第1期
ARTICLES
■ Maximizing RAG efficiency: A comparative analysis of RAG methods（最大化 RAG 效率： RAG 方法的比较分析） by Tolga Şakar, Hakan Emekci, Pages 1-25
■ Learning and semiautomatic intention labeling for classification models: a COVID-19 dialog attendance study for chatbots（分类模型的学习与半自动意图标注： 一项针对聊天机器人的 2019 冠状病毒疾病对话出勤研究） by Valmir Oliveira dos Santos Júnior, Marcos Antonio de Oliveira, Lívia Almada Cruz, Ticiana L. Coelho da Silva, Pages 26-55
■ Augmenting a Spanish clinical dataset for transformer-based linking of negations and their out-of-scope references（扩充一个西班牙临床数据集，用于基于变压器的否定链接及其超出范围的引用） by Antonio Jesús Tamayo-Herrera, Diego A. Burgos, Alexander Gelbukh, Pages 56-89
■ Statistical dataset evaluation: A case study on named entity recognition（统计数据集评估： 以命名实体识别为例） by Chengwen Wang, Qingxiu Dong, Xiaochen Wang, Zhifang Sui, Pages 90-110
■ Building a Turkish UCCA dataset（构建了一个土耳其语命名实体识别数据集） by Necva Bölücü, Burcu Can, Pages 111-149
■ CoAT: Corpus of artificial texts（CoAT: 人工文本语料库） by Tatiana Shamardina, Marat Saidov, Alena Fenogenova, Aleksandr Tumanov, Pages 150-175
BOOK REVIEWS
■ Python for Linguists, Cambridge: Cambridge University Press, 2020.（语言学中的Python，剑桥： 剑桥大学出版社，2020） by Pablo M. Tagarro, Igor Rodriguez, Maite Oronoz, Pages 176-180
第2期
ARTICLES
■ Preface: Special issue on Natural Language Processing applications for low-resource languages（前言： 低资源语言自然语言处理应用专刊） by Partha Pakray, Alexander Gelbukh, Sivaji Bandyopadhyay, Pages 181-182
■ Natural language processing applications for low-resource languages（面向低资源语言的自然语言处理应用） by Partha Pakray, Alexander Gelbukh, Sivaji Bandyopadhyay, Pages 183-197
■ A bidirectional LSTM-based morphological analyzer for Gujarati（基于双向长短时记忆模型的古吉拉特语形态分析器） by Jatayu Baxi, Brijesh Bhatt, Pages 198-214
■ Part-of-speech tagger for Bodo language using deep learning approach（基于深度学习方法的博多语词性标注） by Dhrubajyoti Pathak, Sanjib Narzary, Sukumar Nandi, Bidisha Som, Pages 215-229
■ Probing a pretrained RoBERTa on Khasi language for POS tagging（探索一种用于卡西语词性标注的预训练 RoBERTa） by Aiom Minnette Mitri, Eusebius Lawai Lyngdoh, Sunita Warjri, Goutam Saha,Saralin A. Lyngdoh, Pages 230-249
■ Is Attention always needed? A case study on language identification from speech（注意力总是需要的吗？ —— 从语音中识别语言的个案研究） by Atanu Mandal, Santanu Pal, Indranil Dutta, Mahidas Bhattacharya,Sudip Kumar Naskar, Pages 250-276
■ Cross-lingual dependency parsing for a language with a unique script（跨语言依存句法分析是针对具有独特脚本的语言进行的） by He Zhou, Daniel Dakota, Sandra Kübler, Pages 277-305
■ Improving neural machine translation by integrating transliteration for low-resource English–Assamese language（针对低资源的英语 - 阿萨姆语语言，通过整合音译改进神经机器翻译） by Basab Nath, Sunita Sarkar, Somnath Mukhopadhyay, Arindam Roy, Pages 306-327
■ Statistical machine translation for Indic languages（面向印度语言的统计机器翻译） by Sudhansu Bala Das, Divyajyoti Panda, Tapas Kumar Mishra, Bidyut Kr. Patra, Pages 328-345
