arXiv subjects

Petr Sojka

Publications and source records attributed to Petr Sojka.

At least 19 recordsLinked to original sources

arXiv2026

The Art of Hierarchical Competing Patterns: Gaussian Process Optimization of Hyphenation

Hyphenation patterns remain a compact and widely deployed solution for word breaking in typesetting systems, text processors, and web rendering engines, but their generation still depends on manually tuned patgen program parameter profiles. We formulate patgen profile selection as a black-box hyperparameter optimization problem and evaluate Gaussian-process Bayesian optimization for this task. The search objective combines a precision-oriented F_{1/7}-score with an explicit trie size-accuracy trade-off using a normalized trie-size penalty. We evaluate the method on 17 hyphenated word-list datasets covering 14 languages and multiple scripts. Against two strong hand-tuned profiles regenerated from the same 8/10 training split and evaluated on the same 1/10 held-out test split, the GP-optimized profiles improve F_{1/7} on 16 of 17 datasets and reduce trie size on all 17. The median optimized/baseline trie ratio is 0.407. A dataset-level sign test gives p = 1.37e-4; a separate budget-matched comparison on five representative datasets shows that systematic search is competitive and usually improves over the best hand-tuned profile under the fixed comparison objective. The results show that model-based optimization can make pattern generation more reproducible and less dependent on expert trial-and-error while keeping the accuracy-compactness trade-off explicit.

cs.CL↗

arXiv2025

Negation: A Pink Elephant in the Large Language Models' Room?

Negations are key to determining sentence meaning, making them essential for logical reasoning. Despite their importance, negations pose a substantial challenge for large language models (LLMs) and remain underexplored. We constructed and published two new textual entailment datasets NoFEVER-ML and NoSNLI-ML in four languages (English, Czech, German, and Ukrainian) with examples differing in negation. It allows investigation of the root causes of the negation problem and its exemplification: how popular LLM model properties and language impact their inability to handle negation correctly. Contrary to previous work, we show that increasing the model size may improve the models' ability to handle negations. Furthermore, we find that both the models' reasoning accuracy and robustness to negation are language-dependent and that the length and explicitness of the premise have an impact on robustness. There is better accuracy in projective language with fixed order, such as English, than in non-projective ones, such as German or Czech. Our entailment datasets pave the way to further research for explanation and exemplification of the negation problem, minimization of LLM hallucinations, and improvement of LLM reasoning in multilingual settings.

cs.CL↗

arXiv2024

The impact of motor and non-motor symptoms fluctuations on health-related quality of life in people with functional motor disorder

Objective: To assess the effect of overall, between- and within-day subjectively rated fluctuations in motor and non-motor symptoms in people with functional motor disorder (FMD) on the health-related quality of life (HRQoL). Background: FMD is a complex condition characterized by fluctuating motor and non-motor symptoms that may negatively impact HRQoL. Methods: Seventy-seven patients (54 females, mean age 45.4 (SD 10.4) years) with a clinically established diagnosis of FMD, including weakness, completed symptom diaries, rating the severity of motor and non-motor symptoms (i.e., pain, fatigue, mood, cognitive difficulties) on a 10-point numerical scale three times daily for seven consecutive days. HRQoL was assessed using the SF-36 questionnaire. For the analysis, fluctuation magnitude was defined in terms of the variability in self-reported symptom scores. Results: The mental component of SF-36 was jointly predicted by the overall severity scores (t(74) = -3.61, P < 0.001) and overall general fluctuations (t(74) = -2.98, P = 0.004). The physical SF-36 was found to be related only to the overall symptom severity scores (t(74) = -7.09, P < 0.001), but not to the overall fluctuations. The assessment of the impact of different components showed that the mental component of SF-36 was significantly influenced by the combined effect of average fatigue (t(73) = -3.86, P < 0.001), between-day cognitive symptoms fluctuations (t(73) = -3.22, P = 0.002), and within-day mood fluctuations (t(73) = -2.48, P = 0.015). Conclusions: This study demonstrated the impact of self-reported symptom fluctuations across multiple motor and non-motor domains on mental but not physical HRQoL in FMD and highlighted the importance of assessing and managing fluctuations in clinical practice.

