You can also view the schedule by going to the "day" view on the Schedule page.
AmericasNLP aims to (a) encourage research on NLP, computational linguistics, corpus linguistics, and speech around the globe to work on native American languages; (b) )connect researchers and professionals from underrepresented communities and native speakers of endangered languages with the machine learning and natural language processing communities; and (c) )promote research on both neural and non-neural machine learning approaches suitable for low-resource languages.
The BEA Workshop is a leading venue for NLP innovation in the context of educational applications. It is one of the largest one-day workshops in the ACL community with over 100 registered attendees in the past several years. The growing interest in educational applications and a diverse community of researchers involved resulted in the creation of the Special Interest Group in Educational Applications (SIGEDU) in 2017, which currently has over 300 members.
The BioNLP workshop associated with the ACL SIGBIOMED special interest group has established itself as the primary venue for presenting foundational research in language processing for the biological and medical domains. The workshop is running every year since 2002 and continues getting stronger. BioNLP welcomes and encourages work on languages other than English, and inclusion and diversity. BioNLP truly encompasses the breadth of the domain and brings together researchers in bio- and clinical NLP from all over the world. The workshop will continue presenting work on a broad and interesting range of topics in NLP. The interest to biomedical language has broadened significantly due to the COVID-19 pandemic and continues to grow: as access to information becomes easier and more people generate and access health-related text, it becomes clearer that only language technologies can enable and support adequate use of the biomedical text.
Most work on NLP focuses on language in its canonical written form. This has often led researchers to ignore the differences between written and spoken language or, worse, to conflate the two. Instances of conflation are statements like “Chinese is a logographic language" or “Persian is a right-to-left language", variants of which can be found frequently in the ACL anthology. These statements confuse properties of the language with properties of its writing system. Ignoring differences between written and spoken language leads, among other things, to conflating different words that are spelled the same (e.g., English bass), or treating as different, words that have multiple spellings. \\newline text enFurthermore, methods for dealing with written language issues (e.g., various kinds of normalization or conversion) or for recognizing text input (e.g. OCR \& handwriting recognition or text entry methods) are often regarded as precursors to NLP rather than as fundamental parts of the enterprise, despite the fact that most NLP methods rely centrally on representations derived from text rather than (spoken) language. This general lack of consideration of writing has led to much of the research on such topics to largely appear outside of ACL venues, in conferences or journals of neighboring fields such as speech technology (e.g., text normalization) or human-computer interaction (e.g., text entry). \\newline We will invite submissions on the relationship between written and spoken language, the properties of written language, the ways in which writing systems encode language, and applications specifically focused on characteristics of writing systems.
The last ten years have seen a dramatic improvement in the ability of NLP systems to understand and produce words and sentences. This development has created a renewed interest in discourse phenomena as researchers move towards the processing of long-form text and conversations. There is a surge of activity in discourse parsing, coherence models, text summarization, corpora for discourse level reading comprehension, and discourse related/aided representation learning, to name a few, but the problems in computational approaches to discourse are still substantial. At this juncture, we have organized three Workshops on Computational Approaches to Discourse (CODI) at EMNLP 2020, EMNLP 2021 and COLING 2022 to bring together discourse experts and upcoming researchers. These workshops have catalyzed work to improve the speed and knowledge needed to solve such problems and have served as a forum for the discussion of suitable datasets and reliable evaluation methods.
Clinical text is growing rapidly as electronic health records become pervasive. Much of the information recorded in a clinical encounter is located exclusively in provider narrative notes, which makes them indispensable for supplementing structured clinical data in order to better understand patient state and care provided. The methods and tools developed for the clinical domain have historically lagged behind the scientific advances in the general-domain NLP. Despite the substantial recent strides in clinical NLP, a substantial gap remains. The goal of this workshop is to address this gap by establishing a regular event in CL conferences that brings together researchers interested in developing state-of-the-art methods for the clinical domain. The focus is on improving NLP technology to enable clinical applications, and specifically, information extraction and modeling of narrative provider notes from electronic health records, patient encounter transcripts, and other clinical narratives.
The DialDoc workshop focuses on Document-Grounded Dialogue and Conversational Question Answering. Given the vast amount of content created every day in various mediums, it is a meaningful yet challenging task not only to make such content accessible to end users via various conversational interfaces, but also to make sure the responses provided by the models are grounded and faithful with respect to the knowledge sources.
The International Conference on Spoken Language Translation (IWSLT) is an annual scientific conference, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented.
