2023年的计算语言学协会年会(ACL 2023)共包含26个领域,代表着当前前计算语言学和自然语言处理研究的不同方面。每个领域都有一组相关联的关键字来描述其潜在的子领域, 这些子领域并非排他性的,它们只描述了最受关注的子领域,并希望能够对该领域包含的相关类型的工作提供一些更好的想法。
1.计算机领域顶会(A类)
会议简称 | 主要领域 | 会议全称 | 官网 | 截稿时间 | 会议时间 |
---|---|---|---|---|---|
CVPR2023 | 计算机视觉 | The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 | https://cvpr2023.thecvf.com/ | 2022.11.11 | 2023.6.18 |
ICCV2023 | 计算机视觉 | IEEE International Conference on Computer Vision | https://iccv2023.thecvf.com/ | 2023.3.8 | 2023.9.30 |
ECCV2022 | 计算机视觉 | European Conference on Computer Vision | https://eccv2022.ecva.net/ | 2022.10.23 | |
AAAI2023 | 人工智能 | National Conference of the American Association for Artificial Intelligence | https://aaai-23.aaai.org/ | 2022.8.8 | 2023.2.7 |
IJCAI 2023 | 人工智能 | National Conference of the American Association for Artificial Intelligence | https://ijcai-22.org/# | 2022.8.8 | 2023.2.7 |
NIPS2023 | 机器学习 | International Joint Conference on Artificial Intelligence | https://neurips.cc/Conferences/2022 | 2023.01 | 2023.07 |
ICML 2023 | 机器学习 | International Conference on Machine Learning | https://icml.cc/ | 2023.01 | 2023.06.24 |
ICLR 2023 | 机器学习 | International Conference on Learning Representations | https://iclr.cc/Conferences/2023 | 2022.09.21 | 2023.05.01 |
ICSE 2023 | 软件工程 | International Conference on Software Engineering | https://conf.researchr.org/home/icse-2023 | 2022.09.01 | 2023.05.14 |
SIGKDD 2023 | 数据挖掘 | ACM International Conference on Knowledge Discovery and Data Mining | https://kdd.org/kdd2022/index.html | 2023.02 | 2023.08 |
SIGIR 2023 | 数据挖掘 | ACM International Conference on Research and Development in Information Retrieval | https://sigir.org/sigir2022/ | 2023.01 | 2023.07 |
ACL 2023 | 计算语言 | Association of Computational Linguistics | https://www.2022.aclweb.org/ | 2022.11 | 2023.05 |
ACM MM 2023 | 多媒体 | ACM International Conference on Multimedia | https://2023.acmmmsys.org/participation/important-dates/ | 2022.11.18 | 2023.6.7 |
WWW2023 | 网络应用 | International World Wide Web Conference | https://www2023.thewebconf.org/ | 2022.10.6 | 2023.05.01 |
SIGGRAPH 2023 | 图形学 | ACM SIG International Conference on Computer Graphics and Interactive Techniques | https://s2022.siggraph.org/ | 2023.01 | 2023.08 |
CHI 2023 | 人机交互 | ACM Conference on Human Factors in Computing Systems | https://chi2023.acm.org/ | 2022.09.08 | 2023.04.23 |
CSCW 2023 | 人机交互 | ACM Conference on Computer Supported Cooperative Work and Social Computing | https://cscw.acm.org/2023/ | 2023.01.15 | 2023.10.13 |
CCS 2023 | 信息安全 | ACM Conference on Computer and Communications Security | https://www.sigsac.org/ccs/CCS2022/ | 2023.01 | 2023.11 |
VLDB 2023 | 数据管理 | International Conference on Very Large Data Bases | https://www.vldb.org/2023/?submission-guidelines | 2023.03.01 | 2023.08.28 |
STOC 2023 | 计算机理论 | ACM Symposium on the Theory of Computing | http://acm-stoc.org/stoc2022/ | 2022.11 | 2023.06 |