q-bio.NC↗

arXiv2024

Concept-aware Data Construction Improves In-context Learning of Language Models

Many recent language models (LMs) are capable of in-context learning (ICL), manifested in the LMs' ability to perform a new task solely from natural-language instruction. Previous work curating in-context learners assumes that ICL emerges from a vast over-parametrization or the scale of multi-task training. However, recent theoretical work attributes the ICL ability to concept-dependent training data and creates functional in-context learners even in small-scale, synthetic settings. In this work, we practically explore this newly identified axis of ICL quality. We propose Concept-aware Training (CoAT), a framework for constructing training scenarios that make it beneficial for the LM to learn to utilize the analogical reasoning concepts from demonstrations. We find that by using CoAT, pre-trained transformers can learn to better utilise new latent concepts from demonstrations and that such ability makes ICL more robust to the functional deficiencies of the previous models. Finally, we show that concept-aware in-context learning is more effective for a majority of new tasks when compared to traditional instruction tuning, resulting in a performance comparable to the previous in-context learners using magnitudes of more training data.

cs.CL↗

arXiv2023

Soft Alignment Objectives for Robust Adaptation of Language Generation

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to generalize to other domains, making the open-ended deployments of the adapted models prone to errors. This work introduces novel training objectives built upon a semantic similarity of the predicted tokens to the reference. Our results show that (1) avoiding the common assumption of a single correct prediction by constructing the training target from tokens' semantic similarity can mitigate catastrophic forgetting during domain adaptation, while (2) preserving the quality of the adaptation, (3) with negligible additions to compute costs. In the broader context, the objectives grounded in a continuous token similarity pioneer the exploration of the middle ground between the efficient but na\"ıve exact-match token-level objectives and expressive but computationally- and resource-intensive sequential objectives.

cs.CL↗

arXiv2023

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models

While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model robustness by evaluating their models on out-of-distribution (OOD) datasets of the same task, but these datasets might share the bias of the training dataset. We propose a simple method for measuring a scale of models' reliance on any identified spurious feature and assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA). We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features, suggesting that biases are shared among different QA datasets. Finally, we evidence this to be the case by measuring that the performance of models trained on different QA datasets relies comparably on the same bias features. We hope these results will motivate future work to refine the reports of LMs' robustness to a level of adversarial samples addressing specific spurious features.

cs.CL↗

arXiv2023

Resources and Few-shot Learners for In-context Learning in Slavic Languages

Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.

cs.CL↗

arXiv2022

Interpretable Gait Recognition by Granger Causality

Which joint interactions in the human gait cycle can be used as biometric characteristics? Most current methods on gait recognition suffer from the lack of interpretability. We propose an interpretable feature representation of gait sequences by the graphical Granger causal inference. Gait sequence of a person in the standardized motion capture format, constituting a set of 3D joint spatial trajectories, is envisaged as a causal system of joints interacting in time. We apply the graphical Granger model (GGM) to obtain the so-called Granger causal graph among joints as a discriminative and visually interpretable representation of a person's gait. We evaluate eleven distance functions in the GGM feature space by established classification and class-separability evaluation metrics. Our experiments indicate that, depending on the metric, the most appropriate distance functions for the GGM are the total norm distance and the Ky-Fan 1-norm distance. Experiments also show that the GGM is able to detect the most discriminative joint interactions and that it outperforms five related interpretable models in correct classification rate and in Davies-Bouldin index. The proposed GGM model can serve as a complementary tool for gait analysis in kinesiology or for gait recognition in video surveillance.

cs.CV↗

arXiv2022

Walker-Independent Features for Gait Recognition from Motion Capture Data

MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach. Yet in some applications such as video surveillance new identities can appear on the fly and labeled data for all encountered people may not always be available. This work introduces the concept of learning walker-independent gait features directly from raw joint coordinates by a modification of the Fisher Linear Discriminant Analysis with Maximum Margin Criterion. Our new approach shows not only that these features can discriminate different people than who they are learned on, but also that the number of learning identities can be much smaller than the number of walkers encountered in the real operation.

cs.CV↗

arXiv2022

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods

As a contribution to reproducible research, this paper presents a framework and a database to improve the development, evaluation and comparison of methods for gait recognition from motion capture (MoCap) data. The evaluation framework provides implementation details and source codes of state-of-the-art human-interpretable geometric features as well as our own approaches where gait features are learned by a modification of Fisher's Linear Discriminant Analysis with the Maximum Margin Criterion, and by a combination of Principal Component Analysis and Linear Discriminant Analysis. It includes a description and source codes of a mechanism for evaluating four class separability coefficients of feature space and four rank-based classifier performance metrics. This framework also contains a tool for learning a custom classifier and for classifying a custom query on a custom gallery. We provide an experimental database along with source codes for its extraction from the general CMU MoCap database.

cs.CV↗

arXiv2022

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data

This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional sub-space where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.