Linguistic annotation of natural language corpora is the backbone of supervised methods of statistical natural language processing. The Linguistic Annotation Workshop (LAW) is the annual workshop of the ACL Special Interest Group on Annotation (SIGANN), and it provides a forum for the presentation and discussion of innovative research on all aspects of linguistic annotation, including the creation and evaluation of annotation schemes, methods for automatic and manual annotation, use and evaluation of annotation software and frameworks, representation of linguistic data and annotations, semi-supervised “human in the loop” methods of annotation, crowd-sourcing approaches, and more. As in the past, the LAW will provide a forum for annotation researchers to work towards standardization, best practices, and interoperability of annotation information and software.
Matching Entities from structured and unstructured sources is an important task in many domains and applications such as HR and E-commerce. For example, in HR platforms/services, it is important to match resumes to job descriptions and job seekers to companies. Similarly in web platforms/services, it is important to match customers to businesses such as hotels and restaurant, among others. In such domains, it is also relevant to match “textual customer reviews” to customers queries, and sentences (or phrases) as answers to customer questions. Recent advances in Natural Language Processing, Natural Language Understanding, Conversational AI, Language Generation, Machine Learning, Deep Learning, Data Management, Information Extraction, Knowledge Bases/Graphs, (MultiSingle Hop/Commonsense) Inference/Reasoning, Recommendation Systems, and others, have demonstrated promising results in different Matching tasks related (but not limited) to the previously mentioned domains. We believe that there is tremendous opportunity to further exploit and explore the use of advanced NLP (and language related) techniques applied to Matching tasks. Therefore, the goal of this workshop is to bring together the research communities (from academia and industry) of these related areas, that are interested in the development and the application of novel natural-language-based approaches/models/systems to address challenges around different Matching tasks.
Over the past decades, mathematicians, linguists, and computer scientists have dedicated their efforts towards empowering human-machine communication in natural language. While in recent years the emergence of virtual personal assistants such as Siri, Alexa, Google Assistant, Cortana, and ChatGPT has pushed the field forward, they may still have numerous challenges. \newline Following the success of the 4th NLP for Conversational AI workshop at ACL, The 5th NLP4ConvAI will be a one-day workshop, co-located with ACL 2023 in Toronto, Canada. The goal of this workshop is to bring together researchers and practitioners to discuss impactful research problems in this area, share findings from real-world applications, and generate ideas for future research directions. \newline The workshop will include keynotes, posters, panel sessions, and a shared task. In keynote talks, senior technical leaders from industry and academia will share insights on the latest developments in the field. We would like to encourage researchers and students to share their prospects and latest discoveries. There will also be a panel discussion with noted conversational AI leaders focused on the state of the field, future directions, and open problems across academia and industry.
With recent scaling of large pre-trained Transformer language models (LLMs), the scope of feasible NLP tasks has broadened. Significant recent work has focused on tasks that require some kind of natural language reasoning. A trajectory in question answering has led us from extraction-oriented datasets like SQuAD to “multi-hop” reasoning datasets like HotpotQA and StrategyQA. Although LLMs have shown remarkable performance on most NLP tasks, it is often unclear why their answers follow from what they know. To address this gap, a new class of explanation techniques has emerged which play an integral part in structuring the reasoning necessary to solve these datasets. For example, the chain-of-thought paradigm leverages explanations as vehicles for LLMs to mimic human reasoning processes. Entailment trees offer a way to ground multi-step reasoning in a collection of verifiable steps. Frameworks like SayCan bridge high-level planning in language and with low-level action trajectories. As a result, we see a confluence of methods blending explainable machine learning/NLP, classical AI (especially theorem proving), and cognitive science (how do humans structure explanations?). This workshop aims to bring together a diverse set of perspectives from these different traditions and attempt to establish common ground for how these various kinds of explanation structures can tackle a broad class of reasoning problems in natural language and beyond.
This is the 5th iteration of the Narrative Understanding Workshop, which brings together an interdisciplinary group of researchers from AI, ML, NLP, Computer Vision and other related fields, as well as scholars from the humanities to discuss methods to improve automatic narrative understanding capabilities. The workshop will consist of talks from invited speakers, a panel of researchers and writers, and talks and posters from accepted papers.
The 8th Workshop on Representation Learning for NLP aims to continue the success of the Repl4NLP workshop series, with the 1st Workshop on Representation Learning for NLP having received about 50 submissions and over 250 attendees - the second most attended collocated event at ACL'16 after WMT. The workshop was introduced as a synthesis of several years of independent *CL workshops focusing on vector space models of meaning, compositionality, and the application of deep neural networks and spectral methods to NLP. It provides a forum for discussing recent advances on these topics, as well as future research directions in linguistically motivated vector-based models in NLP. The workshop will take place in a hybrid setting, and, as in previous years, feature interdisciplinary keynotes, paper presentations, posters, as well as a panel discussion.
