FoTran 2018: Found in translation The first workshop on representation learning from multilingual data

Date: September 28, 2018
Place: University of Helsinki

Participation is free of charge (space limits may apply)
but requires registration:

The program features invited talks by:

* Kyunghyun Cho, NYU, New York
* Waleed Ammar, Allen Institute for AI
* André Martins, Unbabel, Lisbon
* Ivan Vulić, University of Cambridge
* Željko Agić, IT University of Copenhagen

The goal of this workshop is to bring together researchers that are
interested in learning meaning representations from natural languages
using multilingual data sets. The main focus is on the use of
translations as “semantic mirrors”, allowing to infer meaning from
translational grounding. With this, FoTran 2018 also constitutes the
start of an ERC project with the same name
( and we hope that
this event will set up a growing network that we will make use of
during the project. Topics of special interest of this kickoff-event
are not restricted to the objectives of the ERC project but include:

* sentence representation learning in general
* multilingual neural machine translation
* cross-lingual NLP and transfer models
* approaches to natural language inference
* interpretation and analyses of neural networks used for NLP

We invite participants to present their own work as short
presentations or posters and we encourage the re-use of talks and
posters from previous events. There is no call for papers nor any
proceedings but we would like to publish presentations on-line
(slides, posters, abstracts or similar) on the workshop website after
the event if the speakers agree.

Local Organisation Team

Jörg Tiedemann
Hande Celikkanat
Raul Vazquez

Рубрика: Конференции | Добавить комментарий

новая магистратура по компьютерной лингвистике — подавать до 6го августа

Новая междисциплинарная магистерская программа

Новосибирского государственного университета

Математическая и компьютерная лингвистика

Направления подготовки:

02.04.01 Математика и компьютерные науки. Профиль: Математическая и компьютерная лингвистика

45.04.01 Филология. Профиль: Математическая и компьютерная лингвистика

Нормативный срок обучения – 2 года

Программа нацелена на подготовку специалистов по теории и практике создания математических и компьютерных инструментов для работы с информацией, содержащейся в устных и письменных текстах на естественном языке.

Программа даёт уникальную возможность:

приобрести знания и опыт для создания и использования инструментов общего назначения, ориентированных на работу с естественным языком;

приобрести углублённые знания по смежным областям математики и лингвистики;

приобрести большой опыт междисциплинарного взаимодействия, осуществляемого на протяжении всего периода обучения в рамках учебной и проектной работы.

Читать далее

Рубрика: Курсы/Образование/Постдоки | Добавить комментарий

AINL 2018: final call for paoers

По просьбам потенциальных участников мы продлили дедлайн до 3го июня. Не упустите свой шанс!

Рубрика: Конференции | Добавить комментарий

Call for participation: 12th Russian Summer School in Information Retrieval (RuSSIR 2018), August 27-31, 2018, Kazan, Russia

12th Russian Summer School in Information Retrieval (RuSSIR 2018)

August 27-31, 2018, Kazan, Russia,

Application deadline: July 10, 2018

*Information Retrieval for Good*
The school will be held with a special focus on applications in humanitarian, medical, and health domains.

The 12th Russian Summer School in Information Retrieval (RuSSIR 2018) will be held on August 27-31, 2018 in Kazan, Russia. The school is co-organized by the Kazan Federal University and the Russian Information Retrieval Evaluation Seminar (ROMIP).

The main goals of the RuSSIR school series are to enable students to learn about modern problems and methods in information retrieval and related disciplines; to stimulate scientific research and collaboration in the field; to create an environment for successful networking between scientists, students, and industry professionals.

RuSSIR 2018 will offer the following keynotes and courses:

* Carlos Castillo (Universitat Pompeu Fabra) — “Crisis Informatics”, “The Biases of Social Data”

* Cathal Gurrin (School of Computing, Dublin City University) — “The Information Retrieval Challenge of Lifelogs and Personal Life Archives”

* Henning Müller (University of Geneva) — “Evaluation of IR systems and multi-modal retrieval in the medical domain”


* Valentin Malykh, Mikhail Burtsev (Moscow Institute of Physics and Technology) — “Conversational AI through Deep Learning”

* Rishabh Mehrotra (Spotify Research) — “Learning from User Interactions”

* Guido Zuccon (Queensland University of Technology) — “Health Search”

* Harrie Oosterhuis (University of Amsterdam) — “Learning to Rank and Evaluation in the Online Setting”

* Prasenjit Mitra (Pennsylvania State University) — “Retrieving Information Interactively Using Natural Language”

Summer school participants will be provided with space and timeslot to present their current research projects/ideas at poster sessions to get feedback from the fellow students and the lecturers.

In addition to educational and social activity, the school will have a versatile social program.

