共找到 20 条结果
Historical Simulation (HS) and its extensions form a popular class of methods for estimating Value-at-Risk for portfolios of financial assets based on historical data. In this note, we seek to unify several ideas and models from throughout the literature into a single modeling framework. By explicitly defining a parametric model form for the asset returns and extracting the realized increments of the driving innovation process from historical data, we are able to reproduce the Historical Simulation, filtered Historical Simulation, and displaced Historical Simulation methods. This shows beyond a doubt that these methods need more underlying assumptions than what is often alluded to.
The growing volume of digitized historical texts requires effective semantic search using text embeddings. However, pre-trained multilingual models face challenges with historical content due to OCR noise and outdated spellings. This study examines multilingual embeddings for cross-lingual semantic search in historical Luxembourgish (LB), a low-resource language. We collect historical Luxembourgish news articles from various periods and use GPT-4o for sentence segmentation and translation, generating 20,000 parallel training sentences per language pair. Additionally, we create a semantic search (Historical LB Bitext Mining) evaluation set and find that existing models perform poorly on cross-lingual search for historical Luxembourgish. Using our historical and additional modern parallel training data, we adapt several multilingual embedding models through contrastive learning or knowledge distillation and increase accuracy significantly for all models. We release our adapted models and historical Luxembourgish-German/French/English bitexts to support further research.
The capabilities of the latest large language models (LLMs) have been extended from pure natural language understanding to complex reasoning tasks. However, current reasoning models often exhibit factual inaccuracies in longer reasoning chains, which poses challenges for historical reasoning and limits the potential of LLMs in complex, knowledge-intensive tasks. Historical studies require not only the accurate presentation of factual information but also the ability to establish cross-temporal correlations and derive coherent conclusions from fragmentary and often ambiguous sources. To address these challenges, we propose Kongzi, a large language model specifically designed for historical analysis. Through the integration of curated, high-quality historical data and a novel fact-reinforcement learning strategy, Kongzi demonstrates strong factual alignment and sophisticated reasoning depth. Extensive experiments on tasks such as historical question answering and narrative generation demonstrate that Kongzi outperforms existing models in both factual accuracy and reasoning depth. By effectively addressing the unique challenges inherent in historical texts, Kongzi sets a new standard
The transcription of historical documents written in Latin in XV and XVI centuries has special challenges as it must maintain the characters and special symbols that have distinct meanings to ensure that historical texts retain their original style and significance. This work proposes a pipeline for the transcription of historical documents preserving these special features. We propose to extend an existing text line recognition method with a layout analysis model. We analyze historical text images using a layout analysis model to extract text lines, which are then processed by an OCR model to generate a fully digitized page. We showed that our pipeline facilitates the processing of the page and produces an efficient result. We evaluated our approach on multiple datasets and demonstrate that the masked autoencoder effectively processes different types of text, including handwritten, printed and multi-language.
This paper introduces foundational resources and models for natural language processing (NLP) of historical Turkish, a domain that has remained underexplored in computational linguistics. We present the first named entity recognition (NER) dataset, HisTR, and the first Universal Dependencies treebank, OTA-BOUN, for a historical form of the Turkish language along with transformer-based models trained using these datasets for named entity recognition, dependency parsing, and part-of-speech tagging tasks. Furthermore, we introduce the Ottoman Text Corpus (OTC), a clean corpus of transliterated historical Turkish texts that spans a wide range of historical periods. Our experimental results demonstrate prominent improvements in the computational analysis of historical Turkish, achieving strong performance on tasks that require understanding of historical linguistic structures -- specifically, 90.29% F1 in named entity recognition, 73.79% LAS for dependency parsing, and 94.98% F1 for part-of-speech tagging. They also highlight existing challenges, such as domain adaptation and language variations between time periods. All the resources and models presented are available at https://hf.co/
We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availability, preventing temporal leakage, designing temporally consistent post-training pipelines, and constructing reliable evaluations. To address these issues, we construct TypewriterCorpus, a 54B-token historical corpus collected from diverse archival and linguistically annotated sources with extensive data cleaning and leakage mitigation procedures. Furthermore, we introduce lexically grounded instructing tuning, a post-training framework that constraints responses to remain directly grounded in historical source documents. Using this framework we construct two historical instruction tuning datasets: History-LIMA and History-SelfInstruct. To evaluate capability and temporal consistency, we introduce History-Event, a benchmark suite for evaluating competence, temporal grounding and data leakage. We release TypewriterLM and all associated resources to support future research on historical language models.
