Tutorials
DeCour: a NLP experience of Deception Detection
Tommaso Fornaciari
In the last 10-15 years, NLP techniques have proven effective in a number of forensic applications, such as author profiling and deception detection. The tutorial will show the experience of DeCour - DEception in COURts -, a corpus constituted by transcripts of hearings held in four Italian courts, which was employed for a typical task of text classification carried out thorough stylometric techniques, in order to distinguish false from truthful statements. The process will be examined with particular attention to the methods employed, from the data collection, through the preprocessing and the feature selection. In the end, the data analysis and the results will be discussed.

Biography
Tommaso Fornaciari is an Investigative Psychologist with the Italian National Police. Since obtaining his Ph.D. at the University of Trento, he has carried out research activities in forensic linguistics, publishing studies in which computational methods are employed with the aim of detecting deception in text and in transcripts of spoken language from criminal proceedings. He presently works at the Department of Public Security of the Italian Ministry of the Interior, engaged in research and technological innovation for public security. Prior to that, he worked at the Forensic Science Police Service, where he dealt with criminal analysis, mostly regarding violent murders.
The frustrating past, the exciting present and the bright future of (neural) machine translation
Jörg Tiedemann
Machine translation has a long and bumpy history. Automatic translation of human languages has been one of the goals since the beginning of the development of computers and digital technology. Starting initially with ideas of deciphering foreign languages, computational linguists quickly moved on with translation engines based on handwritten grammars. Exaggerated expectations lead to major disappointments mocking machine translation as an object of ridicule. The advent of statistical machine translation was received with skepticism until it lead to scientific and commercial success. Today, translation services are accepted and widely used gisting tools but progress does not stop here. The wave of deep learning and neural machine translation swipes over language technology and promises another jump forward. Constantly, new ideas and extensions are proposed making today's MT research an exciting enterprise with a bright future.

In this tutorial, I will present the basic concepts of neural MT as the new state-of-the-art in automatic translation. We will look at the common architecture of attention-based sequence-to-se quence models and include an overview of useful extensions and practical tricks. The tutorial will mention available tools and resources to make it easy to get started with hands-on experience on real-world data. We do not require any deep understanding of neural networks and machine learning as a background but focus on a gentle introduction of models and techniques.