Читать далее

Рубрика: Курсы/Образование/Постдоки | Добавить комментарий

AINL: Call for Papers

AINL: Artificial Intellegince and Natural Language Conference

17-19 October 2018, St. Petersburg, Russia


The 7th conference on Artificial Intelligence and Natural Language invites everybody interested in intellectual technologies, both from academic institutes and innovative companies. The conference aimed to bring together experts in the areas of text mining, speech technologies, dialogue systems, information retrieval, machine learning, artificial intelligence and robotics; to create a platform for sharing experience, extending contacts and searching for possible collaboration.



Shalom Lappin

University of Gothenburg, King’s College London, and Queen Mary University of London


Modelling the Effect of Document Context on Sentence Acceptability



Natural Language Processing

Artificial Intelligence, Deep Learning, Machine Learning for NLP

Information Retrieval

Social Media and Social Network Analysis

Speech Generation and Recognition, Spoken Language Processing

Human-Computer Interfaces, Dialogue Systems

Linked Data and Semantic Web

Context Analysis, Text Mining

Plagiarism Detection, Author Profiling and Authorship Detection

Machine Translation, Crosslingual and Multilingual applications

Big Data and Data Mining

Robotics, Cyber-Physical Systems



May 25 — Short&Full Paper Submission Deadline

June 22 — Notification of long and short paper acceptance

July 15 — Camera-ready submission

Sptember 15 — Industrial submissions, demo and poster deadline

October 1 — Notification for industrial submissions, demo and posters

Читать далее

Рубрика: Конференции | Добавить комментарий

Call for posters and demos: Workshop on dialogue and perception (DaP 2018)

Call for posters and demos: Workshop on dialogue and perception (DaP 2018)

Deadline for submission: 26 April 2018
Notification of acceptance: 10 May 2018
Workshop date: June 14-15, 2018

Venue: Wallenberg Conference Centre, University of Gothenburg

Conference webpage:

Organised by CLASP, University of Gothenburg,

The study of dialogue investigates how natural language is used in interaction between interlocutors and how coordination and successful communication is achieved. Dialogue is multimodal, situated and embodied, with non-linguistic factors such as attention, eye gaze and gesture critical to understanding communication. However, studies on dialogue have often taken for granted that we align our perceptual representations, which are taken to be part of common ground (grounding in dialogue, Clark, 1996). They have also typically remained silent about how we integrate information from different sources and modalities and the different contribution of each of these. These assumptions are unsustainable when we consider interactions between agents with obviously different perceptual capabilities, as is the case in dialogues between humans and artificial agents, such as avatars or robots.

Contrarily, studies of perception have focussed on how an agent interacts with and interprets the information from their perceptual environment. There is significant research on how language is grounded in perception, how words are connected to perceptual representations and agent’s actions and therefore assigned meaning (grounding in action and perception, Harnad, 1990). In the last decade there has been impressive progress on integrated approaches to language, action, and perception, especially with the introduction of deep learning methods in the field of image descriptions that use end-to-end training from data. However, these have a limited integration to the dynamics of dialogue and often fail to take into account the incremental and context sensitive nature of language and the environment.

The aim of this workshop is to initiate a genuine dialogue between these related areas and to examine different approaches from computational, linguistic and psychological perspectives and how these can inform each other. It will feature invited talks by leading researchers in these areas, and high level contributed papers, presented as posters, selected through open competition and rigorous review.

We invite papers of between 2-4 pages of content and up to one additional page for references, following the ACL style guidelines. The conference proceedings will be published online, with an ISSN, on the CLASP website. Authors will have the opportunity to extend their papers for the post-proceedings and will retain the copyright of their papers and be free to publish them elsewhere, with acknowledgement.

Registration is free and participation is open. We warmly invite everyone to attend.

Читать далее

Рубрика: Конференции | Добавить комментарий

*Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP*

*ACL 2018, July 19th*

*Papers Due: April 8th*



*Call for long and short papers*

There is a long standing tradition in NLP focusing on fundamental language
modeling tasks such as morphological analysis, POS tagging, parsing, WSD or
semantic parsing. In the context of end-user NLP tasks, these have played
the role of enabling technologies, providing a layer of representation upon
which more complex tasks can be built. However, in recent years we have
witnessed a number of success stories for tasks ranging from information
extraction or text comprehension to machine translation, for which the use
of embeddings and neural networks has driven state of the art results to
new levels. More importantly, these are often end-to-end architectures
trained on large amounts of data and making little or no use of a
linguistically-informed language representation layer. For example, the
modeling of word senses and word sense disambiguation are implicit in the
functional composition of word embeddings. Other topics such as linear
sentence processing versus syntactic parses or frequency-based word
segmentation versus morphological analysis are still up for debate.

This workshop focuses on the role of linguistic structures in the neural
network era. We aim to gauge their significance in building better, more
generalizable NLP systems. We would like to address the following questions:

— Is linguistic information useful for neural network architectures: can
it improve state of the art neural architectures, and how should it be
used? Does it help in building models that transfer better to new domains,
new languages, new tasks, or for other limited annotated data scenarios?
— Are there any better implicit representations that neural networks can
extract, whether similar or not to linguistic structures, that can be
transferred or shared across tasks and, hence, serve as core language
representation layers?