Social influence is the change in an individual's thoughts, feelings, attitudes, or behaviors that results from interaction with another individual or a group. For example, a buyer uses social influence skills to engage in trade-offs and build rapport when bargaining with a seller. A therapist uses social influence skills like persuasion to motivate a patient towards physical exercise. Social influence is a core function of human communication, and such scenarios are ubiquitous in everyday life, from negotiations to argumentation to behavioral interventions. Consequently, realistic human-machine conversations must reflect these social influence dynamics, making it essential to systematically model and understand them in dialogue research. This requires perspectives not only from NLP and AI research but also from game theory, emotion, communication, and psychology. \\newline We are excited to host the First Workshop on Social Influence in Conversations (SICon 2023). SICon 2023 will be a one-day hybrid event, co-located with ACL 2023. It would be the first venue that uniquely fosters a dedicated discussion on social influence within NLP while involving researchers from other disciplines such as affective computing and the social sciences. SICon 2023 features keynote talks, panel discussions, poster sessions, and lightning talks for accepted papers. We hope to bring together researchers and practitioners from a wide variety of disciplines to discuss important problems related to social influence, as well as share findings and recent advances. We encourage researchers of all stages and backgrounds to share their exciting work!
SIGMORPHON aims to bring together researchers interested in applying computational techniques to problems in morphology, phonology, and phonetics. Work that addresses orthographic issues is also welcome. Papers will be on substantial, original, and unpublished research on these topics, potentially including strong work in progress.
The 17th edition of SemEval features 12 TASKS on a range of topics, including tasks on idiomaticy detection and embedding, sarcasm detection, multilingual news similarity, and linking mathematical symbols to their descriptions. Several tasks are multilingual, and others ask for multimodal approaches.
The Natural Language Processing (NLP) community has, in recent years, demonstrated a notable focus on improving higher scores on standard benchmarks and taking the lead on community-wide leaderboards (e.g., GLUE, SentEval). While this aspiration has led to improvements in benchmark performance of (predominantly neural) models, it has also came at a cost, i.e., increased model complexity and the ever-growing amount of computational resources required for training and using the current state-of-the-art models. Moreover, the recent research efforts have, for the most part, failed to identify sources of empirical gains in models, often failing to empirically justify the model complexity beyond benchmark performance. \newline Because of these easily observable trends, we have proposed the SustaiNLP workshop with the goal of promoting more sustainable NLP research and practices, with two main objectives: (1) encouraging development of more efficient NLP models; and (2) providing simpler architectures and empirical justification of model complexity. For both aspects, we will encourage submissions from all topical areas of NLP.
Recent advances in Natural Language Processing, and the emergence of pretrained Large Language Models (LLM) specifically, have made NLP systems omnipresent in various aspects of our everyday life. In addition to traditional examples such as personal voice assistants, recommender systems, etc, more recent developments include content-generation models such as ChatGPT, text-to-image models (Dall-E), and so on. While these emergent technologies have an unquestionable potential to power various innovative NLP and AI applications, they also pose a number of challenges in terms of their safe and ethical use. To address such challenges, NLP researchers have formulated various objectives, e.g., intended to make models more fair, safe, and privacy-preserving. However, these objectives are often considered separately, which is a major limitation since it is often important to understand the interplay and/or tension between them. For instance, meeting a fairness objective might require access to users’ demographic information, which creates tension with privacy objectives. The goal of this workshop is to move toward a more comprehensive notion of Trustworthy NLP, by bringing together researchers working on those distinct yet related topics, as well as their intersection.
Subjectivity and Sentiment Analysis has become a highly developed research area, ranging from binary classification of reviews to the detection of complex emotion structures between entities found in text. This field has expanded both on a practical level, finding numerous successful applications in business, as well as on a theoretical level, allowing researchers to explore more complex research questions related to affective computing. Its continuing importance is also shown by the interest it generates in other disciplines such as Economics, Sociology, Psychology, Marketing, Crisis Management \& Digital Humanities. \\newline The aim of WASSA 2023 is to bring together researchers working on Subjectivity, Sentiment Analysis, Emotion Detection and Classification and their applications to other NLP or real-world tasks (e.g. public health messaging, fake news, media impact analysis, social media mining, computational literary studies) and researchers working on interdisciplinary aspects of affect computation from text.
The goal of The Workshop on Online Abuse and Harms (WOAH) is to advance research that develops, interrogates and applies computational methods for detecting, classifying and modelling online abuse.