Minimal pairs are a well-established approach to evaluating the grammatical knowledge of language models. However, existing resources for minimal pairs address a limited number of languages and lack diversity of language-specific grammatical phenomena. This paper introduces the Russian Benchmark of Linguistic Minimal Pairs (RuBLiMP), which includes 45k pairs of sentences that differ in grammaticality and isolate a morphological, syntactic, or semantic phenomenon. In contrast to existing benchmarks of linguistic minimal pairs, RuBLiMP is created by applying linguistic perturbations to automatically annotated sentences from open text corpora and decontaminating test data. We describe the data collection protocol and present the results of evaluating 25 language models in various scenarios. We find that the widely used LMs for Russian are sensitive to morphological and agreement-oriented contrasts, but fall behind humans on phenomena requiring the understanding of structural relations, negation, transitivity, and tense. RuBLiMP, the codebase, and other materials are publicly available.

The ease of access to large language models (LLMs) has enabled a widespread of machine-generated texts, and now it is often hard to tell whether a piece of text was human-written or machine-generated. This raises concerns about potential misuse, particularly within educational and academic domains. Thus, it is important to develop practical systems that can automate the process. Here, we present one such system, LLM-DetectAIve, designed for fine-grained detection. Unlike most previous work on machine-generated text detection, which focused on binary classification, LLM-DetectAIve supports four categories: (i) human-written, (ii) machine-generated, (iii) machine-written, then machine-humanized, and (iv) human-written, then machine-polished. Category (iii) aims to detect attempts to obfuscate the fact that a text was machine-generated, while category (iv) looks for cases where the LLM was used to polish a human-written text, which is typically acceptable in academic writing, but not in education. Our experiments show that LLM-DetectAIve can effectively identify the above four categories, which makes it a potentially useful tool in education, academia, and other domains.LLM-DetectAIve is publicly accessible at https://github.com/mbzuai-nlp/LLM-DetectAIve. The video describing our system is available at https://youtu.be/E8eT_bE7k8c.

Instruction tuning has become an integral part of training pipelines for Large Language Models (LLMs) and has been shown to yield strong performance gains. In an orthogonal line of research, Annotation Error Detection (AED) has emerged as a tool for detecting quality problems in gold standard labels. So far, however, the application of AED methods has been limited to classification tasks. It is an open question how well AED methods generalize to language generation settings, which are becoming more widespread via LLMs. In this paper, we present a first and novel benchmark for AED on instruction tuning data: Donkii.It comprises three instruction-tuning datasets enriched with error annotations by experts and semi-automatic methods. We also provide a novel taxonomy of error types for instruction-tuning data.We find that all three datasets contain clear errors, which sometimes propagate directly into instruction-tuned LLMs. We propose four AED baselines for the generative setting and evaluate them extensively on the newly introduced dataset. Our results show that the choice of the right AED method and model size is indeed crucial and derive practical recommendations for how to use AED methods to clean instruction-tuning data.

Mainstream cross-lingual task-oriented dialogue (ToD) systems leverage the transfer learning paradigm by training a joint model for intent recognition and slot-filling in English and applying it, zero-shot, to other languages. We address a gap in prior research, which often overlooked the transfer to lower-resource colloquial varieties due to limited test data. Inspired by prior work on English varieties, we craft and manually evaluate perturbation rules that transform German sentences into colloquial forms and use them to synthesize test sets in four ToD datasets. Our perturbation rules cover 18 distinct language phenomena, enabling us to explore the impact of each perturbation on slot and intent performance. Using these new datasets, we conduct an experimental evaluation across six different transformers. Here, we demonstrate that when applied to colloquial varieties, ToD systems maintain their intent recognition performance, losing 6% (4.62 percentage points) in accuracy on average. However, they exhibit a significant drop in slot detection, with a decrease of 31% (21 percentage points) in slot F₁ score. Our findings are further supported by a transfer experiment from Standard American English to synthetic Urban African American Vernacular English.