Читать далее

Рубрика: Конференции | Добавить комментарий

ESSLLI Workshop «NLP in the Era of Big Data, Deep Learning, and Post Truth»



«NLP in the Era of Big Data, Deep Learning, and Post Truth»


Workshop at ESSLLI 2018

August 13-17, 2018

Sofia, Bulgaria

Deadline: April 16, 2018, midnight Pacific Standard Time (UTC−8).



Recent years have seen fast advances of the field of Natural Language Processing (NLP) due to the simultaneous influence of two revolutionary forces: Big Data and Deep Learning. The aim of using large corpora has been prominent in NLP since an earlier statistical, corpus-based revolution of the 1990s. Indeed, in corpus-based NLP size does matter, and researchers have been exploring corpora as large as the entire Web; now this abundance of data has enabled the return of Neural Networks and the rise of Deep Learning. More recently, we have further seen the rise of Big Data with its 3Vs: Volume, Velocity, and Variety. Even more recently, with the spread of fake news, it has been suggested that a fourth V should be considered: Veracity.


The workshop welcomes work presenting new developments in applying NLP for solving problems related to Big Data, Deep Learning, and Veracity. We also invite discussion about the impact of these revolutionary forces on the field of NLP as a whole.


Selected papers that have been presented at the workshop will be invited to submit a full version of the paper to the Cybernetics and Information Technologies journal, which is indexed by SCOPUS, SJR, and some other databases:

The workshop will be held during the whole second week of the 30th edition of ESSLLI (European Summer School in Logic, Language and Information) August 13 — 17, 2018.

Читать далее

Рубрика: Конференции, Курсы/Образование/Постдоки | Добавить комментарий


Sapienza University of Rome, Italy

Department of Computer Science

Fully-funded Ph.D. positions in Natural Language Processing are open at the
Sapienza University of Rome for foreign students. Students interested in
working in the Linguistic Computing Laboratory (,
Department of Computer Science of the Sapienza (Italian Department of
Excellence, ranked first in computer science), can choose to work in the
context of a 5-year ERC Consolidator Grant funded by the European Research
Council (ERC) and headed by prof. Roberto Navigli
<>, following the success of his
MultiJEDI ERC Starting Grant ( The successful
candidate will participate in a frontier research project aimed at
designing and investigating novel neural network architectures for
multilingual disambiguation and semantic parsing and will work in the
vibrant environment of a leading and highly-active international research
team comprising 3 faculty members, 1 post-doc and 6 Ph.D. students. The
group has published dozens of papers in top-tier venues
<> in the field of
computational linguistics and artificial intelligence.

Ph.D. students in the research group have the option to interact with
Babelscape <>, a Sapienza startup company founded by
prof. Navigli which brings cutting-edge research in multilingual Natural
Language Processing to the market and makes research projects, such as the
award-winning BabelNet <>, sustainable in the long term.
Babelscape is currently working for key players in different fields,
including multinational companies, and national and international public
bodies. Around 20 developers and researchers currently work in the company.
Читать далее

Рубрика: Курсы/Образование/Постдоки | Добавить комментарий

вакансия лингвист-разработчик в СПб

В компании Just AI ( в связи с расширением открывается вакансия на позицию лингвист-разработчик.
Нашим основным технологическим продуктом является платформа для создания чат-ботов.
Направления нашей деятельности: автоматизация служб клиентской поддержки, conversational commerce, обеспечение диалога на естественном языке с роботами и умными домами.

• Составление и проработка сценариев, тем, структуры диалогов для чат-ботов крупных компаний.
• Написание небольших скриптов для обработки данных.
• Анализ логов диалогов «клиент-оператор» и «клиент-бот», выделение структуры и разметка.

• Письменная, стилистическая‚ орфографическая, техническая грамотность, внимательность к деталям.
• Навыки программирования на любом из языков (предпочтительно — Python, JavaScript).

• Очень приветствуется практический опыт работы с системами обработки естественного языка.
• Английский язык
• Знание современных методов компьютерной лингвистики, основных задач NLP и методов их решения.
• Опыт работы с системами контроля версий Git или Mercurial.
• Наличие профильного образования по обработке естественного языка.
• Опыт работы с NLP: MyStem, NLTK.

• Работа в офисе у станции метро «Спортивная».
• Гибкое начало рабочего дня, 8-часовой рабочий день (часы присутствия с 12 до 17).
• Официальное оформление с 1го рабочего дня, «белая» заработная плата.
• Профессиональное развитие и карьерный рост.

Просим отправлять резюме на адрес:

Рубрика: Вакансии/Стажировки | Добавить комментарий