Submissions Areas

● Dialogue and Interactive Systems: dialogue control models, context modeling for dialogue, corpora, tools and evaluation methods for developing dialogue systems, multimodal, embodied, and situated dialogue, social chatbots, open-domain dialogue systems, task-oriented dialog, dialog policy learning, state tracking, conversational understanding, response generation, pragmatic and/or semantic modelling for dialogue

● Discourse and Pragmatics: coreference/anaphora resolution, mention detection, discourse parsing, metonymy recognition, discourse of argumentation, discourse in machine translation, text quality, behavioural insights from text, meaning beyond the sentence

● Document Analysis: language modeling and topic modeling, document classification and clustering, text mining and applications, recommender systems; information retrieval: query understanding and analysis, retrieval and ranking models, cross-lingual retrieval.

● Generation: sentence generation, surface realization, referring expression generation, content selection, data-to-text, concept-to-text, story generation, storytelling, evaluation and resources

● Information Extraction and Text Mining: named entity recognition, named entity resolution, relation extraction, event extraction, open information extraction, knowledge base population, knowledge graph acquisition and alignment, entity linking, entity disambiguation, temporal/spatial relation recognition, keyphrase extraction, text mining for formal or informal text (e.g. news, scientific text or social media text), text mining for specific domains (e.g. biomedical, clinical, chemistry, finance), cross-lingual information extraction

● Linguistic Theories, Cognitive Modeling, and Psycholinguistics: formal theories of phonology/lexicon/syntax/semantics/pragmatics, computational models for linguistics, linguistic typology, experimental methods, language processing, neurolinguistics, language acquisition and loss, mathematical linguistics

● Machine Learning: theoretical/empirical contributions to machine learning models for NLP/CL, Bayesian models, neural network models, online learning, reinforcement learning, transfer learning, embedding methods, relational learning, symbolic learning methods

● Machine Translation: neural machine translation, machine translation models, machine translation evaluation, machine translation applications, word/phrase alignment models, transliteration, speech translation, domain adaptation for machine translation, low-resource machine translation, interactive and computer-assisted machine translation, tools for translators, decipherment, automatic post-editing, multimodal translation

● Multidisciplinary and Area Chair COI: any NLP/CL related topics that are not categorized into other areas, papers with area chair COI

● Multilinguality: multilingual dictionaries/corpora, analysis of translated texts, multilingual applications

● Phonology, Morphology and Word Segmentation: morphological analysis, word segmentation models, theoretical models for phonology/morphology/word formation, multilingual morphology

● Question Answering: factoid/non-factoid question answering, open-domain question answering, question interpretation, answer type classification, answer extraction, answer sentence selection, reading comprehension, community QA, cross-lingual question answering

● Resources and Evaluation: development of linguistic resources such as corpora/treebanks/lexica/ontologies, corpus annotation methods, evaluation methodologies for NLP tasks

● Sentence-level Semantics: semantic parsing, semantic role labelling, natural language interfaces for databases, parsing into logical forms, AMR parsing, sentence/document embeddings, program synthesis
● Sentiment Analysis and Argument Mining: sentiment analysis, opinion mining, opinion representation, subjectivity analysis, argument analysis, argument evaluation, argumentation in discourse

● Social Media: NLP in social media, NLP for noisy/informal text, event detection and social sensing, computational social science, trust evaluation and fake news, computational sociolinguistics, language and demographics, multilingual exchanges and code switching, sarcasm detection

● Summarization: extractive summarization, abstractive summarization, evaluation methods for summarization, multi-document summarization, sentence simplification

● Tagging, Chunking, Syntax and Parsing: part-of-speech tagging, shallow parsing, phrase chunking, phrase structure parsing, dependency parsing, deep parsing, semantic dependency parsing, grammar induction, formal grammar, string/tree/graph automata and transducers

● Textual Inference and Other Areas of Semantics: recognizing textual entailment, semantic textual similarity, common-sense reasoning, story understanding, inference of implicit information, text-level semantic parsing/role labeling, metaphor analysis/generation

● Vision, Robotics, Multimodal, Grounding and Speech: image/video captioning, multimodal QA, NLP for robotics, speech recognition, speech synthesis, language modeling for spoken language, instruction execution, language grounding, language and vision

● Word-level Semantics: word sense disambiguation/induction, word/phrase embeddings, distributional similarity, lexical/phrasal entailment, paraphrasing, lexical knowledge acquisition, sense embeddings, sense tagging, lexical semantics, multiword expressions, selectional preferences

● Applications: papers primarily about applications using NLP rather than advances in one of the above areas