This paper presents Papilusion, an AI-generated scientific text detector developed within the DAGPap24 shared task on detecting automatically generated scientific papers. We propose an ensemble-based approach and conduct ablation studies to analyze the effect of the detector configurations on the performance. Papilusion is ranked 6th on the leaderboard, and we improve our performance after the competition ended, achieving 99.46 (+9.63) of the F1-score on the official test set.

Warning: this work contains upsetting or disturbing content. Large language models (LLMs) tend to learn the social and cultural biases present in the raw pre-training data. To test if an LLM’s behavior is fair, functional datasets are employed, and due to their purpose, these datasets are highly language and culture-specific. In this paper, we address a gap in the scope of multilingual bias evaluation by presenting a bias detection dataset specifically designed for the Russian language, dubbed as RuBia. The RuBia dataset is divided into 4 domains: gender, nationality, socio-economic status, and diverse, each of the domains is further divided into multiple fine-grained subdomains. Every example in the dataset consists of two sentences with the first reinforcing a potentially harmful stereotype or trope and the second contradicting it. These sentence pairs were first written by volunteers and then validated by native-speaking crowdsourcing workers. Overall, there are nearly 2,000 unique sentence pairs spread over 19 subdomains in RuBia. To illustrate the dataset’s purpose, we conduct a diagnostic evaluation of state-of-the-art or near-state-of-the-art LLMs and discuss the LLMs’ predisposition to social biases.

Named Entity Recognition (NER) is a fundamental task to extract key information from texts, but annotated resources are scarce for dialects. This paper introduces the first dialectal NER dataset for German, BarNER, with 161K tokens annotated on Bavarian Wikipedia articles (bar-wiki) and tweets (bar-tweet), using a schema adapted from German CoNLL 2006 and GermEval. The Bavarian dialect differs from standard German in lexical distribution, syntactic construction, and entity information. We conduct in-domain, cross-domain, sequential, and joint experiments on two Bavarian and three German corpora and present the first comprehensive NER results on Bavarian. Incorporating knowledge from the larger German NER (sub-)datasets notably improves on bar-wiki and moderately on bar-tweet. Inversely, training first on Bavarian contributes slightly to the seminal German CoNLL 2006 corpus. Moreover, with gold dialect labels on Bavarian tweets, we assess multi-task learning between five NER and two Bavarian-German dialect identification tasks and achieve NER SOTA on bar-wiki. We substantiate the necessity of our low-resource BarNER corpus and the importance of diversity in dialects, genres, and topics in enhancing model performance.

This paper describes AIpom, a system designed to detect a boundary between human-written and machine-generated text (SemEval-2024 Task 8, Subtask C: Human-Machine Mixed Text Detection). We propose a two-stage pipeline combining predictions from an instruction-tuned decoder-only model and encoder-only sequence taggers. AIpom is ranked second on the leaderboard while achieving a Mean Absolute Error of 15.94. Ablation studies confirm the benefits of pipelining encoder and decoder models, particularly in terms of improved performance.

Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot rankers diminishes when queries and documents are present in different languages. Motivated by this, we propose to train ranking models on artificially code-switched data instead, which we generate by utilizing bilingual lexicons. To this end, we experiment with lexicons induced from (1) cross-lingual word embeddings and (2) parallel Wikipedia page titles. We use the mMARCO dataset to extensively evaluate reranking models on 36 language pairs spanning Monolingual IR (MoIR), Cross-lingual IR (CLIR), and Multilingual IR (MLIR). Our results show that code-switching can yield consistent and substantial gains of 5.1 MRR@10 in CLIR and 3.9 MRR@10 in MLIR, while maintaining stable performance in MoIR. Encouragingly, the gains are especially pronounced for distant languages (up to 2x absolute gain). We further show that our approach is robust towards the ratio of code-switched tokens and also extends to unseen languages. Our results demonstrate that training on code-switched data is a cheap and effective way of generalizing zero-shot rankers for cross-lingual and multilingual retrieval.

