We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training.
In the test set the frequency of all entity types is even.
no code implementations • 19 May 2022 • Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova, Serguei Barannikov, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP.
no code implementations • 15 Feb 2022 • Alena Fenogenova, Maria Tikhonova, Vladislav Mikhailov, Tatiana Shavrina, Anton Emelyanov, Denis Shevelev, Alexandr Kukushkin, Valentin Malykh, Ekaterina Artemova
In the last year, new neural architectures and multilingual pre-trained models have been released for Russian, which led to performance evaluation problems across a range of language understanding tasks.
The labelling is carried out on the crowdsourcing platfrom Yandex. Toloka in two stages.
This is in line with the common understanding of how multilingual models conduct transferring between languages
Recent research has adopted a new experimental field centered around the concept of text perturbations which has revealed that shuffled word order has little to no impact on the downstream performance of Transformer-based language models across many NLP tasks.
1 code implementation • • Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content.
In this paper, we present NEREL, a Russian dataset for named entity recognition and relation extraction.
In the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training.
Moreover, due to the usage of the fine-tuned language model, the generated adversarial examples are hard to detect, thus current models are not robust.
The new generation of pre-trained NLP models push the SOTA to the new limits, but at the cost of computational resources, to the point that their use in real production environments is often prohibitively expensive.
This paper presents a new Massive Open Online Course on Natural Language Processing, targeted at non-English speaking students.
The outstanding performance of transformer-based language models on a great variety of NLP and NLU tasks has stimulated interest in exploring their inner workings.
The success of pre-trained transformer language models has brought a great deal of interest on how these models work, and what they learn about language.
no code implementations • • Artem Shelmanov, Dmitri Puzyrev, Lyubov Kupriyanova, Denis Belyakov, Daniil Larionov, Nikita Khromov, Olga Kozlova, Ekaterina Artemova, Dmitry V. Dylov, Alexander Panchenko
Annotating training data for sequence tagging of texts is usually very time-consuming.
In turn, the Mahalanobis distance captures this disparity easily.
We show-case an application of information extraction methods, such as named entity recognition (NER) and relation extraction (RE) to a novel corpus, consisting of documents, issued by a state agency.
2 code implementations • • Tatiana Shavrina, Alena Fenogenova, Anton Emelyanov, Denis Shevelev, Ekaterina Artemova, Valentin Malykh, Vladislav Mikhailov, Maria Tikhonova, Andrey Chertok, Andrey Evlampiev
In this paper, we introduce an advanced Russian general language understanding evaluation benchmark -- RussianGLUE.
Ranked #1 on Word Sense Disambiguation on RUSSE
We study the effectiveness of contextualized embeddings for the task of diachronic semantic change detection for Russian language data.
The task is to take both the question and a paragraph as input and come up with a yes/no answer, i. e. to produce a binary output.
In this paper we present a corpus of Russian strategic planning documents, RuREBus.
In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP).
In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics.
Applications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out-of-vocabulary (OOV) words.
no code implementations • • Varvara Logacheva, Denis Teslenko, Artem Shelmanov, Steffen Remus, Dmitry Ustalov, Andrey Kutuzov, Ekaterina Artemova, Chris Biemann, Simone Paolo Ponzetto, Alexander Panchenko
We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al. (2018), enabling WSD in these languages.
We investigate the performance of sentence embeddings models on several tasks for the Russian language.
This paper presents the first gold-standard resource for Russian annotated with compositionality information of noun compounds.