results: 文中对多种深度学习文本分类方法进行比较和总结,以便选择合适的方法 для实际应用。Abstract
In recent years, with the rapid development of information on the Internet, the number of complex texts and documents has increased exponentially, which requires a deeper understanding of deep learning methods in order to accurately classify texts using deep learning techniques, and thus deep learning methods have become increasingly important in text classification. Text classification is a class of tasks that automatically classifies a set of documents into multiple predefined categories based on their content and subject matter. Thus, the main goal of text classification is to enable users to extract information from textual resources and process processes such as retrieval, classification, and machine learning techniques together in order to classify different categories. Many new techniques of deep learning have already achieved excellent results in natural language processing. The success of these learning algorithms relies on their ability to understand complex models and non-linear relationships in data. However, finding the right structure, architecture, and techniques for text classification is a challenge for researchers. This paper introduces deep learning-based text classification algorithms, including important steps required for text classification tasks such as feature extraction, feature reduction, and evaluation strategies and methods. At the end of the article, different deep learning text classification methods are compared and summarized.
摘要
Recently, with the rapid development of information on the internet, the number of complex texts and documents has increased exponentially, requiring a deeper understanding of deep learning methods to accurately classify texts using deep learning techniques. As a result, deep learning methods have become increasingly important in text classification. Text classification is a type of task that automatically classifies a set of documents into multiple predefined categories based on their content and subject matter. Therefore, the main goal of text classification is to enable users to extract information from textual resources and perform processes such as retrieval, classification, and machine learning techniques together to classify different categories. Many new techniques of deep learning have already achieved excellent results in natural language processing. The success of these learning algorithms relies on their ability to understand complex models and non-linear relationships in data. However, finding the right structure, architecture, and techniques for text classification is a challenge for researchers. This paper introduces deep learning-based text classification algorithms, including important steps required for text classification tasks such as feature extraction, feature reduction, and evaluation strategies and methods. At the end of the article, different deep learning text classification methods are compared and summarized.Note: Please note that the translation is in Simplified Chinese, which is one of the two standard Chinese writing systems. If you need the translation in Traditional Chinese, please let me know.
Does the “most sinfully decadent cake ever” taste good? Answering Yes/No Questions from Figurative Contexts
for: investigate the robustness of Question Answering (QA) models on figurative text
methods: use yes/no questions with figurative and non-figurative contexts to test the models’ ability to understand figurative language
results: state-of-the-art BERT-based QA models perform poorly on figurative contexts, but models like GPT-3 and ChatGPT can handle them better, and further performance gains can be achieved by automatically simplifying the figurative contexts.Abstract
Figurative language is commonplace in natural language, and while making communication memorable and creative, can be difficult to understand. In this work, we investigate the robustness of Question Answering (QA) models on figurative text. Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models. We propose FigurativeQA, a set of 1000 yes/no questions with figurative and non-figurative contexts, extracted from the domains of restaurant and product reviews. We show that state-of-the-art BERT-based QA models exhibit an average performance drop of up to 15\% points when answering questions from figurative contexts, as compared to non-figurative ones. While models like GPT-3 and ChatGPT are better at handling figurative texts, we show that further performance gains can be achieved by automatically simplifying the figurative contexts into their non-figurative (literal) counterparts. We find that the best overall model is ChatGPT with chain-of-thought prompting to generate non-figurative contexts. Our work provides a promising direction for building more robust QA models with figurative language understanding capabilities.