cs.CV↗

arXiv2022

Learning Robust Features for Gait Recognition by Maximum Margin Criterion

In the field of gait recognition from motion capture data, designing human-interpretable gait features is a common practice of many fellow researchers. To refrain from ad-hoc schemes and to find maximally discriminative features we may need to explore beyond the limits of human interpretability. This paper contributes to the state-of-the-art with a machine learning approach for extracting robust gait features directly from raw joint coordinates. The features are learned by a modification of Linear Discriminant Analysis with Maximum Margin Criterion so that the identities are maximally separated and, in combination with an appropriate classifier, used for gait recognition. Experiments on the CMU MoCap database show that this method outperforms eight other relevant methods in terms of the distribution of biometric templates in respective feature spaces expressed in four class separability coefficients. Additional experiments indicate that this method is a leading concept for rank-based classifier systems.

cs.CV↗

arXiv2022

Gait Recognition from Motion Capture Data

Gait recognition from motion capture data, as a pattern classification discipline, can be improved by the use of machine learning. This paper contributes to the state-of-the-art with a statistical approach for extracting robust gait features directly from raw data by a modification of Linear Discriminant Analysis with Maximum Margin Criterion. Experiments on the CMU MoCap database show that the suggested method outperforms thirteen relevant methods based on geometric features and a method to learn the features by a combination of Principal Component Analysis and Linear Discriminant Analysis. The methods are evaluated in terms of the distribution of biometric templates in respective feature spaces expressed in a number of class separability coefficients and classification metrics. Results also indicate a high portability of learned features, that means, we can learn what aspects of walk people generally differ in and extract those as general gait features. Recognizing people without needing group-specific features is convenient as particular people might not always provide annotated learning data. As a contribution to reproducible research, our evaluation framework and database have been made publicly available. This research makes motion capture technology directly applicable for human recognition.

cs.CV↗

arXiv2022

Adaptor: Objective-Centric Adaptation Framework for Language Models

Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multitask training, custom objectives development, dynamic training curricula, or domain adaptation. Adaptor aims to ease reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.

cs.CL↗

arXiv2022

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel qualitative criteria and on language modeling. We show that the positional and constrained positional models contain interpretable information about the grammatical properties of words and outperform other shallow models on language modeling. We also show that our constrained model outperforms the positional model on language modeling and trains twice as fast.

cs.CL↗

arXiv2021

Towards Math-Aware Automated Classification and Similarity Search of Scientific Publications: Methods of Mathematical Content Representations

In this paper, we investigate mathematical content representations suitable for the automated classification of and the similarity search in STEM documents using standard machine learning algorithms: the Latent Dirichlet Allocation (LDA) and the Latent Semantic Indexing (LSI). The methods are evaluated on a subset of arXiv.org papers with the Mathematics Subject Classification (MSC) as a reference classification and using the standard precision/recall/F1-measure metrics. The results give insight into how different math representations may influence the performance of the classification and similarity search tasks in STEM repositories. Non-surprisingly, machine learning methods are able to grab distributional semantics from textual tokens. A proper selection of weighted tokens representing math may improve the quality of the results slightly. A structured math representation that imitates successful text-processing techniques with math is shown to yield better results than flat TeX tokens.

cs.IR↗

arXiv2021

One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages

Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear fastText models is mostly due to their use of subword information. In previous work, the optimization of fastText's subword sizes has not been fully explored, and non-English fastText models were trained using subword sizes optimized for English and German word analogy tasks. In our work, we find the optimal subword sizes on the English, German, Czech, Italian, Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We then propose a simple n-gram coverage model and we show that it predicts better-than-default subword sizes on the Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We show that the optimization of fastText's subword sizes matters and results in a 14% improvement on the Czech word analogy task. We also show that expensive parameter optimization can be replaced by a simple n-gram coverage model that consistently improves the accuracy of fastText models on the word analogy tasks by up to 3% compared to the default subword sizes, and that it is within 1% accuracy of the optimal subword sizes.

cs.CL↗

arXiv2021

Regressive Ensemble for Machine Translation Quality Evaluation

This work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a correlation to expert-based MQM scores of the WMT 2021 Metrics workshop. In both monolingual and zero-shot cross-lingual settings, we show a significant performance improvement over single metrics. In the cross-lingual settings, we also demonstrate that an ensemble approach is well-applicable to unseen languages. Furthermore, we identify a strong reference-free baseline that consistently outperforms the commonly-used BLEU and METEOR measures and significantly improves our ensemble's performance.

cs.CL↗