Classification of Conversational Sentences Using an Ensemble Pre-Trained Language Model with the Fine-Tuned Parameter

Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.

Word Embeddings and Semantic Spaces in Natural Language Processing

One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.

Six-Writings multimodal processing with pictophonetic coding to enhance Chinese language models

While large language models(LLMs)have made significant strides in natural language processing(NLP),they continue to face challenges in adequately addressing the intricacies of the Chinese language in certain scenarios.We propose a framework called Six-Writings multimodal processing(SWMP)to enable direct integration of Chinese NLP(CNLP)with morphological and semantic elements.The first part of SWMP,known as Six-Writings pictophonetic coding(SWPC),is introduced with a suitable level of granularity for radicals and components,enabling effective representation of Chinese characters and words.We conduct several experimental scenarios,including the following:(1)We establish an experimental database consisting of images and SWPC for Chinese characters,enabling dual-mode processing and matrix generation for CNLP.(2)We characterize various generative modes of Chinese words,such as thousands of Chinese idioms,used as question-and-answer(Q&A)prompt functions,facilitating analogies by SWPC.The experiments achieve 100%accuracy in answering all questions in the Chinese morphological data set(CA8-Mor-10177).(3)A fine-tuning mechanism is proposed to refine word embedding results using SWPC,resulting in an average relative error of≤25%for 39.37%of the questions in the Chinese wOrd Similarity data set(COS960).The results demonstrate that SWMP/SWPC methods effectively capture the distinctive features of Chinese and offer a promising mechanism to enhance CNLP with better efficiency.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

MOSS:An Open Conversational Large Language Model

Conversational large language models(LLMs)such as ChatGPT and GPT-4 have recently exhibited remarkable capabilities across various domains,capturing widespread attention from the public.To facilitate this line of research,in this paper,we report the development of MOSS,an open-sourced conversational LLM that contains 16 B parameters and can perform a variety of instructions in multi-turn interactions with humans.The base model of MOSS is pre-trained on large-scale unlabeled English,Chinese,and code data.To optimize the model for dialogue,we generate 1.1 M synthetic conversations based on user prompts collected through our earlier versions of the model API.We then perform preference-aware training on preference data annotated from AI feedback.Evaluation results on real-world use cases and academic benchmarks demonstrate the effectiveness of the proposed approaches.In addition,we present an effective practice to augment MOSS with several external tools.Through the development of MOSS,we have established a complete technical roadmap for large language models from pre-training,supervised fine-tuning to alignment,verifying the feasibility of chatGPT under resource-limited conditions and providing a reference for both the academic and industrial communities.Model weights and code are publicly available at https://github.com/OpenMOSS/MOSS.

Event-driven process execution model for process virtual machine

Current orchestration and choreography process engines only serve with dedicate process languages.To solve these problems,an Event-driven Process Execution Model(EPEM) was developed.Formalization and mapping principles of the model were presented to guarantee the correctness and efficiency for process transformation.As a case study,the EPEM descriptions of Web Services Business Process Execution Language(WS-BPEL) were represented and a Process Virtual Machine(PVM)-OncePVM was implemented in compliance with the EPEM.

XML-based Data Processing in Network Supported Collaborative Design

In the course of network supported collaborative design, the data processing plays a very vital role. Much effort has been spent in this area, and many kinds of approaches have been proposed. Based on the correlative materials, this paper presents extensible markup language （XML） based strategy for several important problems of data processing in network supported collaborative design, such as the representation of standard for the exchange of product model data （STEP） with XML in the product information expression and the management of XML documents using relational database. The paper gives a detailed exposition on how to clarify the mapping between XML structure and the relationship database structure and how XML-QL queries can be translated into structured query language （SQL） queries. Finally, the structure of data processing system based on XML is presented.

Formalization and Verification of Business Process Modeling Based on UML and Petri Nets

In order to provide a quantitative analysis and verification method for activity diagrams based business process modeling, a formal definition of activity diagrams is introduced. And the basic requirements for activity diagrams based business process models are proposed. Furthermore, the standardized transformation technique between business process models and basic Petri nets is presented and the analysis method for the soundness and well-structured properties of business processes is introduced.