■ EHMMQA: English, Hindi, and Marathi multilingual question answering framework using deep learning（基于深度学习的英语、印地语和马拉地语多语言问答框架） by Pawan Lahoti, Namita Mittal, Girdhari Singh, Pages 346-374
■ Does learning from language family help? A case study on a low-resource question-answering task（语族学习有帮助吗？ —— 一个低资源问答任务的案例研究） by Hariom A. Pandya, Brijesh S. Bhatt, Pages 375-392
■ Hate speech detection in low-resourced Indian languages: An analysis of transformer-based monolingual and multilingual models with cross-lingual experiments（低资源印度语中的仇恨语音检测： 基于转换器的单语和多语模型的跨语言实验分析） by Koyel Ghosh, Apurbalal Senapati, Pages 393-414
■ StereoHate: Toward identifying stereotypical bias and target group in hate speech detection（StereoHate: 识别仇恨语音检测中的刻板偏见和目标群体） by Krishanu Maity, Nilabja Ghosh, Raghav Jain, Sriparna Saha, Pushpak Bhattacharyya, Pages 415-434
■ Context-aware and expert data resources for Brazilian Portuguese hate speech detection（上下文感知和专家数据资源用于巴西葡萄牙语仇恨言论检测） by Francielle Vargas, Isabelle Carvalho, Thiago A. S. Pardo, Fabrício Benevenuto, Pages 435-456
■ Should we stay silent on violence? An ensemble approach to detect violent incidents in Spanish social media texts（我们应该对暴力保持沉默吗？ 西班牙语社交媒体文本中暴力事件检测的集成方法） by Deepawali Sharma, Vedika Gupta, Vivek Kumar Singh, David Pinto, Pages 457-476
■ Sentiment analysis of code-mixed Dravidian languages leveraging pretrained model and word-level language tag（基于预训练模型和词级语言标签的达罗毗荼语系混合语码情感分析） by Supriya Chanda, Anshika Mishra, Sukomal Pal, Pages 477-499
■ Towards a robust deep learning framework for Arabic sentiment analysis（面向阿拉伯语情感分析的鲁棒深度学习框架） by Azzam Radman, Rehab Duwairi, Pages 500-534
■ Predictive authoring for Brazilian Portuguese augmentative and alternative communication（巴西葡萄牙语扩大性和替代性沟通的预测性创作） by Jayr Pereira, Rodrigo Nogueira, Cleber Zanchettin, Robson Fidalgo, Pages 535-558
■ Intent detection and slot filling for Persian: Cross-lingual training for low-resource languages（波斯语的意图检测和插槽填充： 低资源语言的跨语言培训） by Reza Zadkamali, Saeedeh Momtazi, Hossein Zeinali, Pages 559-574
■ A case study on decompounding in Indian language IR（印度语信息检索中的分解个案研究） by Siba Sankar Sahu, Sukomal Pal, Pages 575-605
■ Automatic generation of nominal phrases for Portuguese and Galician（葡萄牙语和加利西亚语名词短语的自动生成） by María José Domínguez Vázquez, Alberto Simões, Daniel Bardanca Outeiriño, María Caíña Hurtado, José Luis Iglesias Allones, Pages 606-630
■ Word sense disambiguation corpus for Kashmiri（克什米尔语词义消歧语料库） by Tawseef Ahmad Mir, Aadil Ahmad Lawaye, Pages 631-654
■ Resource building and classification of Mizo folk songs（克什米尔米佐民歌资源建设与分类） by Esther Ramdinmawii, Sanghamitra Nath, Pages 655-673
■ Ben-Sarc: A self-annotated corpus for sarcasm detection from Bengali social media comments and its baseline evaluation（Ben-Sarc: 一个从孟加拉语社交媒体评论中识别讽刺的自标注语料库及其基线评估） by Sanzana Karim Lora, G. M. Shahariar, Tamanna Nazmin, Noor Nafeur Rahman, Rafsan Rahman, Miyad Bhuiyan, Faisal Muhammad Shah, Pages 674-699
