In recent years, the models were tested on different probing tasks to examine their language knowledge. However, few researchers explored the very process of models’ language acquisition. Nevertheless, the analysis of language acquisition during training could shed light on the model parameters that help to acquire the language faster. In this work, we experiment with model hyperparameters and reveal that the hidden size is the most essential factor for model language acquisition.

Linguistic analysis of language models is one of the ways to explain and describe their reasoning, weaknesses, and limitations. In the probing part of the model interpretability research, studies concern individual languages as well as individual linguistic structures. The question arises: are the detected regularities linguistically coherent, or on the contrary, do they dissonate at the typological scale? Moreover, the majority of studies address the inherent set of languages and linguistic structures, leaving the actual typological diversity knowledge out of scope. In this paper, we present and apply the GUI-assisted framework allowing us to easily probe massive amounts of languages for all the morphosyntactic features present in the Universal Dependencies data. We show that reflecting the anglo-centric trend in NLP over the past years, most of the regularities revealed in the mBERT model are typical for the western-European languages. Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards, allowing practitioners to use and share their familiar probing methods to interpret multilingual models. Thus we propose a toolkit to systematize the multilingual flaws in multilingual models, providing a reproducible experimental setup for 104 languages and 80 morphosyntactic features.

Today, natural language processing heavily relies on pre-trained large language models. Even though such models are criticized for the poor interpretability, they still yield state-of-the-art solutions for a wide set of very different tasks. While lots of probing studies have been conducted to measure the models’ awareness of grammatical knowledge, semantic probing is less popular. In this work, we introduce the probing pipeline to study the representedness of semantic relations in transformer language models. We show that in this task, attention scores are nearly as expressive as the layers’ output activations, despite their lesser ability to represent surface cues. This supports the hypothesis that attention mechanisms are focusing not only on the syntactic relational information but also on the semantic one.

The vast majority of existing datasets for Named Entity Recognition (NER) are built primarily on news, research papers and Wikipedia with a few exceptions, created from historical and literary texts. What is more, English is the main source for data for further labelling. This paper aims to fill in multiple gaps by creating a novel dataset “Razmecheno”, gathered from the diary texts of the project “Prozhito” in Russian. Our dataset is of interest for multiple research lines: literary studies of diary texts, transfer learning from other domains, low-resource or cross-lingual named entity recognition. Razmecheno comprises 1331 sentences and 14119 tokens, sampled from diaries, written during the Perestroika. The annotation schema consists of five commonly used entity tags: person, characteristics, location, organisation, and facility. The labelling is carried out on the crowdsourcing platfrom Yandex.Toloka in two stages. First, workers selected sentences, which contain an entity of particular type. Second, they marked up entity spans. As a result 1113 entities were obtained. Empirical evaluation of Razmecheno is carried out with off-the-shelf NER tools and by fine-tuning pre-trained contextualized encoders. We release the annotated dataset for open access.

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.

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.

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.

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.

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.

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).