Adoption of messaging communication and voice assistants has grown rapidly in the last years. This creates a demand for tools that speed up prototyping of featurerich dialogue systems. An open-source library DeepPavlov is tailored for development of conversational agents. The library prioritises efficiency, modularity, and extensibility with the goal to make it easier to develop dialogue systems from scratch and with limited data available. It supports modular as well as end-to-end approaches to implementation of conversational agents. Conversational agent consists of skills and every skill can be decomposed into components. Components are usually models which solve typical NLP tasks such as intent classification, named entity recognition or pre-trained word vectors. Sequence-to-sequence chitchat skill, question answering skill or task-oriented skill can be assembled from components provided in the library.

Our paper addresses the problem of multilingual named entity recognition on the material of 4 languages: Russian, Bulgarian, Czech and Polish. We solve this task using the BERT model. We use a hundred languages multilingual model as base for transfer to the mentioned Slavic languages. Unsupervised pre-training of the BERT model on these 4 languages allows to significantly outperform baseline neural approaches and multilingual BERT. Additional improvement is achieved by extending BERT with a word-level CRF layer. Our system was submitted to BSNLP 2019 Shared Task on Multilingual Named Entity Recognition and took the 1st place in 3 competition metrics out of 4 we participated in. We open-sourced NER models and BERT model pre-trained on the four Slavic languages.

No abstract

This paper presents an algorithm for automatic word forms inflection. We use the method of longest common subsequence to extract abstract paradigms from given pairs of basic and inflected word forms, as well as suffix and prefix features to predict this paradigm automatically. We elaborate this algorithm using combination of affix feature-based and character ngram models, which substantially enhances performance especially for the languages possessing nonlocal phenomena such as vowel harmony. Our system took part in SIGMORPHON 2016 Shared Task and took 3rd place in 17 of 30 subtasks and 4th place in 7 substasks among 7 participants.