摘要
通用语言中的比喻语言非常普遍,它可以使交流更加生动、创新,但同时也可以使得理解变得更加困难。在这项工作中,我们研究了问答模型对比喻文本的Robustness。特别是yes/no问题,是 figural语言理解能力的一种有用的检验。我们提出了一个名为FigurativeQA的1000个yes/no问题的集合,其中包括了餐厅和产品评论中的figural和非 figural上下文。我们发现,当问答模型回答figural上下文中的问题时,其性能会下降15%左右,相比于非 figural上下文。虽然模型如GPT-3和ChatGPT能够更好地处理figural语言,但我们发现可以通过自动将figural上下文简化成非 figural(literal)上下文来提高性能。我们发现最佳的模型是ChatGPT加chain-of-thought提示,可以生成非 figural上下文。我们的工作提供了构建更加Robust的问答模型的可能方向。
Multiple Relations Classification using Imbalanced Predictions Adaptation
paper_authors: Sakher Khalil Alqaaidi, Elika Bozorgi, Krzysztof J. Kochut
for: 这个论文主要用于关系分类任务中处理多个关系的问题。
methods: 该模型使用自定义输出架构和采用额外输入特征来解决不均匀预测问题。
results: 对于一些常用的数据集,模型表现出了显著的改善,尤其是在处理不均匀预测的情况下。Abstract
The relation classification task assigns the proper semantic relation to a pair of subject and object entities; the task plays a crucial role in various text mining applications, such as knowledge graph construction and entities interaction discovery in biomedical text. Current relation classification models employ additional procedures to identify multiple relations in a single sentence. Furthermore, they overlook the imbalanced predictions pattern. The pattern arises from the presence of a few valid relations that need positive labeling in a relatively large predefined relations set. We propose a multiple relations classification model that tackles these issues through a customized output architecture and by exploiting additional input features. Our findings suggest that handling the imbalanced predictions leads to significant improvements, even on a modest training design. The results demonstrate superiority performance on benchmark datasets commonly used in relation classification. To the best of our knowledge, this work is the first that recognizes the imbalanced predictions within the relation classification task.
摘要
“关系分类任务是将对象和主题实体对应的Semantic关系分类为正确的类别,这个任务在文本挖掘应用中扮演着关键角色,如知识图构建和生物医学文本中实体互动发现。现有关系分类模型采用多种方法来识别单句中的多个关系,但它们忽略了不均匀预测模式。这种模式来自于一些有效的关系,它们需要在大量预定的关系集中得到正面标注。我们提出了一种多关系分类模型,通过自定义输出架构和采用额外输入特征来解决这些问题。我们的发现表明,处理不均匀预测可以取得显著改善,即使在较小的训练设计下。结果表明我们的模型在常用的 benchmark 数据集上显示出了优秀的表现,并且根据我们所知,这是第一个认可关系分类任务中的不均匀预测问题的研究。”
MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
results: 研究结果显示,MentalLLaMA可以与状态艺术方法匹配,并且生成高质量的解释。Abstract
With the development of web technology, social media texts are becoming a rich source for automatic mental health analysis. As traditional discriminative methods bear the problem of low interpretability, the recent large language models have been explored for interpretable mental health analysis on social media, which aims to provide detailed explanations along with predictions. The results show that ChatGPT can generate approaching-human explanations for its correct classifications. However, LLMs still achieve unsatisfactory classification performance in a zero-shot/few-shot manner. Domain-specific finetuning is an effective solution, but faces 2 challenges: 1) lack of high-quality training data. 2) no open-source LLMs for interpretable mental health analysis were released to lower the finetuning cost. To alleviate these problems, we build the first multi-task and multi-source interpretable mental health instruction (IMHI) dataset on social media, with 105K data samples. The raw social media data are collected from 10 existing sources covering 8 mental health analysis tasks. We use expert-written few-shot prompts and collected labels to prompt ChatGPT and obtain explanations from its responses. To ensure the reliability of the explanations, we perform strict automatic and human evaluations on the correctness, consistency, and quality of generated data. Based on the IMHI dataset and LLaMA2 foundation models, we train MentalLLaMA, the first open-source LLM series for interpretable mental health analysis with instruction-following capability. We also evaluate the performance of MentalLLaMA on the IMHI evaluation benchmark with 10 test sets, where their correctness for making predictions and the quality of explanations are examined. The results show that MentalLLaMA approaches state-of-the-art discriminative methods in correctness and generates high-quality explanations.
