The following tutorials have been accepted for ACL-IJCNLP 2021 and will be held on Sunday, August 1st, 2021.
T1: Advances in Debating Technologies: Building AI That Can Debate Humans (3 Hours)
Organizers: Roy Bar-Haim , Liat Ein-Dor , Matan Orbach , Elad Venezian and Noam Slonim
The tutorial focuses on Debating Technologies, a sub-field of computational argumentation defined as “computational technologies developed directly to enhance, support, and engage with human debating” (Gurevych et al., 2016). A recent milestone in this field is Project Debater, which was revealed in 2019 as the first AI system that can debate human experts on complex topics. Project Debater is the third in the series of IBM Research AI’s grand challenges, following Deep Blue and Watson. It has been developed for over six years by a large team of NLP and ML researchers and engineers, and its live demonstration in February 2019 received massive media attention. This research effort has resulted in more than 50 scientific papers to date, and many datasets freely available for research purposes. We discuss the scientific challenges that arise when building such a system, including argument mining, argument quality assessment, stance classification, principled argument detection, narrative generation, and rebutting a human opponent. Many of the underlying capabilities of Project Debater will become freely available for academic research starting April 2021, and the tutorial will include a detailed explanation of how to use and leverage these tools.
A complementary goal of the tutorial is to provide a holistic view of a debating system. Such a view is largely missing in the academic literature, where each paper typically addresses a specific problem in isolation. We present a complete pipeline of a debating system, and discuss the information flow and the interaction between the various components. Finally, we discuss practical applications and future challenges of debating technologies.
T2: Event-Centric Natural Language Understanding (3.5 Hours)
Instructors: Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown and Dan Roth
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text. These include methods to extract the internal structures of an event regarding its protagonist(s), participant(s) and properties, as well as external structures concerning memberships, temporal and causal relations of multiple events. This tutorial will provide audience with a systematic introduction of (i) knowledge representations and acquisition of events, (ii) various methods for automated extraction, conceptualization, coreference resolution and prediction of events and their relations, (iii) induction of event processes and properties, and (iv) a wide range of NLU and commonsense understanding tasks that benefit from aforementioned techniques. We will conclude the tutorial by outlining emerging research problems in this area.
T3: Meta Learning and Its Applications to Natural Language Processing (3 Hours)
Instructors: Hung-yi Lee, Ngoc Thang Vu, Shang-Wen Li
Deep learning based natural language processing (NLP) has become the mainstream of research in recent years and significantly outperforms conventional methods. However, deep learning models are notorious for being data and computation hungry. These downsides limit such models’ application from deployment to different domains, languages, countries, or styles, since collecting in-genre data and model training from scratch are costly. The long-tail nature of human language makes challenges even more significant. Meta-learning, or ‘Learning to Learn’, aims to learn better learning algorithms, including better parameter initialization, optimization strategy, network architecture, distance metrics, and beyond. Meta-learning has been shown to allow faster fine tuning, converge to better performance, and achieve outstanding results for few-shot learning in many applications. Meta-learning is one of the most important new techniques in machine learning in recent years. There is a related tutorial in ICML 20191 and a related course at Stanford2, but most of the example applications given in these materials are about image processing. It is believed that meta learning has excellent potential to be applied in NLP, and some works have been proposed with notable achievements in several relevant problems, e.g., relation extraction, machine translation, and dialogue generation and state tracking. However, it does not catch the same level of attention as in the image processing community.
In the tutorial, we will first introduce Meta learning approaches and the theory behind them, and then review the works of applying this technology to NLP problems. This tutorial intends to facilitate researchers in the NLP community to understand this new technology better and promote more research studies using this new technology.
T4: Pre-training Methods for Neural Machine Translation (3 hours)
Instructors: Mingxuan Wang, Lei Li
This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation, including multilingual NMT and speech NMT. Firstly, we will briefly introduce the background of NMT, pre-training methodology, and point out the main challenges when applying pre-training for NMT. Then we will focus on analyzing the role of pre-training in enhancing the performance of NMT, how to design a better pretraining model for executing specific NMT tasks and how to better integrate the pre-trained model into NMT system. In each part, we will provide examples, discuss training techniques and analyze what is transferred when applying pre-training.
T5: Prosody: Models, Methods, and Applications (3 hours)
Instructors: Nigel Ward, Gina-Anne Levow
Prosody is fundamental to human interaction, enabling people to show interest, establish rapport, efficiently convey nuances of attitude or intent, and so on. Over the past ten years the ability to effectively model prosody has rapidly advanced. This tutorial will start with the acoustic and perceptual foundations and the basics of prosodic feature computation and normalization. It will then discuss prosody’s three realms of function: phonological and structural, paralinguistic, and pragmatic, with short, non-computational pair work exercises to illustrate. The tutorial will survey some classic and recent representations, models, algorithms, tools and resources. Finally we will overview the state of the art in the major applications areas and discuss both short-term and long-term challenges.
T6: Recognizing Multimodal Entailment (3 hours)
Instructors: Cesar Ilharco, Vaiva Imbrasaite, Ricardo Marino, Jannis Bulian, Chen Sun, Afsaneh Shirazi, Gabriel Ilharco, Georg Osang, Lucas Smaira and Cordelia Schmid
New social technologies and widespread access to the internet have allowed for new forms of content creation, connectivity and information sharing. With vast unstructured data and limited labels, organizing and reconciling information from different sources and modalities with bounded supervision is one of the current challenges in machine learning. This cutting-edge tutorial focuses on models and approaches for recognizing multimodal entailment, and uses as case study two real-world multi-domain datasets which prompt for understanding the fine-grained visual and linguistic semantics.