2.ACL 2023自然语言处理(NLP)研究子方向领域汇总
(一)计算社会科学和文化分析 (Computational Social Science and Cultural Analytics)
- 人类行为分析 (Human behavior analysis)
- 态度检测 (Stance detection)
- 框架检测和分析 (Frame detection and analysis)
- 仇恨言论检测 (Hate speech detection)
- 错误信息检测和分析 (Misinformation detection and analysis)
- 人口心理画像预测 (psycho-demographic trait prediction)
- 情绪检测和分析 (emotion detection and analysis)
- 表情符号预测和分析 (emoji prediction and analysis)
- 语言和文化偏见分析 (language/cultural bias analysis)
- 人机交互 (human-computer interaction)
- 社会语言学 (sociolinguistics)
- 用于社会分析的自然语言处理工具 (NLP tools for social analysis)
- 新闻和社交媒体的定量分析 (quantiative analyses of news and/or social media)
(二)对话和交互系统 (Dialogue and Interactive Systems)
- 口语对话系统 (Spoken dialogue systems)
- 评价指标 (Evaluation and metrics)
- 任务型 (Task-oriented)
- 人工介入 (Human-in-a-loop)
- 偏见和毒性 (Bias/toxity)
- 事实性 (Factuality)
- 检索 (Retrieval)
- 知识增强 (Knowledge augmented)
- 常识推理 (Commonsense reasoning)
- 互动讲故事 (Interactive storytelling)
- 具象代理人 (Embodied agents)
- 应用 (Applications)
- 多模态对话系统 (Multi-modal dialogue systems)
- 知识驱动对话 (Grounded dialog)
- 多语言和低资源 (Multilingual / low-resource)
- 对话状态追踪 (Dialogue state tracking)
- 对话建模 (Conversational modeling)
(三)话语和语用学 (Discourse and Pragmatics)
- 回指消解 (Anaphora resolution)
- 共指消解 (Coreference resolution)
- 桥接消解 (Bridging resolution)
- 连贯 (Coherence)
- 一致 (Cohesion)
- 话语关系 (Discourse relations)
- 话语分析 (Discourse parsing)
- 对话 (Dialogue)
- 会话 (Conversation)
- 话语和多语性 (Dialugue and multilinguality)
- 观点挖掘 (Argument mining)
- 交际 (Communication)
(四)自然语言处理和伦理 (Ethics and NLP)
- 数据伦理 (Data ethics)
- 模型偏见和公正性评价 (Model bias/fairness evaluation)
- 减少模型的偏见和不公平性 (Model bias/unfairness mitigation)
- 自然语言处理中的人类因素 (Human factors in NLP)
- 参与式和基于社群的自然语言处理 (Participatory/community-based NLP)
- 自然语言处理应用中的道德考虑 (Ethical considerations in NLP)
- 透明性 (Transparency)
- 政策和治理 (Policy and governance)
- 观点和批评 (Reflections and critiques)
(五)语言生成 (Generation)
- 人工评价 (Human evaluation)
- 自动评价 (Automatic evaluation)
- 多语言 (Multilingualism)
- 高效模型 (Efficient models)
- 少样本生成 (Few-shot generation)
- 分析 (Analysis)
- 领域适应 (Domain adaptation)
- 数据到文本生成 (Data-to-text generation)
- 文本到文博生成 (Text-to-text generation)
- 推断方法 (Inference methods)
- 模型结构 (Model architectures)
- 检索增强生成 (Retrieval-augmented generation)
- 交互和合作生成 (Interactive and collaborative generation)
(六)信息抽取 (Information Extraction)
- 命名实体识别和关系抽取 (Named entity recognition and relation extraction)
- 事件抽取 (Event extraction)
- 开放信息抽取 (Open information extraction)
- 知识库构建 (Knowledge base construction)
- 实体连接和消歧 (Entity linking and disambiguation)
- 文档级抽取 (Document-level extraction)
- 多语言抽取 (Multilingual extraction)
- 小样本和零样本抽取 (Zero-/few-shot extraction)
(七)信息检索和文本挖掘 (Information Retrieval and Text Mining)
- 段落检索 (Passage retrieval)
- 密集检索 (Dense retrieval)
- 文档表征 (Document representation)