3D Model Reconstruction Based on Process Information

The traditional strategy of 3D model reconstruction mainly concentrates on orthographic projections or engineering drawings. But there are some shortcomings. Such as, only few kinds of solids can be reconstructed, the high complexity of time and less information about the 3D model. The research is extended and process card is treated as part of the 3D reconstruction. A set of process data is a superset of 2D engineering drawings set. The set comprises process drawings and process steps, and shows a sequencing and asymptotic course that a part is made from roughcast blank to final product. According to these characteristics, the object to be reconstructed is translated from the complicated engineering drawings into a series of much simpler process drawings. With the plentiful process information added for reconstruction, the disturbances such as irrelevant graph, symbol and label, etc. can be avoided. And more, the form change of both neighbor process drawings is so little that the engineering drawings interpretation has no difficulty; in addition, the abnormal solution and multi-solution can be avoided during reconstruction, and the problems of being applicable to more objects is solved ultimately. Therefore, the utility method for 3D reconstruction model will be possible. On the other hand, the feature information in process cards is provided for reconstruction model. Focusing on process cards, the feasibility and requirements of Working Procedure Model reconstruction is analyzed, and the method to apply and implement the Natural Language Understanding into the 3D reconstruction is studied. The method of asymptotic approximation product was proposed, by which a 3D process model can be constructed automatically and intelligently. The process model not only includes the information about parts characters, but also can deliver the information of design, process and engineering to the downstream applications.

TG-SMR:AText Summarization Algorithm Based on Topic and Graph Models

Recently,automation is considered vital in most fields since computing methods have a significant role in facilitating work such as automatic text summarization.However,most of the computing methods that are used in real systems are based on graph models,which are characterized by their simplicity and stability.Thus,this paper proposes an improved extractive text summarization algorithm based on both topic and graph models.The methodology of this work consists of two stages.First,the well-known TextRank algorithm is analyzed and its shortcomings are investigated.Then,an improved method is proposed with a new computational model of sentence weights.The experimental results were carried out on standard DUC2004 and DUC2006 datasets and compared to four text summarization methods.Finally,through experiments on the DUC2004 and DUC2006 datasets,our proposed improved graph model algorithm TG-SMR(Topic Graph-Summarizer)is compared to other text summarization systems.The experimental results prove that the proposed TG-SMR algorithm achieves higher ROUGE scores.It is foreseen that the TG-SMR algorithm will open a new horizon that concerns the performance of ROUGE evaluation indicators.

A Study on the Importance of Language Input in Second Language Acquisition(SLA)

Input theory as a theoretical foundation in language teaching plays an important role in SLA.Though a wealth of re⁃search has been done by linguists to demonstrate the importance of language input in SLA,little has been written about the type and amount of language input for successful SLA,especially its processing model while acquiring a second language.This paper first discusses the Krashen’s input hypothesis in language learning,and then an introduction to Chaudron’s processing model of in⁃put is made.In the final part,the author explains the acquisition process based on word acquisition and grammar acquisition and concludes that in the process of acquiring a second language,the language learners reconstruct a new cognitive model by taking in consistent comprehensible language input.

A PERT-BiLSTM-Att Model for Online Public Opinion Text Sentiment Analysis

As an essential category of public event management and control,sentiment analysis of online public opinion text plays a vital role in public opinion early warning,network rumor management,and netizens’person-ality portraits under massive public opinion data.The traditional sentiment analysis model is not sensitive to the location information of words,it is difficult to solve the problem of polysemy,and the learning representation ability of long and short sentences is very different,which leads to the low accuracy of sentiment classification.This paper proposes a sentiment analysis model PERT-BiLSTM-Att for public opinion text based on the pre-training model of the disordered language model,bidirectional long-term and short-term memory network and attention mechanism.The model first uses the PERT model pre-trained from the lexical location information of a large amount of corpus to process the text data and obtain the dynamic feature representation of the text.Then the semantic features are input into BiLSTM to learn context sequence information and enhance the model’s ability to represent long sequences.Finally,the attention mechanism is used to focus on the words that contribute more to the overall emotional tendency to make up for the lack of short text representation ability of the traditional model,and then the classification results are output through the fully connected network.The experimental results show that the classification accuracy of the model on NLPCC14 and weibo_senti_100k public data sets reach 88.56%and 97.05%,respectively,and the accuracy reaches 95.95%on the data set MDC22 composed of Meituan,Dianping and Ctrip comment.It proves that the model has a good effect on sentiment analysis of online public opinion texts on different platforms.The experimental results on different datasets verify the model’s effectiveness in applying sentiment analysis of texts.At the same time,the model has a strong generalization ability and can achieve good results for sentiment analysis of datasets in different fields.

