1,720,989 research outputs found
Explainable LLM-based evaluation for NLG using error analysis
No full textTraditional metrics for evaluating natural language generation (NLG) often struggle to capture linguistic complexity or align with human judgment. Recently, approaches based on large language models (LLMs) have been proposed to address these limitations. However, many existing approaches rely on proprietary LLMs or lack sufficient explainability. This thesis explores the potential of open-weight LLMs to develop a robust and explainable method for NLG evaluation. We develop a prompt-based evaluation method that applies an ensemble of LLMs to assess the quality of generated texts. This method is then applied to construct a synthetic training dataset that represents a wide range of tasks, evaluation aspects and systems. Using this dataset, we train a specialized evaluator model through distillation, employing Llama 3.1 8B as the backbone. Evaluation on a number of benchmarks demonstrates that our ensemble approach outperforms both the traditional NLG metrics as well as trained neural models and LLM-based methods. Additionally, the fine-tuned evaluator achieves competitive performance, with substantial improvements over the backbone model
Explainable LLM-based evaluation for NLG using error analysis
Full text linkTraditional metrics for evaluating natural language generation (NLG) often struggle to capture linguistic complexity or align with human judgment. Recently, approaches based on large language models (LLMs) have been proposed to address these limitations. However, many existing approaches rely on proprietary LLMs or lack sufficient explainability. This thesis explores the potential of open-weight LLMs to develop a robust and explainable method for NLG evaluation. We develop a prompt-based evaluation method that applies an ensemble of LLMs to assess the quality of generated texts. This method is then applied to construct a synthetic training dataset that represents a wide range of tasks, evaluation aspects and systems. Using this dataset, we train a specialized evaluator model through distillation, employing Llama 3.1 8B as the backbone. Evaluation on a number of benchmarks demonstrates that our ensemble approach outperforms both the traditional NLG metrics as well as trained neural models and LLM-based methods. Additionally, the fine-tuned evaluator achieves competitive performance, with substantial improvements over the backbone model.Tradiční metriky pro evaluaci generování přirozeného jazyka (NLG) často nedokážou adekvátně zachytit komplexitu jazyka a mnohdy se neshodují s lidským hodnocením. V poslední době byly navrženy přístupy založené na velkých jazykových modelech (LLM), které si kladou za cíl tyto nedostatky překonat. Nicméně, většina současných přístupů je založena na uzavřených (closed-source) modelech nebo postrádá dostatečnou interpretovatelnost. Tato práce se zaměřuje na využití otevřených LLM k vytvoření robustní a interpretovatelné metody pro evaluaci NLG, a prezentuje přístup založený na promptech, který využívá ensemble několika LLM. Tuto metodu následně využíváme k vytvoření syntetického trénovacího datasetu, který zahrnuje řadu úloh, evaluačních kritérií a typů systémů. Na tomto datasetu trénujeme specializovaný evaluační model založený na Llama 3.1 8B. Evaluace na různých benchmarcích ukazuje, že náš ensemble přístup překonává jak tradiční metriky NLG, tak i metody založené na neuronových sítích a LLM. Dále, náš trénovaný model dosahuje přesvědčivých výsledků a významně překonává svůj základní model.Ústav formální a aplikované lingvistikyInstitute of Formal and Applied LinguisticsMatematicko-fyzikální fakultaFaculty of Mathematics and Physic
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Tackling the Problem of Class Imbalance in Multi-class Sentiment Classification: An Experimental Study
No full textSentiment classification is an important task which gained extensive attention both in academia and in industry. Many issues related to this task such as handling of negation or of sarcastic utterances were analyzed and accordingly addressed in previous works. However, the issue of class imbalance which often compromises the prediction capabilities of learning algorithms was scarcely studied. In this work, we aim to bridge the gap between imbalanced learning and sentiment analysis. An experimental study including twelve imbalanced learning preprocessing methods, four feature representations, and a dozen of datasets, is carried out in order to analyze the usefulness of imbalanced learning methods for sentiment classification. Moreover, the data difficulty factors — commonly studied in imbalanced learning — are investigated on sentiment corpora to evaluate the impact of class imbalance
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
