Area Keywords at ARR

Choosing the right track may be tricky for the authors, and to aid them, in this page we provide the keywords associated with ARR tracks.

This list was initially based on ACL’23 list. In April 2024 we added Language Modeling and Human-Centered NLP tracks, in May 2025 the keywords were updated based on input from EMNLP’25 PCs. Starting from March 2026 the following tracks will be used, based on input from ACL’26 and EMNLP’26 program chairs. This list is overall expected to change over time. It is not meant to be exhaustive, but it should still give some idea of what is the focus of different areas. In the future, they can be used to analyze the submission volume for different subtopics (so that we could tell which areas are growing and may need their own areas), and for paper-reviewer matching.

How does one choose the right area, given that there are so many overlaps? Here are a few examples:

Should a question answering resource paper go to the resource area or the question answering area? Generally, if there is a task-specific area, it takes both modeling and resource papers, but if your paper is very centered on data collection methodology, you might still want to consider the resource area.
What about a paper on multilingual generation? It could go for the generation area if the focus is on generation strategies, or to the multilingualism area - if the focus is on those languages.
What about work in low-resource settings - is it efficiency or multilingualism? If the focus is on the training, and the low-resource setting is simulated from a well-resourced language, then we’d suggest the efficiency area. If you are contributing resources, analysis, or new solutions for languages that haven’t had that kind of thing before, consider the multilingualism area.

The current ARR areas are as follows.

