were compared through a new framework "collect-synthesize-communicate" referring to information gathering from data, its synthesis, and communication to the end user. Overall, 128 articles were included, representing various medical fields. Exclusively structured data were used as input in 46.1% (59/128) of papers, text in 41.4% (53/128) of articles, and both in 10.2% (13/128) of papers. Using the proposed framework, 42.2% (54/128) of the records contributed to information collection, 27.3% (35/128) contributed to information synthesis, and 46.1% (59/128) presented solutions for summary communication. Numerous summarization approaches have been presented, including extractive (n=13) and abstractive summarization (n=19); topic modeling (n=5); summary specification (n=11); concept and relation extraction (n=30); visual design considerations (n=59); and complete pipelines (n=7) using information extraction, synthesis, and communication. Graphical displays (n=53), short texts (n=41), static reports (n=7), and problem-oriented views (n=7) were the most common types in terms of summary communication. Although temporality and uncertainty information were usually not conserved in most studies (74/128, 57.8% and 113/128, 88.3%, respectively), some studies presented solutions to treat this information. Overall, 115 (89.8%) articles showed results of an evaluation, and methods included evaluations with human participants (median 15, IQR 24 participants): measurements in experiments with human participants (n=31), real situations (n=8), and usability studies (n=28). Methods without human involvement included intrinsic evaluation (n=24), performance on a proxy (n=10), or domain-specific tasks (n=11). Overall, 11 (8.6%) reports described a system deployed in clinical settings. The scientific literature contains many propositions for summarizing patient information but reports very few comparisons of these proposals. This work proposes to compare these algorithms through how they conserve essential aspects of clinical information and through the "collect-synthesize-communicate" framework. We found that current propositions usually address these 3 steps only partially. Moreover, they conserve and use temporality, uncertainty, and pertinent medical aspects to varying extents, and solutions are often preliminary.

ITALIAN-LEGAL-BERT models for improving natural language processing tasks in the Italian legal domain

Legal-BERT models are based on the BERT architecture (or its variants) and have been developed specifically for the legal domain. They have reached the state of the art in complex legal tasks such as legal research, document synthesis, contract analysis, argument extraction, and legal prediction. In this paper, we proposed four versions of Legal-BERT models pre-trained on the Italian legal domain. They aim to improve NLP applications in the Italian legal context. We have shown that they outperforms the Italian "generalpurpose" BERT in several domain-specific tasks, such as named entity recognition, sentence classification, semantic similarity with Bi-encoders, and document classification.

DEVELOPMENT OF A QUESTION ANSWERING CHATBOT FOR BLOCKCHAIN DOMAIN

Large Language Models (LLMs), such as ChatGPT, have transformed the field of natural language processing with their capacity for language comprehension and generation of human-like, fluent responses for many downstream tasks. Despite their impressive capabilities, they often fall short in domain-specific and knowledge-intensive domains due to a lack of access to relevant data. Moreover, most state-of-art LLMs lack transparency as they are often accessible only through APIs. Furthermore, their application in critical real-world scenarios is hindered by their proclivity to produce hallucinated information and inability to leverage external knowledge sources. To address these limitations, we propose an innovative system that enhances LLMs by integrating them with an external knowledge management module. The system allows LLMs to utilize data stored in vector databases, providing them with relevant information for their responses. Additionally, it enables them to retrieve information from the Internet, further broadening their knowledge base. The research approach circumvents the need to retrain LLMs, which can be a resource-intensive process. Instead, it focuses on making more efficient use of existing models. Preliminary results indicate that the system holds promise for improving the performance of LLMs in domain-specific and knowledge-intensive tasks. By equipping LLMs with real-time access to external data, it is possible to harness their language generation capabilities more effectively, without the need to continually strive for larger models.