The development of state-of-the-art systems in different applied areas of machine learning (ML) is driven by benchmarks, which have shaped the paradigm of evaluating generalisation capabilities from multiple perspectives. Although the paradigm is shifting towards more fine-grained evaluation across diverse tasks, the delicate question of how to aggregate the performances has received particular interest in the community. In general, benchmarks follow the unspoken utilitarian principles, where the systems are ranked based on their mean average score over task-specific metrics. Such aggregation procedure has been viewed as a sub-optimal evaluation protocol, which may have created the illusion of progress. This paper proposes Vote’n’Rank, a framework for ranking systems in multi-task benchmarks under the principles of the social choice theory. We demonstrate that our approach can be efficiently utilised to draw new insights on benchmarking in several ML sub-fields and identify the best-performing systems in research and development case studies. The Vote’n’Rank’s procedures are more robust than the mean average while being able to handle missing performance scores and determine conditions under which the system becomes the winner.

This paper investigates how Transformer language models (LMs) fine-tuned for acceptability classification capture linguistic features. Our approach is based on best practices of topological data analysis (TDA) in NLP: we construct directed attention graphs from attention matrices, derive topological features from them and feed them to linear classifiers. We introduce two novel features, chordality and the matching number, and show that TDA-based classifiers outperform fine-tuning baselines. We experiment with two datasets, CoLA and RuCoLA, in English and Russian, which are typologically different languages. On top of that, we propose several black-box introspection techniques aimed at detecting changes in the attention mode of the LM’s during fine-tuning, defining the LM’s prediction confidences, and associating individual heads with fine-grained grammar phenomena. Our results contribute to understanding the behaviour of monolingual LMs in the acceptability classification task, provide insights into the functional roles of attention heads, and highlight the advantages of TDA-based approaches for analyzing LMs.We release the code and the experimental results for further uptake.

Bilingual word lexicons map words in one language to their synonyms in another language. Numerous papers have explored bilingual lexicon induction (BLI) in high-resource scenarios, framing a typical pipeline that consists of two steps: (i) unsupervised bitext mining and (ii) unsupervised word alignment. At the core of those steps are pre-trained large language models (LLMs).In this paper we present the analysis of the BLI pipeline for German and two of its dialects, Bavarian and Alemannic. This setup poses a number of unique challenges, attributed to the scarceness of resources, relatedness of the languages and lack of standardization in the orthography of dialects. We analyze the BLI outputs with respect to word frequency and the pairwise edit distance. Finally, we release an evaluation dataset consisting of manual annotations for 1K bilingual word pairs labeled according to their semantic similarity.

Linguistic acceptability (LA) attracts the attention of the research community due to its many uses, such as testing the grammatical knowledge of language models and filtering implausible texts with acceptability classifiers.However, the application scope of LA in languages other than English is limited due to the lack of high-quality resources.To this end, we introduce the Russian Corpus of Linguistic Acceptability (RuCoLA), built from the ground up under the well-established binary LA approach. RuCoLA consists of 9.8k in-domain sentences from linguistic publications and 3.6k out-of-domain sentences produced by generative models. The out-of-domain set is created to facilitate the practical use of acceptability for improving language generation.Our paper describes the data collection protocol and presents a fine-grained analysis of acceptability classification experiments with a range of baseline approaches.In particular, we demonstrate that the most widely used language models still fall behind humans by a large margin, especially when detecting morphological and semantic errors. We release RuCoLA, the code of experiments, and a public leaderboard to assess the linguistic competence of language models for Russian.

The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP. However, the ability of the attention heads to judge the grammatical acceptability of a sentence has been underexplored. This paper approaches the paradigm of acceptability judgments with topological data analysis (TDA), showing that the geometric properties of the attention graph can be efficiently exploited for two standard practices in linguistics: binary judgments and linguistic minimal pairs. Topological features enhance the BERT-based acceptability classifier scores by 8%-24% on CoLA in three languages (English, Italian, and Swedish). By revealing the topological discrepancy between attention maps of minimal pairs, we achieve the human-level performance on the BLiMP benchmark, outperforming nine statistical and Transformer LM baselines. At the same time, TDA provides the foundation for analyzing the linguistic functions of attention heads and interpreting the correspondence between the graph features and grammatical phenomena. We publicly release the code and other materials used in the experiments.