Survey Paper
■ Discourse annotation guideline for low-resource languages（面向低资源语言的话语标注指南） by Francielle Vargas, Wolfgang Schmeisser-Nieto, Zohar Rabinovich, Thiago A. S. Pardo, Fabrício Benevenuto, Pages 700-743
第3期
ARTICLES
■ Constructing ensembles for hate speech detection（构造集成的仇恨语音检测算法） by Izzet Emre Kucukkaya, Cagri Toraman, Pages 745-770
■ Improved bidirectional attention flow (BIDAF) model for Arabic machine reading comprehension（改进的双向注意力流模型用于阿拉伯语机器阅读理解） by Mariam M. Biltawi, Arafat Awajan, Sara Tedmori, Pages 771-799
■ Textual form features for text readability assessment（面向文本可读性评估的文本形态特征） by Wenjing Pan, Xia Li, Xiaoyin ChenRui Xu, Pages 800-841,
■ Thought flow nets: From single predictions to trains of model thought（思维流网络： 从单一预测到模型思路） by Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Pages 842-873
■ Dialogue agents 101: a beginner’s guide to critical ingredients for designing effective conversational systems（对话代理 101: 设计有效对话系统的关键要素初学者指南） by Shivani Kumar, Sumit Bhatia, Milan AggarwalTanmoy Chakraborty, Pages 874-912,
■ Linguistic synesthesia detection: Leveraging culturally enriched linguistic features（语言联觉检测： 利用文化丰富的语言特征） by Qingqing Zhao, Yunfei Long, Xiaotong JiangZhongqing Wang, Chu-Ren Huang, Guodong Zhou, Pages 913-935,
■ Topic aware probing: From sentence length prediction to idiom identification how reliant are neural language models on topic?（主题感知探测： 从句子长度预测到成语识别，神经语言模型对主题的依赖程度如何？） by Vasudevan Nedumpozhimana, John D. Kelleher, Pages 936-964
EMERGING TRENDS
■ Emerging trends: translationese（新兴趋势： 翻译用语） by Kenneth Church, Boyang Li, Peter VickersShiran Dudy, Richard Yue, Pages 965-981,
第4期
SURVEY PAPER
■ A survey of context in neural machine translation and its evaluation（神经机器翻译中的语境研究及其评价）Sheila Castilho, Rebecca Knowles, Pages 986-1016
ARTICLE
■ Calibration and context in human evaluation of machine translation（机器翻译人工评价中的校准和语境问题）Rebecca Knowles, Chi-kiu Lo, Pages 1017-1041
■ Evaluating NMT using the non-inferiority principle（使用非劣效性原则对机器翻译进行评价）María do Campo Bayón, Pilar Sánchez-Gijón, Pages 1042-1061
■ Evaluating optimal reference translations（评估最佳参考文献翻译）Vilém Zouhar, Věra Kloudová, Martin Popel, Ondřej Bojar, Pages 1062-1085
ERRATUM
■ Evaluating optimal reference translations – ERRATUM（评估最佳参考文献翻译 - 勘误表）Vilém Zouhar, Věra Kloudová, Martin Popel, Ondřej Bojar, Pages 1086
第5期
ARTICLES
■ Identification and summarisation of events from Twitter using clustering algorithms and deep neural network（基于聚类算法和深度神经网络的 Twitter 事件识别与摘要）by Kunal Chakma,Anupam Jamatia, Dwijen Rudrapal, Pages 1087-1115
■ Prompt tuning discriminative language models for hierarchical text classification（针对层次化文本分类，快速调优判别性语言模型）by Jaco du Toit ,Marcel Dunaiski, Pages 1116-1133
■ Verifying the robustness of automatic credibility assessment（验证自动可信度评估的鲁棒性）by Piotr Przybyła, Alexander Shvets, Horacio Saggion, Pages 1134-1162
