Issues in training the TreeTagger for Georgian

Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this article, we propose COde assistaNt viA retrieval-augmeNted language model (CONAN), which aims to build a code assistant by mimicking the knowledge-seeking behaviors of humans during coding. Specifically, it consists of a code structure-aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G). CONAN-R pretrains CodeT5 using Code-Documentation Alignment and Masked Entity Prediction tasks to make language models code structure-aware and learn effective representations for code snippets and documentation. Then CONAN-G designs a dual-view code representation mechanism for implementing a retrieval-augmented code generation model. CONAN-G regards the code documentation descriptions as prompts, which help language models better understand the code semantics. Our experiments show that CONAN achieves convincing performance on different code generation tasks and significantly outperforms previous retrieval augmented code generation models. Our further analyses show that CONAN learns tailored representations for both code snippets and documentation by aligning code-documentation data pairs and capturing structural semantics by masking and predicting entities in the code data. Additionally, the retrieved code snippets and documentation provide necessary information from both program language and natural language to assist the code generation process. CONAN can also be used as an assistant for Large Language Models (LLMs), providing LLMs with external knowledge in shorter code document lengths to improve their effectiveness on various code tasks. It shows the ability of CONAN to extract necessary information and help filter out the noise from retrieved code documents.

BackgroundLarge language models (LLMs), such as ChatGPT-4o, Grok 3.0, Gemini Advanced 2.0 Pro, and DeepSeek, have been tested in many medical domains in recent years, ranging from clinical decision support systems to patient information processes and even some intraoperative scenarios. However, despite this widespread use, how LLMs perform as step-by-step guides in environments requiring sensory-motor interaction—such as direct cadaver dissection—has not yet been systematically evaluated. This gap is particularly pronounced in anatomically complex areas with low error tolerance, such as brachial plexus dissection. This study aimed to comparatively analyze the performance of four different large language models (LLMs) in terms of scientific quality, educational value, and readability of their responses to structured questions in a cadaver dissection environment.MethodsA structured question set of 28 items on brachial plexus dissection was created. Four experienced anatomists blindly evaluated the responses from the models using the modified DISCERN scale (mDISCERN) and the Global Quality Score (GQS). Readability was assessed using Flesch Reading Ease Score (FRES), Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook (SMOG), Gunning Fog Index (GFI), and Coleman-Liau Index (CLI). Content validity was tested via the Content Validity Index (CVI), and inter-rater reliability was calculated using Intraclass Correlation Coefficient (ICC) and Cohen’s Kappa.ResultsChatGPT-4o and Grok 3.0 received the highest scores for scientific accuracy and guidance structure (p < 0.01). DeepSeek showed high readability but limited content depth, while Gemini performed moderately across all parameters. Readability metrics were significantly correlated with quality scores.ConclusionThis is one of the first studies to systematically examine how LLM-based systems perform in a training context with sensory challenges such as cadaver dissection. While LLMs cannot replace the ethical and educational value provided by real human donors, they may offer scalable, individualized support in settings with limited mentorship or cadaver availability. Our study not only aims to support anatomy education in resource-limited environments, but also serves as a foundational reference for future AI-assisted cadaveric studies and intraoperative decision-support models in surgical anatomy.

Where there is life, there is conflict. It is the nature of beings to differ and to clash; what matters is how peace is restored. Conflict resolution is solution and essential for emotional and intellectual development too, especially for first-year undergraduates’ diverse cultures. This study examines emerging adults’ conflict resolution beliefs in Nagaland, India, where indigenous values and educational transitions impact interpersonal behaviour. The goal is to evaluate attitudes and demographics. The study follows a descriptive quantitative design and is based on primary data collected from 226 students enrolled in social science and language programs across government and private colleges in Kohima and Dimapur. A modified ASCRA-VS scale was used for data collection via self-administered Google Forms. The sampling method was non-probability purposive, targeting first-year undergraduates. Research showed that 73.5% of students have an average conflict resolution attitude. Female students scored higher on the “role and responsibility” category statistically. Based on family type, residence, or institutional membership, attitudes were similar across groups. The study concludes that while students demonstrate a moderate readiness for constructive conflict management, targeted interventions are needed to further strengthen their competencies. Gender-responsive programs could enhance role-taking skills, and culturally contextual training can promote socio-emotional well-being. This study emphasizes the need for conflict resolution education in college curriculum, especially in tribal and multicultural contexts. Theory and practice in youth development. Emotional intelligence and higher education policy are enhanced by findings. Keywords: Conflict Resolution, Attitude, Undergraduate Students, Nagaland, Tribal Students, Socio-Emotional Learning.