- 哈希 (Hashing)
- 重排序 (Re-ranking)
- 预训练 (Pre-training)
- 对比学习 (Constrastive learning)
(八)自然语言处理模型的可解释性与分析 (Interpretability and Analysis of Models in NLP)
- 对抗性攻击/例子/训练 (Adversarial attacks/examples/training)
- 校正和不确定性 (Calibration/uncertainty)
- 反事实和对比解释 (Counterfactual/contrastive explanations)
- 数据影响 (Data influence)
- 数据瑕疵 (Data shortcuts/artifacts)
- 解释的忠诚度 (Explantion faithfulness)
- 特征归因 (Feature attribution)
- 自由文本和自然语言解释 (Free-text/natural language explanation)
- 样本硬度 (Hardness of samples)
- 结构和概念解释 (Hierarchical & concept explanations)
- 以人为主体的应用评估 (Human-subject application-grounded evaluations)
- 知识追溯、发现和推导 (Knowledge tracing/discovering/inducing)
- 探究 (Probing)
- 稳健性 (Robustness)
- 话题建模 (Topic modeling)
(九)视觉、机器人等领域的语言基础 (Language Grounding to Vision, Robotics and Beyond)
- 视觉语言导航 (Visual Language Navigation)
- 跨模态预训练 (Cross-modal pretraining)
- 图像文本匹配 (Image text macthing)
- 跨模态内容生成 (Cross-modal content generation)
- 视觉问答 (Visual question answering)
- 跨模态应用 (Cross-modal application)
- 跨模态信息抽取 (Cross-modal information extraction)
- 跨模态机器翻译 (Cross-modal machine translation)
(十)大模型(Large Language Models)
- 预训练 (Pre-training)
- 提示 (Prompting)
- 规模化 (Scaling)
- 稀疏模型 (Sparse models)
- 检索增强模型 (Retrieval-augmented models)
- 伦理 (Ethics)
- 可解释性和分析 (Interpretability/Analysis)
- 连续学习 (Continual learning)
- 安全和隐私 (Security and privacy)
- 应用 (Applications)
- 稳健性 (Robustness)
- 微调 (Fine-tuning)
(十一)语言多样性 (Language Diversity)
- 少资源语言 (Less-resource languages)
- 濒危语言 (Endangered languages)
- 土著语言 (Indigenous languages)
- 少数民族语言 (Minoritized languages)
- 语言记录 (Language documentation)
- 少资源语言的资源 (Resources for less-resourced languages)
- 软件和工具 (Software and tools)
(十二)语言学理论、认知建模和心理语言学 (Linguistic Theories, Cognitive Modeling and Psycholinguistics)
- 语言学理论 (Linguistic theories)
- 认知建模 (Cognitive modeling)
- 计算心理语言学 (Computational pyscholinguistics)
(十三)自然语言处理中的机器学习 (Machine Learning for NLP)
- 基于图的方法 (Graph-based methods)
- 知识增强的方法 (Knowledge-augmented methods)
- 多任务学习 (Multi-task learning)
- 自监督学习 (Self-supervised learning)
- 对比学习 (Contrastive learning)
- 生成模型 (Generation model)
- 数据增强 (Data augmentation)
- 词嵌入 (Word embedding)
- 结构化预测 (Structured prediction)
- 迁移学习和领域适应 (Transfer learning / domain adaptation)
- 表征学习 (Representation learning)
- 泛化 (Generalization)
- 模型压缩方法 (Model compression methods)
- 参数高效的微调方法 (Parameter-efficient finetuning)
- 少样本学习 (Few-shot learning)
- 强化学习 (Reinforcement learning)
- 优化方法 (Optimization methods)
- 连续学习 (Continual learning)
- 对抗学习 (Adversarial training)
- 元学习 (Meta learning)
- 因果关系 (Causality)
- 图模型 (Graphical models)
- 人参与的学习和主动学习 (Human-in-a-loop / Active learning)
(十四)机器翻译 (Machine Translation)
- 自动评价 (Automatic evaluation)
- 偏见 (Biases)
- 领域适应 (Domain adaptation)
- 机器翻译的高效推理方法 (Efficient inference for MT)
- 高效机器翻译训练 (Efficient MT training)
- 少样本和零样本机器翻译 (Few-/Zero-shot MT)
