Oleg Serikov


pdf bib
Emergent Structures and Training Dynamics in Large Language Models
Ryan Teehan | Miruna Clinciu | Oleg Serikov | Eliza Szczechla | Natasha Seelam | Shachar Mirkin | Aaron Gokaslan
Proceedings of BigScience Episode \#5 -- Workshop on Challenges & Perspectives in Creating Large Language Models

Large language models have achieved success on a number of downstream tasks, particularly in a few and zero-shot manner. As a consequence, researchers have been investigating both the kind of information these networks learn and how such information can be encoded in the parameters of the model. We survey the literature on changes in the network during training, drawing from work outside of NLP when necessary, and on learned representations of linguistic features in large language models. We note in particular the lack of sufficient research on the emergence of functional units, subsections of the network where related functions are grouped or organised, within large language models and motivate future work that grounds the study of language models in an analysis of their changing internal structure during training time.

pdf bib
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP
Tatiana Shavrina | Vladislav Mikhailov | Valentin Malykh | Ekaterina Artemova | Oleg Serikov | Vitaly Protasov
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP


pdf bib
Discourse-Driven Integrated Dialogue Development Environment for Open-Domain Dialogue Systems
Denis Kuznetsov | Dmitry Evseev | Lidia Ostyakova | Oleg Serikov | Daniel Kornev | Mikhail Burtsev
Proceedings of the 2nd Workshop on Computational Approaches to Discourse

Development environments for spoken dialogue systems are popular today because they enable rapid creation of the dialogue systems in times when usage of the voice AI Assistants is constantly growing. We describe a graphical Discourse-Driven Integrated Dialogue Development Environment (DD-IDDE) for spoken open-domain dialogue systems. The DD-IDDE allows dialogue architects to interactively define dialogue flows of their skills/chatbots with the aid of the discourse-driven recommendation system, enhance these flows in the Python-based DSL, deploy, and then further improve based on the skills/chatbots usage statistics. We show how these skills/chatbots can be specified through a graphical user interface within the VS Code Extension, and then run on top of the Dialog Flow Framework (DFF). An earlier version of this framework has been adopted in one of the Alexa Prize 4 socialbots while the updated version was specifically designed to power the described DD-IDDE solution.

pdf bib
Teaching a Massive Open Online Course on Natural Language Processing
Ekaterina Artemova | Murat Apishev | Denis Kirianov | Veronica Sarkisyan | Sergey Aksenov | Oleg Serikov
Proceedings of the Fifth Workshop on Teaching NLP

In this paper we present a new Massive Open Online Course on Natural Language Processing, targeted at non-English speaking students. The course lasts 12 weeks, every week consists of lectures, practical sessions and quiz assigments. Three weeks out of 12 are followed by Kaggle-style coding assigments. Our course intents to serve multiple purposes: (i) familirize students with the core concepts and methods in NLP, such as language modelling or word or sentence representations, (ii) show that recent advances, including pre-trained Transformer-based models, are build upon these concepts; (iii) to introduce architectures for most most demanded real-life applications, (iii) to develop practical skills to process texts in multiple languages. The course was prepared and recorded during 2020 and so far have received positive feedback.

pdf bib
Morph Call: Probing Morphosyntactic Content of Multilingual Transformers
Vladislav Mikhailov | Oleg Serikov | Ekaterina Artemova
Proceedings of the Third Workshop on Computational Typology and Multilingual NLP

The outstanding performance of transformer-based language models on a great variety of NLP and NLU tasks has stimulated interest in exploration of their inner workings. Recent research has been primarily focused on higher-level and complex linguistic phenomena such as syntax, semantics, world knowledge and common-sense. The majority of the studies is anglocentric, and little remains known regarding other languages, specifically their morphosyntactic properties. To this end, our work presents Morph Call, a suite of 46 probing tasks for four Indo-European languages of different morphology: Russian, French, English and German. We propose a new type of probing tasks based on detection of guided sentence perturbations. We use a combination of neuron-, layer- and representation-level introspection techniques to analyze the morphosyntactic content of four multilingual transformers, including their understudied distilled versions. Besides, we examine how fine-tuning on POS-tagging task affects the probing performance.

pdf bib
SIGTYP 2021 Shared Task: Robust Spoken Language Identification
Elizabeth Salesky | Badr M. Abdullah | Sabrina Mielke | Elena Klyachko | Oleg Serikov | Edoardo Maria Ponti | Ritesh Kumar | Ryan Cotterell | Ekaterina Vylomova
Proceedings of the Third Workshop on Computational Typology and Multilingual NLP

While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource availability: where larger datasets exist, they may be single-speaker or have different domains than desired application scenarios, demanding a need for domain and speaker-invariant language identification systems. This year’s shared task on robust spoken language identification sought to investigate just this scenario: systems were to be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking realistic low-resource scenarios. We see that domain and speaker mismatch proves very challenging for current methods which can perform above 95% accuracy in-domain, which domain adaptation can address to some degree, but that these conditions merit further investigation to make spoken language identification accessible in many scenarios.


pdf bib
Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation
Vladislav Mikhailov | Lorenzo Tosi | Anastasia Khorosheva | Oleg Serikov
Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects

The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-decoder model with attention. Our algorithm provides lemmatisation and morphological analysis generation for previously unseen low-resource language surface forms with only annotated data on the related languages given. Despite the inherently lossy annotation projection, we achieved the best lemmatisation F1-score in the VarDial 2019 Shared Task on Cross-Lingual Morphological Analysis for both Karachay-Balkar (Turkic languages, agglutinative morphology) and Sardinian (Romance languages, fusional morphology).