In this paper we investigate the usefulness of morphosyntactic information as well as clustering in modeling Polish for automatic speech recognition. Polish is an inflectional language, thus we investigate the usefulness of an N-gram model based on morphosyntactic features. We present how individual types of features influence the model and which types of features are best suited for building a language model for automatic speech recognition. We compared the results of applying them with a class-based model that is automatically derived from the training corpus. We show that our approach towards clustering performs significantly better than frequently used SRI LM clustering method. However, this difference is apparent only for smaller corpora.

Evaluation of ChatGPT\u2019s performance on emergency medicine board examination questions

In large vocabulary continuous speech recognition (LVCSR) for agglutinative and inflectional languages, we encounter problems due to theoretically infinite full-word lexicon size. Sub-word lexicon units may be utilized to dramatically reduce the out-of-vocabulary rate in test data. One can develop language models based on sub-word units to perform LVCSR. However, it has not always been beneficial to use sub-word lexicon units, since shorter units have higher acoustic confusability among them and language model history is effectively shorter as compared to the history in full-word language models. To reduce the aforementioned problems, we propose using the longest possible sub-word units in our lexicon, namely half-words and full-words only. We also incorporate linguistic rules of half-word combination into our statistical language model. The language constraints are represented with a rule-based WFSM which can be combined with an N-gram language model to yield a better and smaller language model. We study the performance of the proposed system for Turkish LVCSR, when the language constraint takes the form of enforcing vowel harmony between stems and endings. We also introduce novel error-rate metrics that are more appropriate than word-error-rate for agglutinative languages. Using half-words with a bi-gram model yields a significant reduction in word-error-rate as compared to a bi-gram full-word model. In addition, combining a tri-gram half-word language model with the vowel-harmony WFSM improves the accuracy further when rescoring the bi-gram lattices.

Language modeling plays a critical role for automatic speech recognition. Typically, the n-gram language models suffer from the lack of a good representation of historical words and an inability to estimate unseen parameters due to insufficient training data. In this study, we explore the application of latent semantic information (LSI) to language modeling and parameter smoothing. Our approach adopts latent semantic analysis to transform all words and documents into a common semantic space. The word-to-word, word-to-document and document-to-document relations are, accordingly, exploited for language modeling and smoothing. For language modeling, we present a new representation of historical words based on retrieval of the most relevant document. We also develop a novel parameter smoothing method, where the language models of seen and unseen words are estimated by interpolating the k nearest seen words in the training corpus. The interpolation coefficients are determined according to the closeness of words in the semantic space. As shown by experiments, the proposed modeling and smoothing methods can significantly reduce the perplexity of language models with moderate computational cost.

This paper presents the results of a study on modeling the highly inflective Slovenian language. We focus on creating a language model for a large vocabulary speech recognition system. A new data-driven method is proposed for the induction of inflectional morphology into language modeling. The research focus is on data sparsity, which results from the complex morphology of the language. The idea of using subword units is examined. An attempt is made to figure out the segmentation of words into two subword units: stems and endings. No prior knowledge of the language is used. The subword units should fit into the frameworks of the probabilistic language models. A morphologically correct decomposition of words is not being sought, but searching for a decomposition which yields the minimum entropy of the training corpus. This entropy is approximated by using N-gram models. Despite some seemingly over-simplified assumption, the subword models improve the applicability of the language models for a sparse training corpus. The experiments were performed using the VEČER newswire text corpus as a training corpus. The test set was taken from the SNABI speech database, because the final models were evaluated in speech recognition experiments on SNABI speech database. Two different subword-based models are proposed and examined experimentally. The experiments demonstrate that subword-based models, which considerably reduce OOV rate, improve speech recognition WER when compared with standard word-based models, even though they increase test set perplexity. Subword-based models with improved perplexity, but which reduce the OOV rate much less than the previous ones, do not improve speech recognition results.

Contextual language processing plays an important role for the post-processing of speech recognition. The purpose of the contextual language processing is to find the most plausible candidate for each syllable with the maximum likelihood probability. Generally, the performance of the probabilistic model is affected by two major errors, i.e., modeling error and estimation error in training corpus. In this paper, we focus on the problem of estimation error in training corpus. An adaptive learning algorithm is proposed to decrease the influences of variant run-time context domain. It shows which objects are to be adjusted and how to adjust their probabilities by a neural network model. The resulting techniques are greatly simplified and robust. The experimental results demonstrate the effects of the learning algorithm from generic domain to specific domain. In general, these techniques can be easily extended to various language models and corpus-based applications.