Recent advances in zero-shot and few-shot learning have shown promise for a scope of research and practical purposes. However, this fast-growing area lacks standardized evaluation suites for non-English languages, hindering progress outside the Anglo-centric paradigm. To address this line of research, we propose TAPE (Text Attack and Perturbation Evaluation), a novel benchmark that includes six more complex NLU tasks for Russian, covering multi-hop reasoning, ethical concepts, logic and commonsense knowledge. The TAPE’s design focuses on systematic zero-shot and few-shot NLU evaluation: (i) linguistic-oriented adversarial attacks and perturbations for analyzing robustness, and (ii) subpopulations for nuanced interpretation. The detailed analysis of testing the autoregressive baselines indicates that simple spelling-based perturbations affect the performance the most, while paraphrasing the input has a more negligible effect. At the same time, the results demonstrate a significant gap between the neural and human baselines for most tasks. We publicly release TAPE (https://tape-benchmark.com) to foster research on robust LMs that can generalize to new tasks when little to no supervision is available.

Code-switching (CS) is a phenomenon of mixing words and phrases from multiple languages within a single sentence or conversation. The ever-growing amount of CS communication among multilingual speakers in social media has highlighted the need to adapt existing NLP products for CS speakers and lead to a rising interest in solving CS NLP tasks. A large number of contemporary approaches use synthetic CS data for training. As previous work has shown the positive effect of pretraining on high-quality CS data, the task of evaluating synthetic CS becomes crucial. In this paper, we address the task of evaluating synthetic CS in two settings. In supervised setting, we apply Hinglish finetuned models to solve the quality rating prediction task of HinglishEval competition and establish a new SOTA. In unsupervised setting, we employ the method of acceptability measures with the same models. We find that in both settings, models finetuned on CS data consistently outperform their original counterparts.

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.

This paper presents the two submissions of NamedEntityRangers Team to the MultiCoNER Shared Task, hosted at SemEval-2022. We evaluate two state-of-the-art approaches, of which both utilize pre-trained multi-lingual language models differently. The first approach follows the token classification schema, in which each token is assigned with a tag. The second approach follows a recent template-free paradigm, in which an encoder-decoder model translates the input sequence of words to a special output, encoding named entities with predefined labels. We utilize RemBERT and mT5 as backbone models for these two approaches, respectively. Our results show that the oldie but goodie token classification outperforms the template-free method by a wide margin. Our code is available at: https://github.com/Abiks/MultiCoNER.

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. These findings contradict the common understanding of how the models encode hierarchical and structural information and even question if the word order is modeled with position embeddings. To this end, this paper proposes nine probing datasets organized by the type of controllable text perturbation for three Indo-European languages with a varying degree of word order flexibility: English, Swedish and Russian. Based on the probing analysis of the M-BERT and M-BART models, we report that the syntactic sensitivity depends on the language and model pre-training objectives. We also find that the sensitivity grows across layers together with the increase of the perturbation granularity. Last but not least, we show that the models barely use the positional information to induce syntactic trees from their intermediate self-attention and contextualized representations.

In this paper, we present NEREL, a Russian dataset for named entity recognition and relation extraction. NEREL is significantly larger than existing Russian datasets: to date it contains 56K annotated named entities and 39K annotated relations. Its important difference from previous datasets is annotation of nested named entities, as well as relations within nested entities and at the discourse level. NEREL can facilitate development of novel models that can extract relations between nested named entities, as well as relations on both sentence and document levels. NEREL also contains the annotation of events involving named entities and their roles in the events. The NEREL collection is available via https://github.com/nerel-ds/NEREL.

Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging task. We conduct an extensive empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework and find the best combinations for different types of models. Besides, we also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance and reduces obstacles for applying deep active learning in practice.