- 人工评价 (Human evaluation)
- 交互机器翻译 (Interactive MT)
- 机器翻译部署和维护 (MT deployment and maintainence)
- 机器翻译理论 (MT theory)
- 建模 (Modeling)
- 多语言机器翻译 (Multilingual MT)
- 多模态 (Multimodality)
- 机器翻译的线上运用 (Online adaptation for MT)
- 并行解码和非自回归的机器翻译 (Parallel decoding/non-autoregressive MT)
- 机器翻译预训练 (Pre-training for MT)
- 规模化 (Scaling)
- 语音翻译 (Speech translation)
- 转码翻译 (Code-switching translation)
- 词表学习 (Vocabulary learning)
(十五)多语言和跨语言自然语言处理 (Multilingualism and Cross-Lingual NLP)
- 转码 (Code-switching)
- 混合语言 (Mixed language)
- 多语言 (Multilingualism)
- 语言接触 (Language contact)
- 语言变迁 (Language change)
- 语言变体 (Language variation)
- 跨语言迁移 (Cross-lingual transfer)
- 多语言表征 (Multilingual representation)
- 多语言预训练 (Multilingual pre-training)
- 多语言基线 (Multilingual benchmark)
- 多语言评价 (Multilingual evaluation)
- 方言和语言变种 (Dialects and language varieties)
(十六)自然语言处理应用 (NLP Applications)
- 教育应用、语法纠错、文章打分 (Educational applications, GEC, essay scoring)
- 仇恨言论检测 (Hate speech detection)
- 多模态应用 (Multimodal applications)
- 代码生成和理解 (Code generation and understanding)
- 事实检测、谣言和错误信息检测 (Fact checking, rumour/misinformation detection)
- 医疗应用、诊断自然语言处理 (Healthcare applications, clinical NLP)
- 金融和商务自然语言处理 (Financial/business NLP)
- 法律自然语言处理 (Legal NLP)
- 数学自然语言处理 (Mathematical NLP)
- 安全和隐私 (Security/privacy)
- 历史自然语言处理 (Historical NLP)
- 知识图谱 (Knowledge graph)
(十七)音系学、形态学和词语分割 (Phonology, Morphology and Word Segmentation)
- 形态变化 (Morphological inflection)
- 范式归纳 (Paradigm induction)
- 形态学分割 (Morphological segementation)
- 子词表征 (Subword representations)
- 中文分割 (Chinese segmentation)
- 词性还原 (Lemmatization)
- 有限元形态学 (Finite-state morphology)
- 形态学分析 (Morphological analysis)
- 音系学 (Phonology)
- 字素音素转换 (Grapheme-to-phoneme conversion)
- 发音建模 (Pronunciation modeling)
(十八)问答 (Question Answering)
- 常识问答 (Commonsense QA)
- 阅读理解 (Reading comprehension)
- 逻辑推理 (Logic reasoning)
- 多模态问答 (Multimodal QA)
- 知识库问答 (Knowledge base QA)
- 语义分析 (Semantic parsing)
- 多跳问答 (Multihop QA)
- 生物医学问答 (Biomedical QA)
- 多语言问答 (Multilingual QA)
- 可解释性 (Interpretability)
- 泛化 (Generalization)
- 推理 (Reasoning)
- 对话问答 (Conversational QA)
- 少样本问答 (Few-shot QA)
- 数学问答 (Math QA)
- 表格问答 (Table QA)
- 开放域问答 (Open-domain QA)
- 问题生成 (Question generation)
(十九)语言资源及评价 (Resources and Evaluation)
- 语料库构建 (Corpus creation)
- 基线构建 (Benchmarking)
- 语言资源 (Language resources)
- 多语言语料库 (Multilingual corpora)
- 词表构建 (Lexicon creation)
- 语言资源的自动构建与评价 (Automatic creation and evaluation of language resources)
- 自然语言处理数据集 (NLP datasets)
- 数据集自动评价 (Automatic evaluation of datasets)
- 评价方法 (Evaluation methodologies)
- 低资源语言数据集 (Datasets for low resource languages)
- 测量指标 (Metrics)
- 复现性 (Reproducibility)
- 用于评价的统计检验 (Statistical testing for evaluation)
(二十)语义学:词汇层面 (Semantics: Lexical)
- 一词多义 (Polysemy)
- 词汇关系 (Lexical relationships)
- 文本蕴含 (Textual entailment)
- 语义合成性 (Compositionality)
- 多词表达 (Multi-word expressions)