■ Reliable uncertainty estimation in emotion recognition in conversation using conformal prediction framework（利用共形预测框架对会话中情感识别的不确定性进行可靠估计）by Samad Roohi, Richard Skarbez, Hien Duy Nguyen, Pages 1163-1186
SQUIB
■ Second language learning of degree expressions: A computational approach（程度表达式的第二语言学习： 一种计算方法）by Yan Cong, Pages 1187-1209
ARTICLE
■ Clinical information extraction for lower-resource languages and domains with few-shot learning using pretrained language models and prompting（使用预训练的语言模型和提示对低资源语言和领域进行少次学习的临床信息抽取）by Phillip Richter-Pechanski,Philipp Wiesenbach,Dominic Mathias Schwab,Christina Kiriakou, Nicolas Geis, Christoph Dieterich, Anette Frank, Pages 1210-1233
■ DarijaBanking: A new resource for overcoming language barriers in banking intent detection for Moroccan Arabic speakers（DarijaBanking: 为摩洛哥阿拉伯语使用者克服银行意图检测中的语言障碍的新资源）by Abderrahman Skiredj, Ferdaous Azhari, Ismail Berrada,Saad Ezzini, Pages 1234-1264
■ Chinese spelling correction based on Long Short-Term Memory Network-enhanced Transformer and dynamic adaptive weighted multi-task learning（基于长短期记忆网络增强型 Transformer 和动态自适应加权多任务学习的中文拼写校正）by Mingying Xu, Jie Liu, Kui Peng, Zhen Li, Pages 1265-1284
■ Chinese word segmentation with heterogeneous graph convolutional network（基于异构图卷积网络的中文分词）by Xuemei Tang, Qi Su, Jun Wang, Pages 1285-1307
BOOKREVIEW
■ Data Analytics for Discourse Analysis with Python: The Case of Therapy Talk, by Dennis Tay. （使用 Python 进行篇章分析的数据分析： The Case of Therapy）by Fengmei Cai,Xingbing Liu, Pages 1308-1311
INDUSTRY WATCH
■ Sovereign AI in 2025（2025 年的主权人工智能）by Robert Dale, Pages 1312-1321
ERRATUM
■ Thought flow nets: From single predictions to trains of model thought – ERRATUM（思维流网络： 从单一预测到模型思维 - 勘误表）by Hendrik Schuff,Heike Adel,Ngoc Thang Vu, Pages 1322
第6期
ARTICLES
■ Focal inferential infusion coupled with tractable density discrimination for implicit hate detection（局部推断灌注结合易处理密度判别的隐性憎恨检测） by Sarah Masud, Ashutosh Bajpai, Tanmoy Chakraborty, Pages 1323-1349
■ Multiclass hate speech detection with an aggregated dataset（基于聚合数据集的多类仇恨语音检测） by Sinéad Walsh, Paul Greaney, Pages 1350-1366
■ DocSpider: a dataset of cross-domain natural language querying for MongoDB（DocSpider: 针对 MongoDB 的跨域自然语言查询数据集） by Arif Görkem Özer, Recep Firat Cekinel, Ismail Hakki Toroslu, Pinar Karagoz, Pages 1367-1398
■ Enhancing security in text-to-SQL systems: A novel dataset and agent-based framework（增强文本到 sql 系统的安全性： 一个新颖的数据集和基于代理的框架） by Salmane Chafik, Saad Ezzini, Ismail Berrada, Pages 1399-1422
■ Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics（神经词嵌入的语义丰富： 利用分类学相似性增强分布式语义） by Dongqiang Yang, Xinru Zhang, Tonghui Han, Yi Liu, Pages 1423-1449
■ Propagating machine translation traits to predict potential impact on the target language（传播机器翻译特征以预测对目标语言的潜在影响） by Nora Aranberri, Jose A. Pascual, Pages 1450-1469
EMERGING TRENDS
■ Emerging trends: This is not cheating（新兴趋势： 这不是作弊） by Kenneth Ward Church, Pages 1470-1477
（以上为小编翻译，仅供参考）
登录