Biography
Jörg Tiedemann works as a professor of language technology at the University of Helsinki since August 2015. He received his Ph.D. in computational linguistics from Uppsala University in 2003. His work is mainly focused on machine translation, question answering and data mining from multilingual resources. During his Ph.D. he spent a year at the University of Edinburgh and worked as a post-doctoral researcher at the University of Groningen. He maintains OPUS, the world's largest open collection of parallel corpora and more details about his research can be found at http://blogs.helsinki.fi/tiedeman/
Main program
Interpretable probabilistic embeddings: bridging the gap between topic models and neural networks
Anna Potapenko, Artem Popov and Konstantin Vorontsov
Deep Learning for Acoustic Addressee Detection in Spoken Dialogue Systems
Aleksei Pugachev, Oleg Akhtiamov, Alexey Karpov and Wolfgang Minker
Deep neural networks in Russian speech recognition
Nikita Markovnikov, Irina Kipyatkova, Alexey Karpov and Andrey Filchenkov
A close look at Russian morphological parsers: which one is the best?
Evgeny Kotelnikov, Elena Razova and Irina Fisheva
Semantic Feature Aggregation for Gender Identification in Russian Facebook
Polina Panicheva, Aliya Mirzagitova and Yanina Ledovaya
Boosting a rule-based chatbot using statistics and user satisfaction ratings
Octavia Efraim, Vladislav Maraev and João Rodrigues
Morpheme level word embedding
Ruslan Galinsky, Tatiana Kovalenko, Julia Yakovleva and Andrey Filchenkov
Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition
Anh Le, Mikhail Burtsev and Mikhail Arkhipov
Multi-objective topic modeling for exploratory search in tech news
Anastasia Yanina and Konstantin Vorontsov
A Deep Forest for Transductive Transfer Learning by Using a Consensus Measure
Lev Utkin and Mikhail Ryabinin
Using Linguistic Activity In Social Networks To Predict And Interpret Dark Psychological Traits
Arseny Moskvichev, Sergey Menshov, Marina Dubova and Andrey Filchenkov
Active Learning for Information Extraction from Scientific Papers
Roman Suvorov and Artem Shelmanov
Corpus of Syntactic Co-Occurrences: A Delayed Promise
Eduard Klyshinsky and Natalia Lukashevich
Employing Wikipedia data for coreference resolution in Russian
Ilya Azerkovich
Comparison of Vector Space Representations of Documents for the Task of Information Retrieval of Massive Open Online Courses
Julius Klenin, Dmitry Botov and Yuri Dmitrin
Combined feature representation for emotion classification from Russian speech
Oxana Verkholyak and Alexey Karpov
Building Wordnet for Russian Language from Ru.Wiktionary
Yuliya Chernobay
poster and demo session
POSTERS
Facial Expressions and Gestures of the Head: Semantic Transitions and Inversions.
Alexandra Evdokimova
Construction of a frame polarity lexicon for Russian
Viktoria Karnaukhova
Don't Count, Look! Finding Correlation Between Distributional Word Embeddings and Eye-Tracking Gaze Vectors
Amir Bakarov
Unlemmatization: Recovering Word Forms in Morphologically Rich Languages
Anton Alekseev
News Targeting for Corporate Users: Solving the Cold Start Problem with Word Embeddings
Olga Kozlova, Maria Komissarova, Anastasia Gaevskaya
Minstrel: Emotional Import from Music and Stories
Vladislav Maraev, Ye Tian, Chiara Mazzocconi, Ilya Utekhin, Jonathan Ginzburg
Vector Space Modeling of Music Tracks
Yuriy Khudyakov
Conditional Generators of Words Definitions
Artyom Gadetsky, Ilia Yakubovskiy, Dmitry Vetrov
KartaSlov.ru — Rethinking Dictionaries in Mobile Era
Denis Kulagin
Using the Power of Crowd to Mine Linguistic Data
Denis Kulagin
DEMOS
Facticity in Semantic Concept Definitions
Ivan Rygaev
Context-Oriented Ontoeditor Diagogue
Gennady Kanygin
Russian Syntactic Parser LPaRus of Company Megaputer Intelligence
Mikhail Kiselev, Diana Antoshina
Verbal Aggression in Dialogue with a Chatbot
Ilya Utekhin
ParaPhraser API: Paraphrase-oriented Linguistic Service
Ekaterina Pronoza
industrial session
Kirill Petrov (Just AI)
Talking Robot Emelya: Case of NLU Integration in IoT
Tasha Nagamine (Droice Labs)
Machine Learning in Healthcare: Applications, Challenges, and Solutions
Denis Kulagin (KartaSlov)
Machine Learning and Crowdsourcing: Taking the Best of two Worlds to Upgrade a Dictionary into a Linguistic Platform
Artyom Popov (VK)
Look-alike Targeting in Social Networks Advertising
Hackathon for plagiarism detection in Russian texts
Date: September 22-23, 2017
Topic: Copy & paste and paraphrased plagiarism detection
Registration: https://goo.gl/tp6r7N or on the day of the event on-site
Contact information: plagevalrus@gmail.com
Site: http://ru-eval.ru/plageval/en/

Hack the Plagiarizer!

For the first time ever, a plagiarism detection for the Russian language hackathon is organized, co-located with the AINL conference.

What is it about?

The Hackathon is focused on developing and evaluating algorithms for monolingual Russian plagiarism detection with the focus on scientific texts (academic plagiarism). The problem offered to the participants will be similar to the Text Alignment (TA) task evaluated at the PAN competitions; i.e., in a pair of texts, paraphrased or copy-pasted fragments taken from one text are to be found in a second text. For the task, the organizers provide training data. Participants are supposed to develop and train their approaches on this dataset.

The Hackathon opens with the talks by the Hackathon organizers. They will tell about the technologies used in plagiarism detection.

More details on the hackathon rules and workflow. (in Russian)

Hackathon organizers
Mikhail Kopotev (University of Helsinki), Andrey Kutuzov (University of Oslo), Ivan Smirnov and Denis Zubarev (Institute for Systems Analysis, FRC CSC RAS, Moscow), Olga Lyashevskaya (Higher School of Economics, Moscow).
Feel free to contact us at ainlevent@gmail.com