摘要
随着网络技术的发展,社交媒体文本正在成为自动心理健康分析的丰富来源。传统的排除性方法具有低可解释性问题,而最近的大语言模型在社交媒体上进行可解释心理健康分析,旨在提供详细的解释以及预测。结果显示,ChatGPT可以生成接近人类解释的正确分类结果。然而,LLMs仍在零容量/几容量情况下实现不满足的分类性能。预处理特定领域的训练是有效的解决方案,但面临两个挑战:1)缺乏高质量训练数据。2)没有开源LLMs для可解释心理健康分析,以降低训练成本。为解决这些问题,我们建立了首个多任务多源可解释心理健康指令(IMHI)数据集,包括105W个数据样本。 raw社交媒体数据由10个现有源收集,覆盖8个心理健康分析任务。我们使用专家写的少量示例和收集的标签来提取ChatGPT的回答,并对其生成的数据进行严格的自动和人类评估,以确保数据的正确性、一致性和质量。基于IMHI数据集和LLaMA2基础模型,我们训练了心理LLaMA,首个开源LLM系列 для可解释心理健康分析,并实现了指令遵循能力。我们还对IMHI评估标准测试集进行了10个测试集的性能评估,其中正确性和生成的解释质量均进行了评估。结果显示,心理LLaMA与状态艺术方法相当,并生成高质量的解释。
Substituting Data Annotation with Balanced Updates and Collective Loss in Multi-label Text Classification
results: 实验结果显示,提案的框架在具有仅具有几个标签的低监控情况下可以获得有效的性能,并且相比使用预训语言模型时,提案的方法可以提高性能 BY 70%。Abstract
Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text, and has a wide range of application domains. Most existing approaches require an enormous amount of annotated data to learn a classifier and/or a set of well-defined constraints on the label space structure, such as hierarchical relations which may be complicated to provide as the number of labels increases. In this paper, we study the MLTC problem in annotation-free and scarce-annotation settings in which the magnitude of available supervision signals is linear to the number of labels. Our method follows three steps, (1) mapping input text into a set of preliminary label likelihoods by natural language inference using a pre-trained language model, (2) calculating a signed label dependency graph by label descriptions, and (3) updating the preliminary label likelihoods with message passing along the label dependency graph, driven with a collective loss function that injects the information of expected label frequency and average multi-label cardinality of predictions. The experiments show that the proposed framework achieves effective performance under low supervision settings with almost imperceptible computational and memory overheads added to the usage of pre-trained language model outperforming its initial performance by 70\% in terms of example-based F1 score.
摘要
多标签文本分类(MLTC)是将多个标签分配给一个文本的任务,具有广泛的应用领域。大多数现有方法需要巨大量的注释数据来学习一个分类器和/或一组定义的约束,例如层次关系,这些约束可能会变得复杂,特别是当标签数量增加时。在这篇论文中,我们研究了在无注释和缺乏注释的设置下进行MLTC问题。我们的方法包括以下三步:1. 将输入文本映射到一组初步的标签可能性,使用一个预训练的自然语言模型进行自然语言推理。2. 计算一个签名标签依赖图,使用标签描述来计算。3. 更新初步的标签可能性,使用消息传递算法在标签依赖图上进行更新,驱动一个集体损失函数,该函数注入预期的标签频率和预测多个标签 cardinality的信息。实验表明,我们的框架在低级注释设置下达到了有效性,并且增加了非常小的计算和存储开销,相对于使用预训练自然语言模型的使用,提高了70%的例子基于F1分数。
The Study of Perceptual Training of Chinese Mandarin Tones for Monolingual Speakers of English Using Adaptive Computer Based Training Software
results: 研究发现,使用该新技术可以提高学生对声调的识别和生成能力,并且可以帮助学生更好地理解和使用声调。Abstract
The study explored a new technique of phonetic tone training, which may have a positive impact on second language learning and tone training.
摘要
研究探讨了一种新的声音训练技巧,这种技巧可能对第二语言学习和声音训练产生积极影响。Here's a breakdown of the translation:研究 (study)探讨 (explored)一种 (a new)声音 (phonetic)训练 (training)技巧 (technique)可能 (may)对 (positive impact on)第二语言 (second language)学习 (learning)和 (and)声音 (tone)训练 (training)产生 (have a positive impact)