A self-supervised language model selection strategy for biomedical question answering

Large neural-based Pre-trained Language Models (PLM) have recently gained much attention due to their noteworthy performance in many downstream Information Retrieval (IR) and Natural Language Processing (NLP) tasks. PLMs can be categorized as either general-purpose, which are trained on resources such as large-scale Web corpora, and domain-specific which are trained on in-domain or mixed-domain corpora. While domain-specific PLMs have shown promising performance on domain-specific tasks, they are significantly more computationally expensive compared to general-purpose PLMs as they have to be either retrained or trained from scratch. The objective of our work in this paper is to explore whether it would be possible to leverage general-purpose PLMs to show competitive performance to domain-specific PLMs without the need for expensive retraining of the PLMs for domain-specific tasks. By focusing specifically on the recent BioASQ Biomedical Question Answering task, we show how different general-purpose PLMs show synergistic behaviour in terms of performance, which can lead to overall notable performance improvement when used in tandem with each other. More concretely, given a set of general-purpose PLMs, we propose a self-supervised method for training a classifier that systematically selects the PLM that is most likely to answer the question correctly on a per-input basis. We show that through such a selection strategy, the performance of general-purpose PLMs can become competitive with domain-specific PLMs while remaining computationally light since there is no need to retrain the large language model itself. We run experiments on the BioASQ dataset, which is a large-scale biomedical question-answering benchmark. We show that utilizing our proposed selection strategy can show statistically significant performance improvements on general-purpose language models with an average of 16.7% when using only lighter models such as DistilBERT and DistilRoBERTa, as well as 14.2% improvement when using relatively larger models such as BERT and RoBERTa and so, their performance become competitive with domain-specific large language models such as PubMedBERT.

Executive functions and sport agents

The present review aims at investigating the scientific production with respect to the link between executive functions (EF) and sport agents (athletes, players, coaches, umpires). For that purpose, a series of searches were carried out on WoS that yielded 703 references. Upon a screening process following the PRISMA guidelines, a total of 94 papers were used to complete a bibliometric analysis together with a scoping review. Some underlying themes were detected, namely, domain-general vs domain-specific EF tests in sport, EF and type of sport, talent detection, EF and sport-specific skills, EF and position on the field/court, expert/elite paradigm and EF, EF and other sport agents and high-performance athletes with disabilities and the role of EF. In light of results, more longitudinal studies are required to confirm their value in athlete´s development, albeit the consensus with regard to their importance. Recent studies indicate the lack of predictive value of EF in talent detection. Likewise, there some indicators that point out to their role in open-skills, strategic sports as well as in the difference found between athletes and non-athletes and experts versus amateurs. In addition, domain-specific tasks are required to assess EF with both ecological and construct validity and EF should also be used to test other sport agents, such as coaches and referees/umpires.

Assessment of Cognitive Behavioral Characteristics in Intelligent Systems with Predictive Ability and Computing Power

The article proposes a universal dual-axis intelligent systems assessment scale. The scale considers the properties of intelligent systems within the environmental context, which develops over time. In contrast to the frequent consideration of the “mind” of artificial intelligent systems on a scale from “weak” to “strong”, we highlight the modulating influences of anticipatory ability on their “brute force”. In addition, the complexity, the ”weight“ of the cognitive task and the ability to critically assess it beforehand determine the actual set of cognitive tools, the use of which provides the best result in these conditions. In fact, the presence of ”common sense“ options is what connects the ability to solve a problem with the correct use of such an ability itself. The degree of ”correctness“ and ”adequacy“ is determined by the combination of a suitable solution with the temporal characteristics of the event, phenomenon, object or subject under study. The proposed approach can be applied in the evaluation of various intelligent agents in different contexts including AI and humans performing complex domain-specific tasks with high uncertainty.

Intelligent predictive maintenance of hydraulic systems based on virtual knowledge graph

In the manufacturing industry, a hydraulic system harnesses liquid fluid power to create powerful machines. Under the trend of Industry 4.0, the predictive maintenance of hydraulic systems is transforming to more intelligent and automated approaches that leverage the strong power of artificial intelligence and data science technologies. However, due to the knowledge-intensive and heterogeneous nature of the manufacturing domain, the data and information required for predictive maintenance are normally collected from ubiquitous sensing networks. This leads to the gap between massive heterogeneous data/information resources in hydraulic system components and the limited cognitive ability of system users. Moreover, how to capture and structure useful domain knowledge (in a machine-readable way) for solving domain-specific tasks remains an open challenge for the predictive maintenance of hydraulic systems. To address these challenges, in this paper we propose a virtual knowledge graph-based approach for the digital modeling and intelligent predictive analytics of hydraulic systems. We evaluate the functionalities and effectiveness of the proposed approach on a predictive maintenance task under real-world industrial contexts. Results show that our proposed approach is capable and feasible to be implemented for digital modeling, data access, data integration, and predictive analytics.

