Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
Latent structure models are a powerful tool for modeling compositional data, discovering linguistic structure, and building NLP pipelines. They are appealing for two main reasons: they allow incorporating structural bias during training, leading to more accurate models; and they allow discovering hidden linguistic structure, which provides better interpretability. This tutorial will cover recent advances in discrete latent structure models. We discuss their motivation, potential, and limitations, then explore in detail three strategies for designing such models: gradient approximation, reinforcement learning, and end-to-end differentiable methods. We highlight connections among all these methods, enumerating their strengths and weaknesses. The models we present and analyze have been applied to a wide variety of NLP tasks, including sentiment analysis, natural language inference, language modeling, machine translation, and semantic parsing. Examples and evaluation will be covered throughout. After attending the tutorial, a practitioner will be better informed about which method is best suited for their problem.
This tutorial is on representing and processing sentence meaning in the form of labeled directed graphs. The tutorial will (a) briefly review relevant background in formal and linguistic semantics; (b) semi-formally define a unified abstract view on different flavors of semantic graphs and associated terminology; (c) survey common frameworks for graph-based meaning representation and available graph banks; and (d) offer a technical overview of a representative selection of different parsing approaches.
Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many downstream applications. This involves identifying the topic structure, the coherence structure, the coreference structure, and the conversation structure for conversational discourse. Taken together, these structures can inform text summarization, machine translation, essay scoring, sentiment analysis, information extraction, question answering, and thread recovery. The tutorial starts with an overview of basic concepts in discourse analysis – monologue vs. conversation, synchronous vs. asynchronous conversation, and key linguistic structures in discourse analysis. We also give an overview of linguistic structures and corresponding discourse analysis tasks that discourse researchers are generally interested in, as well as key applications on which these discourse structures have an impact.
In the last twenty years, political scientists started adopting and developing natural language processing (NLP) methods more actively in order to exploit text as an additional source of data in their analyses. Over the last decade the usage of computational methods for analysis of political texts has drastically expanded in scope, allowing for a sustained growth of the text-as-data community in political science. In political science, NLP methods have been extensively used for a number of analyses types and tasks, including inferring policy position of actors from textual evidence, detecting topics in political texts, and analyzing stylistic aspects of political texts (e.g., assessing the role of language ambiguity in framing the political agenda). Just like in numerous other domains, much of the work on computational analysis of political texts has been enabled and facilitated by the development of resources such as, the topically coded electoral programmes (e.g., the Manifesto Corpus) or topically coded legislative texts (e.g., the Comparative Agenda Project). Political scientists created resources and used available NLP methods to process textual data largely in isolation from the NLP community. At the same time, NLP researchers addressed closely related tasks such as election prediction, ideology classification, and stance detection. In other words, these two communities have been largely agnostic of one another, with NLP researchers mostly unaware of interesting applications in political science and political scientists not applying cutting-edge NLP methodology to their problems. The main goal of this tutorial is to systematize and analyze the body of research work on political texts from both communities. We aim to provide a gentle, all-round introduction to methods and tasks related to computational analysis of political texts. Our vision is to bring the two research communities closer to each other and contribute to faster and more significant developments in this interdisciplinary research area.
This tutorial examines the role of Wikipedia in tasks related to text analysis and retrieval. Text analysis tasks, which take advantage of Wikipedia, include coreference resolution, word sense and entity disambiguation and information extraction. In information retrieval, a better understanding of the structure and meaning of queries helps in matching queries against documents, clustering search results, answer and entity retrieval and retrieving knowledge panels for queries asking about popular entities.
This introductory tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, “deep learning” is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The “semantic structure” in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The “distribution function” in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network, long short-term memory, sequence-to-sequence model, variational auto-encoder, generative adversarial network, attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network and policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies and domain applications are presented to tackle different issues in deep Bayesian processing, learning and understanding. At last, we will point out a number of directions and outlooks for future studies.
In this tutorial, we provide a comprehensive survey of the exciting recent work on cutting-edge weakly-supervised and unsupervised cross-lingual word representations. After providing a brief history of supervised cross-lingual word representations, we focus on: 1) how to induce weakly-supervised and unsupervised cross-lingual word representations in truly resource-poor settings where bilingual supervision cannot be guaranteed; 2) critical examinations of different training conditions and requirements under which unsupervised algorithms can and cannot work effectively; 3) more robust methods for distant language pairs that can mitigate instability issues and low performance for distant language pairs; 4) how to comprehensively evaluate such representations; and 5) diverse applications that benefit from cross-lingual word representations (e.g., MT, dialogue, cross-lingual sequence labeling and structured prediction applications, cross-lingual IR).
This course aims to introduce students to an exciting and dynamic area that has witnessed remarkable growth over the past 36 months. Argument mining builds on opinion mining, sentiment analysis and related to tasks to automatically extract not just *what* people think, but *why* they hold the opinions they do. From being largely beyond the state of the art barely five years ago, there are now many hundreds of papers on the topic, millions of dollars of commercial and research investment, and the 6th ACL workshop on the topic will be in Florence in 2019. The tutors have delivered tutorials on argument mining at ACL 2016, at IJCAI 2016 and at ESSLLI 2017; for ACL 2019, we have developed a tutorial that provides a synthesis of the major advances in the area over the past three years.
In this tutorial, we wish to cover the foundational, methodological, and system development aspects of translating structured data (such as data in tabular form) and knowledge bases (such as knowledge graphs) into natural language. The attendees of the tutorial will be able to take away from this tutorial, (1) the basic ideas around how modern NLP and NLG techniques could be applied to describe and summarize textual data in format that is non-linguistic in nature or has some structure, and (2) a few interesting open-ended questions, which could lead to significant research contributions in future. The tutorial aims to convey challenges and nuances in structured data translation, data representation techniques, and domain adaptable solutions for translation of the data into natural language form. Various solutions, starting from traditional rule based/heuristic driven and modern data-driven and ultra-modern deep-neural style architectures will be discussed, followed by a brief discussion on evaluation and quality estimation. A significant portion of the tutorial will be dedicated towards unsupervised, scalable, and adaptable solutions, given that systems for such an important task will never naturally enjoy sustainable large scale domain independent labeled (parallel) data.