自然语言处理领域中的词嵌入方法综述

词嵌入作为自然语言处理任务的第一步,其目的是将输入的自然语言文本转换为模型可以处理的数值向量,即词向量,也称词的分布式表示。词向量作为自然语言处理任务的根基,是完成一切自然语言处理任务的前提。然而,国内外针对词嵌入方法的综述文献大多只关注于不同词嵌入方法本身的技术路线,而未能将词嵌入的前置分词方法以及词嵌入方法完整的演变趋势进行分析与概述。以word2vec模型和Transformer模型作为划分点,从生成的词向量是否能够动态地改变其内隐的语义信息来适配输入句子的整体语义这一角度,将词嵌入方法划分为静态词嵌入方法和动态词嵌入方法,并对此展开讨论。同时,针对词嵌入中的分词方法,包括整词切分和子词切分,进行了对比和分析;针对训练词向量所使用的语言模型,从概率语言模型到神经概率语言模型再到如今的深度上下文语言模型的演化,进行了详细列举和阐述;针对预训练语言模型时使用的训练策略进行了总结和探讨。最后,总结词向量质量的评估方法,分析词嵌入方法的当前现状并对其未来发展方向进行展望。

JADE-DB:基于靶向变异的大语言模型安全通用基准测试集

提出大语言模型安全通用基准测试集—JADE-DB,该数据集基于靶向变异方法自动化构建,能够将经验丰富的大语言模型安全测试员和多学科专家学者手工撰写的测试问题转化为高危通用问题,保持语言自然性的同时不改变其核心语义,且能够攻破十余款国内外知名大语言模型的安全防护机制.根据语言复杂性差异,JADE-DB包含基础、进阶、高危3个安全测试等级,共计上千条覆盖违法犯罪、侵犯权益、歧视偏见和核心价值观4大类违规主题、30多种违规主题的通用测试问题,其中针对国内开源(中文,8款)、国内商用(中文,6款)和国外商用大语言模型(英文,4款)这3组大语言模型分别构建的3款通用高危测试集,可造成每组模型在高危测试集上的平均违规率均超过70%,测试问题均可同时触发多款模型违规生成.这表明,语言的复杂性导致现有大语言模型难以学习到人类无穷多种表达方式,因此无法识别其中不变的违规本质.

Pre-trained models for natural language processing: A survey

Recently, the emergence of pre-trained models(PTMs) has brought natural language processing(NLP) to a new era. In this survey, we provide a comprehensive review of PTMs for NLP. We first briefly introduce language representation learning and its research progress. Then we systematically categorize existing PTMs based on a taxonomy from four different perspectives. Next,we describe how to adapt the knowledge of PTMs to downstream tasks. Finally, we outline some potential directions of PTMs for future research. This survey is purposed to be a hands-on guide for understanding, using, and developing PTMs for various NLP tasks.