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.

Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such datasets is time- and labor-consuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. 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 one-shot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the intrinsic properties of two-generation approaches. The attributes of the generated data are close to original test sets, collected via crowd-sourcing.

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.

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. Despite the prominent performance of existing methods for artificial text detection, they still lack interpretability and robustness towards unseen models. To this end, we propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) which is currently understudied in the field of NLP. We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties. The results demonstrate that TDA is a promising line with respect to NLP tasks, specifically the ones that incorporate surface and structural information.

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. However, prior research in the field is mainly devoted to English, and little is known regarding other languages. To this end, we introduce RuSentEval, an enhanced set of 14 probing tasks for Russian, including ones that have not been explored yet. We apply a combination of complementary probing methods to explore the distribution of various linguistic properties in five multilingual transformers for two typologically contrasting languages – Russian and English. Our results provide intriguing findings that contradict the common understanding of how linguistic knowledge is represented, and demonstrate that some properties are learned in a similar manner despite the language differences.

The existing dialogue summarization corpora are significantly extractive. We introduce a methodology for dataset extractiveness evaluation and present a new low-extractive corpus of movie dialogues for abstractive text summarization along with baseline evaluation. The corpus contains 153k dialogues and consists of three parts: 1) automatically aligned subtitles, 2) automatically aligned scenes from scripts, and 3) manually aligned scenes from scripts. We also present an alignment algorithm which we use to construct the corpus.

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 words. In-depth processing of noun compounds requires not only splitting them into smaller components (or even roots) but also the identification of instances that should remain unsplitted as they are of idiomatic nature. We develop a two-fold deep learning-based approach of noun compound splitting and idiomatic compound detection for the German language that we train using a newly collected corpus of annotated German compounds. Our neural noun compound splitter operates on a sub-word level and outperforms the current state of the art by about 5%

Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge representations motivate the development of completely unsupervised and knowledge-free approaches to word sense disambiguation (WSD). They are particularly useful for under-resourced languages which do not have any resources for building either supervised and/or knowledge-based models. In this paper, we present a method that takes as input a standard pre-trained word embedding model and induces a fully-fledged word sense inventory, which can be used for disambiguation in context. 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. Models and system are available online.

In this paper, we introduce an advanced Russian general language understanding evaluation benchmark – Russian SuperGLUE. Recent advances in the field of universal language models and transformers require the development of a methodology for their broad diagnostics and testing for general intellectual skills - detection of natural language inference, commonsense reasoning, ability to perform simple logical operations regardless of text subject or lexicon. For the first time, a benchmark of nine tasks, collected and organized analogically to the SuperGLUE methodology, was developed from scratch for the Russian language. We also provide baselines, human level evaluation, open-source framework for evaluating models, and an overall leaderboard of transformer models for the Russian language. Besides, we present the first results of comparing multilingual models in the translated diagnostic test set and offer the first steps to further expanding or assessing State-of-the-art models independently of language.

This paper presents the first gold-standard resource for Russian annotated with compositionality information of noun compounds. The compound phrases are collected from the Universal Dependency treebanks according to part of speech patterns, such as ADJ+NOUN or NOUN+NOUN, using the gold-standard annotations. Each compound phrase is annotated by two experts and a moderator according to the following schema: the phrase can be either compositional, non-compositional, or ambiguous (i.e., depending on the context it can be interpreted both as compositional or non-compositional). We conduct an experimental evaluation of models and methods for predicting compositionality of noun compounds in unsupervised and supervised setups. We show that methods from previous work evaluated on the proposed Russian-language resource achieve the performance comparable with results on English corpora.

In this paper we tackle multilingual named entity recognition task. We use the BERT Language Model as embeddings with bidirectional recurrent network, attention, and NCRF on the top. We apply multilingual BERT only as embedder without any fine-tuning. We test out model on the dataset of the BSNLP shared task, which consists of texts in Bulgarian, Czech, Polish and Russian languages.