- 同义转换 (Paraphrasing)
- 隐喻 (Metaphor)
- 词汇语义变迁 (Lexical semantic change)
- 词嵌入 (Word embeddings)
- 认知 (Cognition)
- 词汇资源 (Lexical resources)
- 情感分析 (Sentiment analysis)
- 多语性 (Multilinguality)
- 可解释性 (Interpretability)
- 探索性研究 (Probing)
(二十一)语义学:句级语义、文本推断和其他领域 (Semantics: Sentence-Level Semantics, Textual Inference and Other Areas)
- 同义句识别 (Paraphrase recognition)
- 文本蕴含 (Textual entailment)
- 自然语言推理 (Natural language inference)
- 逻辑推理 (Reasoning)
- 文本语义相似性 (Semantic textual similarity)
- 短语和句子嵌入 (Phrase/sentence embedding)
- 同义句生成 (Paraphrase generation)
- 文本简化 (Text simiplification)
- 词和短语对齐 (Word/phrase alignment)
(二十二)情感分析、文本风格分析和论点挖掘 (Sentiment Analysis, Stylistic Analysis and Argument Mining)
- 论点挖掘 (Argument mining)
- 观点检测 (Stance detection)
- 论点质量评价 (Argument quality assessment)
- 修辞和框架 (Rhetoric and framing)
- 论证方案和推理 (Argument schemes and reasoning)
- 论点生成 (Argument generation)
- 风格分析 (Style analysis)
- 风格生成 (Style generation)
- 应用 (Applications)
(二十三)语音和多模态 (Speech and Multimodality)
- 自动语音识别 (Automatic speech recognition)
- 口语语言理解 (Spoken language understanding)
- 口语翻译 (Spoken language translation)
- 口语语言基础 (Spoken language grounding)
- 语音和视觉 (Speech and vision)
- 口语查询问答 (QA via spoken queries)
- 口语对话 (Spoken dialog)
- 视频处理 (Video processing)
- 语音基础 (Speech technologies)
- 多模态 (Multimodality)
(二十四)文摘 (Summarization)
- 抽取文摘 (Extractive summarization)
- 摘要文摘 (Abstractive summarization)
- 多模态文摘 (Multimodal summarization)
- 多语言文摘 (Multilingual summarization)
- 对话文摘 (Conversational summarization)
- 面向查询的文摘 (Query-focused summarization)
- 多文档文摘 (Multi-document summarization)
- 长格式文摘 (Long-form summarization)
- 句子压缩 (Sentence compression)
- 少样本文摘 (Few-shot summarization)
- 结构 (Architectures)
- 评价 (Evaluation)
- 事实性 (Factuality)
(二十五)句法学:标注、组块分析和句法分析 (Syntax: Tagging, Chunking and Parsing)
- 组块分析、浅层分析 (Chunking, shallow-parsing)
- 词性标注 (Part-of-speech tagging)
- 依存句法分析 (Dependency parsing)
- 成分句法分析 (Constituency parsing)
- 深层句法分析 (Deep syntax parsing)
- 语义分析 (Semantic parsing)
- 句法语义接口 (Syntax-semantic inferface)
- 形态句法相关任务的标注和数据集 (Optimized annotations or data set for morpho-syntax related tasks) 句法分析算法 (Parsing algorithms)
- 语法和基于知识的方法 (Grammar and knowledge-based approach)
- 多任务方法 (Multi-task approaches)
- 面向大型多语言的方法 (Massively multilingual oriented approaches)
- 低资源语言词性标注、句法分析和相关任务 (Low-resource languages pos-tagging, parsing and related tasks)
- 形态丰富语言的词性标注、句法分析和相关任务 (Morphologically-rich languages pos tagging, parsing and related tasks)
(二十六)主题领域:现实检测 (Theme Track: Reality Check)
- 因为错误的原因而正确 (Right for the wrong reasons)
- 实际运用中的教训 (Lessons from deployment)
- (非)泛化能力 (Non-)generalization
- (非)复现能力 (Non-)reproducibility)
- 评价 (Evaluation)
- 方法 (Methodology)
- 负面结果 (Negative results)
- 人工智能噱头和期待 (AI hype and expectations)
- 科学 vs 工程 (Science-vs-engineering)
- 其他领域的结合 (Lessons from other fields)