基于大语言模型的数据查询机器人在医学领域的应用

本研究对大语言模型(large language model,LLM)、数据查询机器人(data query robot,DQR)的发展历程和研究现状进行了介绍,同时通过实证分析,探讨了在数字医学领域中,基于LLM的DQR的实际应用效果及其在处理医疗数据查询和分析的复杂任务中的作用,证实了基于LLM的DQR能为非技术人员提供一个直观且便捷的工具,显著提升医疗数据的查询效率和分析能力。此外,本文还探讨了LLM和DQR技术在当前应用中的局限性及未来发展潜力,为进一步的研究和应用提供参考。

预训练大语言模型发展对中国数字创意产业的启示

预训练大语言模型与数字创意产业的结合,一方面可以促进预训练大语言模型技术研发和应用,推动自然语言处理相关产业发展,另一方面也可以为数字创意产业提供更高效、精准的解决方案,促进产业数字化转型升级。然而,目前中国预训练大语言模型在数字创意产业的运用主要侧重于文本识别生成和语音生成等领域。为此,通过阐述预训练大语言模型以及中国数字创意产业的发展现状,梳理预训练大语言模型在数字创意产业的应用范畴和商业布局,综合分析作为新质生产力引擎的预训练大语言模型在中国数字创意产业发展中的机遇与挑战,并为中国数字创意产业的发展提出建议。研究发现:融合发展是中国数字创意产业的重要趋势,网络文学、动漫游戏、短视频等细分产业开始发展出完整的产业链条;预训练大语言模型可提升数字创意产业的内容生成效率、丰富艺术创意、拓展数字娱乐形式,也可以加强社交媒体分析监测、提高跨语言应用的效率、辅助科研教育,带来提升数字创意产业的智能化水平、增强用户黏性、数字创意生产者身份多元化等机遇,但同时也面临数据成本、隐私安全、知识产权等问题。提出未来在预训练大语言模型应用于数字创意产业的发展中,重视构建相关监管评估框架和知识产权保护体系,提升多模态技术水平,强化智能算力体系建设,以推动数字创意产业的智能化发展。

基于Transformer的司法文书命名实体识别方法

命名实体识别是自然语言处理领域的关键任务之一,是实现下游任务的基础。目前针对司法领域的相关研究相对较少,司法系统的信息化和智能化转型仍有许多问题亟需解决。相比其他领域的文本,司法文书存在专业性强、语料资源少等局限,导致现有的司法文书识别结果较低。因此,从以下3方面开展研究:首先,提出了一种多标签层级迭代的文本标注方式,可以对原始司法文书文本进行自动化标注,同时有效地提升司法文书命名实体识别任务的实体识别效果;其次,提出了一种交融式的Transformer神经网络模型,对汉字固有属性的深层特征进行了充分利用,用于对司法文书进行命名实体识别;最后,对所提出的标注方法和模型与其他神经网络模型进行了对比实验。所提出的文本标注方式可以较为准确地实现司法文书的标注任务;同时,所提出的模型在通用数据集中相对于对照模型有较大的提高,并在司法领域数据集中取得了良好的效果。

基于主题模型的通用文本匹配方法

检测长文本和短文本相似性的应用场景越来越多,文本对的一致性检测大多可以统一抽象成文本相似性的比较问题。该问题的难点在于短文本是零散的,从而很难判断其属于哪个领域及其背景知识,也难以引入词嵌入来解决在通用场景的具体文本匹配问题。基于这个问题,提出一种新的基于文本聚类主题模型的轻量方法,不需要利用额外的背景知识来匹配通用文本相似性。在两个经典测试样本数据集上的实验结果表明,该方法的文本相似性检测效率非常高。

基于业务流程的认知图谱

针对目前软件项目开发过程中无法充分利用已有业务资源,进而导致开发效率低、能力弱等问题,通过研究业务资源之间的关联,提出一种基于业务流程的认知图谱。首先,通过正式文档抽取业务知识,提出建立知识层级的方法并修正;其次,通过代码特征挖掘与代码实体相似度判断构建代码网络表示模型;最后,利用实际业务数据进行实验验证,并与向量空间模型(VSM)、多样化排序和深度学习等方法进行对比。最终构建的基于业务流程的认知图谱在代码检索方面优于目前基于文本匹配的方法和深度学习算法,分别在前5准确率(precision@5)、平均精度均值(mAP)、归一化折扣增益值(?-NDCG)这3项指标上高过多样化排序的代码检索方法4.30、0.38和2.74个百分点,有效解决了潜在业务词汇识别、业务认知推理表示等多个问题,提升了代码检索效果与业务资源利用率。