EMNLP 2017: Conference on Empirical Methods in Natural Language Processing — September 7–11, 2017 — Copenhagen, Denmark.


SIGDAT, the Association for Computational Linguistics special interest group on linguistic data and corpus-based approaches to NLP, invites you to participate in EMNLP 2017.


Two days of tutorials are scheduled before the main conference, on September 7 and 8. The tutorials are organised in morning and afternoon slots of three hours each.

Sep 7, morning
Acquisition, Representation and Usage of Conceptual Hierarchies

The tutorial examines the theoretical foundations of subsumption, and its practical embodiment through IsA relations compiled manually or extracted automatically. It addresses IsA relations from their formal definition; through practical choices made in their representation within the larger and more widely-used of the available knowledge resources; to their automatic acquisition from document repositories, as opposed to their manual compilation by human contributors; to their impact in text analysis and information retrieval.

Presented by: Marius Pasca

More details at the tutorial page.

Sep 7, morning
Computational Sarcasm

Sarcasm is a form of verbal irony that is intended to express contempt or ridicule. Motivated by challenges posed by sarcastic text to sentiment analysis, computational approaches to sarcasm have witnessed a growing interest at NLP forums in the past decade. Computational sarcasm refers to automatic approaches pertaining to sarcasm. The tutorial will provide a bird’s-eye view of the research in computational sarcasm for text, while focusing on significant milestones.

Presented by: Pushpak Bhattacharyya, Aditya Joshi

More details at the tutorial page.

Sep 7, afternoon
Graph-based Text Representations: Boosting Text Mining, NLP and Information Retrieval with Graphs

The goal of this tutorial is to offer a comprehensive presentation of recent methods that rely on graph-based text representations to deal with various tasks in NLP and IR. We will describe basic as well as novel graph theoretic concepts and we will examine how they can be applied in a wide range of text-related application domains, including IR, text categorization and keyword extraction.

Presented by: Fragkiskos Malliaros, Michalis Vazirgiannis

More details at the tutorial page.

Sep 7, afternoon
Semantic Role Labeling

This is the 3rd tutorial on semantic role labeling, following the first well-attended tutorials at NAACL in 2013 and ACL in 2009. We will introduce the task of semantic role labeling (SRL) and discuss recent research directions related to the task. The audience of this tutorial will learn about the linguistic background and motivation for semantic roles, and also about a range of computational models for this task, from early approaches to the current state-of-the-art. We will further discuss recently proposed variations of the traditional SRL task, including topics such as AMR parsing, semantic proto-role labeling and implicit argument linking.

Presented by: Diego Marcheggiani, Michael Roth, Ivan Titov, Benjamin Van Durme

More details at the tutorial page.

Sep 8, afternoon
Memory Augmented Neural Networks for Natural Language Processing

Memory Augmented Neural Networks (MANNs) can store and read information from an external memory. While the traditional machine learning algorithms (including neural networks) accepts an input and process it to perform a prediction, MANNs can use the explicit memory to store necessary information during the execution of the task and retrieve information from the memory when needed. This can be helpful for complex tasks like reasoning, planning, question answering, and dialogue systems. The aim of this tutorial is to introduce this paradigm of memory augmented neural networks to the NLP community since this has large scope in several complex NLP tasks like question answering, reading comprehension, dialogue systems, and summarization.

Presented by: Caglar Gulcehre, Sarath Chandar

More details at the tutorial page.

Sep 8, afternoon
A Unified Framework for Structured Prediction: From Theory to Practice

Structured prediction is one of the most important topics in various fields, including machine learning, computer vision, natural language processing and bioinformatics. In this tutorial, we present a novel framework that unifies various structured prediction models.

Presented by: Wei Lu

More details at the tutorial page.

Sep 8, afternoon
Cross-Lingual Word Representations: Induction and Evaluation

Cross-lingual modeling is an integral part of machine translation and multilingual search, but also enables better modeling of low-resource languages through cross-lingual transfer. In this tutorial, we will focus on: (i) how to induce cross-lingual word representations (covering both bilingual and multilingual ones) from various data types and resources (e.g., parallel data, comparable data, non-aligned monolingual data in different languages, dictionaries and theasuri, or, even, images and large-scale usage statistics); (ii) how to evaluate such representations, intrinsically and extrinsically.

Presented by: Manaal Faruqui, Anders Søgaard, Ivan Vulić

More details at the tutorial page.