Embracing transdisciplinarity to prepare for the future: revisiting the gap between the labour market and translator education

ABSTRACT There has long been a disconnect between the labour market for translators and translator education. Most research on this disconnect focuses on either industry or education in isolation, leaving the problem unsolved. To address this gap, this study examines both industrial and educational perspectives on transdisciplinarity in translators’ domain competence through an epistemological lens. Three types of data are collected: translation-related job ads, curriculum plans of Master of Translation and Interpretation (MTI) programmes, and semi-structured interviews with teachers-cum-translators. The findings, derived from data mining and textometric analyses of targeted job ads together with content analyses of both curriculum plans and interviews, show a shared epistemological understanding in industry and education of new forms of knowledge pertaining to domain-specific translation tasks. Alongside this shared understanding, we highlight misalignment between market needs for and training on knowledge about cross-boundary collaborations, and we explore the transdisciplinary domain competence required to cope with a complex-market reality using a common language shared with stakeholders. The implications for a transdisciplinary approach to translator education are also discussed.

Unsupervised Domain Adaptation for Image Classification and Object Detection Using Guided Transfer Learning Approach and JS Divergence.

Unsupervised domain adaptation (UDA) is a transfer learning technique utilized in deep learning. UDA aims to reduce the distribution gap between labeled source and unlabeled target domains by adapting a model through fine-tuning. Typically, UDA approaches assume the same categories in both domains. The effectiveness of transfer learning depends on the degree of similarity between the domains, which determines an efficient fine-tuning strategy. Furthermore, domain-specific tasks generally perform well when the feature distributions of the domains are similar. However, utilizing a trained source model directly in the target domain may not generalize effectively due to domain shift. Domain shift can be caused by intra-class variations, camera sensor variations, background variations, and geographical changes. To address these issues, we design an efficient unsupervised domain adaptation network for image classification and object detection that can learn transferable feature representations and reduce the domain shift problem in a unified network. We propose the guided transfer learning approach to select the layers for fine-tuning the model, which enhances feature transferability and utilizes the JS-Divergence to minimize the domain discrepancy between the domains. We evaluate our proposed approaches using multiple benchmark datasets. Our domain adaptive image classification approach achieves 93.2% accuracy on the Office-31 dataset and 75.3% accuracy on the Office-Home dataset. In addition, our domain adaptive object detection approach achieves 51.1% mAP on the Foggy Cityscapes dataset and 72.7% mAP on the Indian Vehicle dataset. We conduct extensive experiments and ablation studies to demonstrate the effectiveness and efficiency of our work. Experimental results also show that our work significantly outperforms the existing methods.

Autistic traits are associated with enhanced working memory capacity for abstract visual stimuli

We tested whether the association between autistic traits and enhanced performance in visual-perceptual tasks extends to visual working memory capacity. We predicted that any positive effect of autistic traits on visual working memory performance would be greatest during domain-specific tasks, in which visual resources must be relied upon. We used a visual ‘matrix’ task, involving recall of black-and-white chequered patterns which increased in size, to establish participants' capacity (span). We assessed 144 young adults' (M = 22.0 years, SD = 2.5) performance on abstract, ‘low semantic’ versus ‘high semantic’ task versions. The latter offered multimodal coding due to the availability of long-term memory resources that could supplement visual working memory. Participants also completed measures of autistic traits and trait anxiety. Autistic traits, especially Attention to Detail, Attention Switching, and Communication, positively predicted visual working memory capacity, specifically in the low semantic task, which relies on visual working memory resources. Autistic traits are therefore associated with enhanced processing and recall of visual information. The benefit is removed, however, when multimodal coding may be incorporated, emphasising the visual nature of the benefit. Strengths in focused attention to detail therefore appear to benefit domain-specific visual working memory task performance.

Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation

White matter fiber clustering is an important strategy for white matter parcellation, which enables quantitative analysis of brain connections in health and disease. In combination with expert neuroanatomical labeling, data-driven white matter fiber clustering is a powerful tool for creating atlases that can model white matter anatomy across individuals. While widely used fiber clustering approaches have shown good performance using classical unsupervised machine learning techniques, recent advances in deep learning reveal a promising direction toward fast and effective fiber clustering. In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances. This process learns a high-dimensional embedding feature representation for each fiber, regardless of the order of fiber points reconstructed during tractography. We design a novel network architecture that represents input fibers as point clouds and allows the incorporation of additional sources of input information from gray matter parcellation. Thus, DFC makes use of combined information about white matter fiber geometry and gray matter anatomy to improve the anatomical coherence of fiber clusters. In addition, DFC conducts outlier removal naturally by rejecting fibers with low cluster assignment probability. We evaluate DFC on three independently acquired cohorts, including data from 220 individuals across genders, ages (young and elderly adults), and different health conditions (healthy control and multiple neuropsychiatric disorders). We compare DFC to several state-of-the-art white matter fiber clustering algorithms. Experimental results demonstrate superior performance of DFC in terms of cluster compactness, generalization ability, anatomical coherence, and computational efficiency.

Modeling and Measuring Domain-Specific Quantitative Reasoning in Higher Education Business and Economics

Quantitative reasoning is considered a crucial prerequisite for acquiring domain-specific expertise in higher education. To ascertain whether students are developing quantitative reasoning, validly assessing its development over the course of their studies is required. However, when measuring quantitative reasoning in an academic study program, it is often confounded with other skills. Following a situated approach, we focus on quantitative reasoning in the domain of business and economics and define domain-specific quantitative reasoning primarily as a skill and capacity that allows for reasoned thinking regarding numbers, arithmetic operations, graph analyses, and patterns in real-world business and economics tasks, leading to problem solving. As many studies demonstrate, well-established instruments for assessing business and economics knowledge like the Test of Understanding College Economics (TUCE) and the Examen General para el Egreso de la Licenciatura (EGEL) contain items that require domain-specific quantitative reasoning skills. In this study, we follow a new approach and assume that assessing business and economics knowledge offers the opportunity to extract domain-specific quantitative reasoning as the skill for handling quantitative data in domain-specific tasks. We present an approach where quantitative reasoning – embedded in existing measurements from TUCE and EGEL tasks – will be empirically extracted. Hereby, we reveal that items tapping domain-specific quantitative reasoning constitute an empirically separable factor within a Confirmatory Factor Analysis and that this factor (domain-specific quantitative reasoning) can be validly and reliably measured using existing knowledge assessments. This novel methodological approach, which is based on obtaining information on students’ quantitative reasoning skills using existing domain-specific tests, offers a practical alternative to broad test batteries for assessing students’ learning outcomes in higher education.

A novel neural network model fusion approach for improving medical named entity recognition in online health expert question-answering services

Because of the frequent occurrence of chronic diseases, the COVID-19 pandemic, etc., online health expert question-answering (HQA) services have been unable to cope with the rapidly increasing demand for online consultations. Building a virtual health assistant based on medical named entity recognition (NER) can effectively assist with the consultation process, but the unstandardized expressions within HQA text pose a serious challenge for medical NER tasks. The main goal of this study is to propose a novel deep medical NER approach based on a collaborative decision strategy (CDS), i.e., co_decision_NER (CDN), that can identify standard and nonstandard medical entities in the HQA context. We collected 10,000 question–answer pairs from HaoDF, extracted medical entities from 15 entity categories, and used a CDS to fuse the advantages of different NER models. Ultimately, CDN achieved a performance (precision = 84.50%, recall = 84.30%, F1 = 84.40%) that was significantly better than that of the state-of-the-art (SOTA) method. Our empirical analysis suggests that the entity types Disease (DIS), Sign (SIG), Test (TES), Drug (DRU), Surgery (SUR), Precaution (PRE), and Region (REG) can be most easily expressed arbitrarily in the doctor–patient interaction scenario of HQA services. In addition, CDN can identify not only standard but also nonstandard medical entities, effectively alleviating the severe out-of-vocabulary (OOV) problem faced by HQA services when performing medical NER tasks. The core contribution of this study is the development of a novel neural network model fusion algorithm that can improve the performance of entity recognition in medical domain-specific tasks.