Contextual word representations generated by language models learn spurious associations present in the training corpora. Adversaries can exploit these associations to reverse-engineer the private attributes of entities mentioned in the training corpora. These findings have led to efforts towards minimizing the privacy risks of language models. However, existing approaches lack interpretability, compromise on data utility and fail to provide privacy guarantees. Thus, the goal of my doctoral research is to develop interpretable approaches towards privacy preservation of text representations that maximize data utility retention and guarantee privacy. To this end, I aim to study and develop methods to incorporate steganographic modifications within the vector geometry to obfuscate underlying spurious associations and retain the distributional semantic properties learnt during training.

Statistical n-gram language modeling is popular for speech recognition and many other applications. The conventional n-gram suffers from the insufficiency of modeling long-distance language dependencies. This paper presents a novel approach focusing on mining long distance word associations and incorporating these features into language models based on linear interpolation and maximum entropy (ME) principles. We highlight the discovery of the associations of multiple distant words from training corpus. A mining algorithm is exploited to recursively merge the frequent word subsets and efficiently construct the set of association patterns. By combining the features of association patterns into n-gram models, the association pattern n-grams are estimated with a special realization to trigger pair n-gram where only the associations of two distant words are considered. In the experiments on Chinese language modeling, we find that the incorporation of association patterns significantly reduces the perplexities of n-gram models. The incorporation using ME outperforms that using linear interpolation. Association pattern n-gram is superior to trigger pair n-gram. The perplexities are further reduced using more association steps. Further, the proposed association pattern n-grams are not only able to elevate document classification accuracies but also improve speech recognition rates

To improve the accuracy of lip-reading recognition, an emotions and topic-related mixed language model has been researched. On the basis of the key words, the topic is divided by subject words, improved scene training corpus design and parameter estimation methods are used, the scene training corpus of different topics is expressed as the fuzzy subset of the whole scene training corpus, parameter estimated which can be got is also based on the fuzzy training set of different topics. The problem of sparse data which is introduced by less of training corpus in traditional language model has been eased by improved methods, quantitative description about the relationship of scene training corpus and topics has been presented, and full use of the image identification techniques for expression recognition in lipreading recognition area, auxiliary emotional factors language model to carry out lip-reading recognition.

Pretrained language models (PLMs) learn stereotypes held by humans and reflected in text from their training corpora, including gender bias. When PLMs are used for downstream tasks such as picking candidates for a job, people’s lives can be negatively affected by these learned stereotypes. Prior work usually identifies a linear gender subspace and removes gender information by eliminating the subspace. Following this line of work, we propose to use DensRay, an analytical method for obtaining interpretable dense subspaces. We show that DensRay performs on-par with prior approaches, but provide arguments that it is more robust and provide indications that it preserves language model performance better. By applying DensRay to attention heads and layers of BERT we show that gender information is spread across all attention heads and most of the layers. Also we show that DensRay can obtain gender bias scores on both token and sentence levels. Finally, we demonstrate that we can remove bias multilingually, e.g., from Chinese, using only English training data.

Research shows that errors in natural language can be corrected by translating texts to another language and back using language models. We explore to what extent this latent correction capability extends to Automated Program Repair (APR) by investigating Round-Trip Translation (RTT): translating code from one programming language into another programming or natural language and back, using Large Language Models (LLMs). We hypothesize that RTT restores patterns most commonly seen in the LLM’s training corpora through regression toward the mean , replacing infrequent bugs with more frequent, natural , bug-free code. To test this hypothesis, we employ nine LLMs and four common APR benchmarks in Java, and perform a detailed quantitative and qualitative analysis of RTT-generated patches. We find that RTT through English generates plausible patches for 100 of 164 bugs with GPT-4 on the HumanEval-Java benchmark, and 97 are found to be correct in our manual assessment. Moreover, RTT uniquely generates plausible patches for 46 bugs that were missed by LLMs specifically fine-tuned for APR. While this demonstrates the viability of RTT for APR, we also observe limitations, such as a lower overall bug fix rate than the state-of-the-art and diluting the original coding style. We analyze the impact of these limitations and discuss the potential of using RTT as a complementary component in APR frameworks.

Candidate fusion: Integrating language modelling into a sequence-to-sequence handwritten word recognition architecture