Clinical and Biomedical Applications: biomedical knowledge extraction, discovery, and text mining; biomedical question answering; clinical and biomedical language models; clinical dialogue systems; clinical and biomedical text summarisation; NLP tools for biomedical knowledge graphs, clinical decision support, clinical coding, drug adverse event discovery, mental health; phrase mining and disease association; regulatory and ethical considerations; other clinical and biomedical applications which explicitly involve natural language as a central element in the paper contribution.
Computational Social Science and Cultural Analytics: human behavior analysis; stance detection; frame detection and analysis; hate-speech detection; misinformation detection and analysis; psycho-demographic trait prediction; emotion detection and analysis; emoji prediction and analysis; language/cultural bias analysis; sociolinguistics; NLP tools for social analysis; quantitative analyses of news and/or social media;
Dialogue and Interactive Systems: spoken dialogue systems; evaluation and metrics; task-oriented; bias/toxicity; factuality; retrieval; knowledge augmented; commonsense reasoning; interactive storytelling; embodied agents; applications; multi-modal dialogue systems; grounded dialog; multilingual / low resource; dialogue state tracking; conversational modeling;
Discourse and Pragmatics: anaphora resolution; coreference resolution; bridging resolution; coherence; cohesion; discourse relations; discourse parsing; dialogue; conversation; discourse and multilinguality; argument mining; communication; discourse-level inference; inter-sentential reasoning; pragmatic inference and reasoning.
Efficient Methods for NLP: quantization; pruning; distillation; parameter-efficient-training; data-efficient training; data augmentation; LLM efficiency; NLP in resource-constrained settings;
Ethics, Bias, and Fairness: data ethics; model alignment; model bias/fairness evaluation; model bias/unfairness mitigation; ethical considerations in NLP applications; transparency; policy and governance; reflections and critiques;
Generation: human evaluation; automatic evaluation; multilingualism; efficient models; few-shot generation; analysis; domain adaptation; data-to-text generation; text-to-text generation; inference methods; model architectures; retrieval-augmented generation; interactive and collaborative generation;
Human-Centered NLP and Human-AI Interaction: human-AI interaction/cooperation; human-in-the-loop; human-centered evaluation; user-centered design; value-centered design; human factors in NLP; participatory/community-based NLP; values and culture;
Information Extraction: named entity recognition and relation extraction; event extraction; open information extraction; knowledge base construction; entity linking/disambiguation; document-level extraction; multilingual extraction; zero/few-shot extraction;
Information Retrieval and Text Mining: passage retrieval; dense retrieval; document representation; hashing; re-ranking; pre-training; contrastive learning; retrieval for RAG;
Interpretability and Analysis of Models for NLP: adversarial attacks/examples/training; calibration/uncertainty; counterfactual/contrastive explanations; data influence; data shortcuts/artifacts; explanation faithfulness; feature attribution; free-text/natural language explanations; hardness of samples; hierarchical & concept explanations; human-subject application-grounded evaluations; knowledge tracing/discovering/inducing; model editing; probing; robustness; topic modeling;
Language Modeling: adversarial attacks; chain-of-thought; fine-tuning; continual learning; hallucinations; neurosymbolic approaches; pre-training; privacy; prompting; safety; scaling; security; sparse models; red teaming; retrieval-augmented language models; robustness; transfer; watermarking;
LLM agents: tool use; function calling; multi-modal agents; multi-agent systems; planning in agents; agent communication; agent coordination and negotiation; environment interaction; agent memory; reinforcement learning in agents; LLM-based controllers; agent evaluation; grounded agents; embodied agents;
Linguistic Theories, Cognitive Modeling, and Psycholinguistics: linguistic theories; cognitive modeling; computational psycholinguistics;
Machine Learning for NLP: graph-based methods; knowledge-augmented methods; multi-task learning; self-supervised learning; contrastive learning; generative models; data augmentation; word embeddings; structured prediction; transfer learning / domain adaptation; representation learning; generalization; few-shot learning; reinforcement learning; optimization methods; continual learning; adversarial training; meta learning; causality; graphical models; human-in-the-loop / active learning;
Machine Translation: automatic evaluation; biases; domain adaptation; efficient inference for MT; efficient MT training; few-shot/zero-shot MT; human evaluation; interactive MT; MT deployment and maintenance; MT theory; modeling; multilingual MT; multimodality; online adaptation for MT; parallel decoding/non-autoregressive MT; pre-training for MT; scaling; speech translation; switch-code translation; vocabulary learning;
Multilingualism and Cross-Lingual NLP: code-switching; mixed language; multilingualism; language contact; language change; linguistic variation; cross-lingual transfer; multilingual representations; multilingual pre-training; multilingual benchmarks; multilingual evaluation; dialects and language varieties; less-resourced languages; endangered languages; indigenous languages; minoritized languages; language documentation; resources for less-resourced languages; software and tools;
Multimodality and Language Grounding to Vision, Robotics and Beyond: vision language navigation; cross-modal pretraining; image text matching; cross-modal content generation; vision question answering; cross-modal application; cross-modal information extraction; cross-modal machine translation; automatic speech recognition; spoken language understanding; spoken language translation; spoken language grounding; speech and vision; QA via spoken queries; spoken dialog; video processing; speech technologies; multimodality;
NLP and Code Models: language-to-code generation, code-to-language generation, other topics which explicitly involve natural language as a central element in the paper contribution.
NLP and Symbolic Reasoning: natural language AND symbolic reasoning topics (e.g. mathematical / symbolic /neurosymbolic / logical reasoning, symbolic AI, logical neural networks, differentiable inductive logic programming, neural theorem provers, knowledge graph embeddings, Markov logics), as long as there is a clear contribution to computational processing of natural language;
NLP Applications: educational applications, essay scoring; financial/business NLP; grammatical error correction, hate speech detection; historical NLP; NLP for knowledge graphs; legal NLP; multimodal applications; code generation and understanding; fact checking, rumor/misinformation detection; security/privacy; NLP for social good;
Phonology, Morphology, and Word Segmentation: morphological inflection; paradigm induction; morphological segmentation; subword representations; chinese segmentation; lemmatization; finite-state morphology; morphological analysis; phonology; grapheme-to-phoneme conversion; pronunciation modeling;
Question Answering: commonsense QA; reading comprehension; logical reasoning; multimodal QA; knowledge base QA; semantic parsing; multihop QA; biomedical QA; multilingual QA; interpretability; generalization; reasoning; conversational QA; few-shot QA; math QA; table QA; open-domain QA; question generation; RAG for QA;
Resources and Evaluation: corpus creation; benchmarking; language resources; multilingual corpora; lexicon creation; automatic creation and evaluation of language resources; NLP datasets; automatic evaluation of datasets; evaluation methodologies; evaluation; datasets for low resource languages; metrics; reproducibility; statistical testing for evaluation;
Semantics: Lexical and Sentence-Level: polysemy; lexical relationships; textual entailment; compositionality; multi-word expressions; metaphor; lexical semantic change; word embeddings; lexical resources; paraphrase recognition; textual entailment; natural language inference; semantic textual similarity; phrase/sentence embedding; paraphrasing; text simplification; word/phrase alignment;
Sentiment Analysis, Stylistic Analysis, and Argument Mining: applications; argument generation; argument mining; argument schemes and reasoning; argument quality assessment; computational affective science; stance detection; style analysis; style adaptation; rhetoric and framing;
Speech Recognition, Text-to-Speech and Spoken Language Understanding: automatic speech recognition; speech technologies; spoken dialog; spoken language grounding; speech and vision; spoken language translation; spoken language understanding; QA via spoken queries;
Summarization: extractive summarisation; abstractive summarisation; multimodal summarization; multilingual summarisation; conversational summarization; query-focused summarization; multi-document summarization; long-form summarization; sentence compression; few-shot summarisation; architectures; evaluation; factuality;
Syntax: Tagging, Chunking and Parsing: chunking, constituency parsing; deep syntax parsing; dependency parsing; grammar and knowledge-based approaches; hierarchical structure prediction; low-resources languages pos tagging, parsing and related tasks; massively multilingual oriented approaches; morphologically-rich languages pos tagging, parsing and related tasks; multi-task approaches (large definition); optimized annotations or data set for morpho-syntax related tasks; parsing algorithms (symbolic, theoretical results); part-of-speech tagging; semantic parsing; shallow-parsing; syntax-to-semantic interface;
Special Theme Track: this is conference-specific, it is usually described in the CFP for each conference.