The analysis of data metamodels’ extensional layer via extended generalized graph

There are several limitations known in data modeling discipline, which are related directly to the traditionally used data modeling languages expressiveness. The strong limitations of the expressiveness of the existing well known data modelling languages combined with the lack of a very general universal data modeling language have negative impact to modelling naturalness. As the result of mentioned limits the reality must be transformed to avoid (workaround) the limits introduced by the modelling language. In turn, the transformation process requires extra effort. The problem is strengthened by the lack of mechanisms, which can be used to measure the expressiveness of a particular data modeling language. Some limitations of the existing data modeling languages result from both their metamodel (abstract syntax) and model (metamodel instance) graph-like structure constraints. This kind of limits also has negative impact to a domain-specific modeling naturalness. The paper addresses all problems mentioned above. The problems can be solved with the help of the EGG data modeling language introduced in the paper. First, a universal and customizable EGG data modeling language together with the customization mechanisms (extensions and generalizations) is introduced. According to the first usage scenario the EGG may be applied for domain-specific data modelling tasks in place of other data modeling languages. Second, the paper proposes and applies (for some data modeling languages: RDF, XML, RDBM, UML and AOM) a novel concept of measuring and comparing data modelling languages via mapping their metamodels to the EGG metamodel. So, according to the second usage scenario the EGG metamodel can be used as a reference metamodel for the data modeling language expressiveness comparative studies. It may also support the decision process when a data modeling language must be chosen for a particular domain-specific data modeling task. Third, the EGG introduced in the paper helps to avoid transforming reality to the needs resulting from the data modeling language as the EGG is general enough for the domain data modeling task. Complete abstract syntax of the Extended Generalized Graph is introduced and is expressed through its implementations in terms of the Association-Oriented Metamodel and the Unified Modeling Language. Semantics of each syntactical category of abstract syntax is described. Two complete concrete syntaxes for the Extended Generalized Graph are also introduced in the paper. The case studies related to both social network and knowledge modeling illustrate the applicability and usefulness of the EGG. syntax is compared to several other metamodels. The comparative study of the case study models created first in different metamodels and then expressed in the Extended Generalized Graph metamodel is summarized quantitatively in the form of a proposed measure.

The performance difference of interdisciplinary teams in the field specific and general innovation tasks

Collaborative innovation in interdisciplinary teams is a collaborative approach to accomplish cooperative tasks and achieve innovative goals through a multidisciplinary intersection in the form of member combinations. The purpose of this study was to reveal the neural mechanisms underlying the impact of interdisciplinary collaboration on groups and individuals. Each group of subjects consisted of two people with and without a design background, who were asked to solve two realistic presented problems (RPP), and two design innovation tasks based on RPP adaptations. The study used hyperscanning of functional near-infrared spectroscopic (fNIRS) brain functional imaging techniques to simultaneously record the neural responses of interacting participants in each group. The study compared the innovation performance of interdisciplinary teams with design backgrounds in domain-specific versus domain-general innovation tasks, and the results showed differences in individual and group performance in different types of innovation tasks, with individual fluency being the most significant. The study may provide empirical evidence for the performance benefits of interdisciplinary teams in real-world collaborative co-innovation.

Medical text classification based on the discriminative pre-training model and prompt-tuning.

Medical text classification, as a fundamental medical natural language processing task, aims to identify the categories to which a short medical text belongs. Current research has focused on performing the medical text classification task using a pre-training language model through fine-tuning. However, this paradigm introduces additional parameters when training extra classifiers. Recent studies have shown that the "prompt-tuning" paradigm induces better performance in many natural language processing tasks because it bridges the gap between pre-training goals and downstream tasks. The main idea of prompt-tuning is to transform binary or multi-classification tasks into mask prediction tasks by fully exploiting the features learned by pre-training language models. This study explores, for the first time, how to classify medical texts using a discriminative pre-training language model called ERNIE-Health through prompt-tuning. Specifically, we attempt to perform prompt-tuning based on the multi-token selection task, which is a pre-training task of ERNIE-Health. The raw text is wrapped into a new sequence with a template in which the category label is replaced by a [UNK] token. The model is then trained to calculate the probability distribution of the candidate categories. Our method is tested on the KUAKE-Question Intention Classification and CHiP-Clinical Trial Criterion datasets and obtains the accuracy values of 0.866 and 0.861. In addition, the loss values of our model decrease faster throughout the training period compared to the fine-tuning. The experimental results provide valuable insights to the community and suggest that prompt-tuning can be a promising approach to improve the performance of pre-training models in domain-specific tasks.