Historical visualizations are a rich resource for visualization research. While taxonomy is commonly used to structure and understand the design space of visualizations, existing taxonomies primarily focus on contemporary visualizations and largely overlook historical visualizations. To address this gap, we describe an empirical method for taxonomy development. We introduce a coding protocol and the VisTaxa system for taxonomy labeling and comparison. We demonstrate using our method to develop a historical visualization taxonomy by coding 400 images of historical visualizations. We analyze the coding result and reflect on the coding process. Our work is an initial step toward a systematic investigation of the design space of historical visualizations.
Historical visualizations are a valuable resource for studying the history of visualization and inspecting the cultural context where they were created. When investigating historical visualizations, it is essential to consider contributions from different cultural frameworks to gain a comprehensive understanding. While there is extensive research on historical visualizations within the European cultural framework, this work shifts the focus to ancient China, a cultural context that remains underexplored by visualization researchers. To this aim, we propose a semi-automatic pipeline to collect, extract, and label historical Chinese visualizations. Through the pipeline, we curate ZuantuSet, a dataset with over 71K visualizations and 108K illustrations. We analyze distinctive design patterns of historical Chinese visualizations and their potential causes within the context of Chinese history and culture. We illustrate potential usage scenarios for this dataset, summarize the unique challenges and solutions associated with collecting historical Chinese visualizations, and outline future research directions.
Digitization of historical records has produced a significant amount of data for analysis and interpretation. A critical challenge is the ability to relate historical information across different archives to allow for the data to be framed in the appropriate historical context. This paper presents a real-world case study on historical information integration and record matching with the goal to improve the historical value of archives containing data in the period 1800 to 1920. The archives contain unique information about Métis and Indigenous people in Canada and interactions with European settlers. The archives contain thousands of records that have increased relevance when relationships and interconnections are discovered. The contribution is a record linking approach suitable for historical archives and an evaluation of its effectiveness. Experimental results demonstrate potential for discovering historical linkage with high precision enabling new historical discoveries.
Historical maps are invaluable sources of information about the past, and scanned historical maps are increasingly accessible in online libraries. To retrieve maps from these large libraries that contain specific places of interest, previous work has applied computer vision techniques to recognize words on historical maps, enabling searches for maps that contain specific place names. However, searching for multiword place names is challenging due to complex layouts of text labels on historical maps. This paper proposes an efficient query method for searching a given multiword place name on historical maps. Using existing methods to recognize words on historical maps, we link single-word text labels into potential multiword phrases by constructing minimum spanning trees. These trees aim to link pairs of text labels that are spatially close and have similar height, angle, and capitalization. We then query these trees for the given multiword place name. We evaluate the proposed method in two experiments: 1) to evaluate the accuracy of the minimum spanning tree approach at linking multiword place names and 2) to evaluate the number and time range of maps retrieved by the query approach
This paper presents a comprehensive analysis of historical data across two popular blockchain networks: Ethereum and Solana. Our study focuses on two key aspects: transaction conflicts and the maximum theoretical parallelism within historical blocks. We aim to quantify the degree of transaction parallelism and assess how effectively it can be exploited by systematically examining block-level characteristics, both within individual blocks and across different historical periods. In particular, this study is the first of its kind to leverage historical transactional workloads to evaluate conflict patterns. By offering a structured approach to analyzing these conflicts, our research provides valuable insights and an empirical basis for developing more efficient parallel execution techniques for smart contracts in the Ethereum and Solana. Our empirical analysis reveals that historical Ethereum blocks frequently achieve high independence, with over 50\% independent transactions in more than 50\% of blocks, while, on average, Solana blocks contain longer conflict chains $\sim$58\%, compared to $\sim$18\% in Ethereum, reflecting fundamentally different parallel execution dynamics.
Linking named entities occurring in text to their corresponding entity in a Knowledge Base (KB) is challenging, especially when dealing with historical texts. In this work, we introduce Musical Heritage named Entities Recognition, Classification and Linking (MHERCL), a novel benchmark consisting of manually annotated sentences extrapolated from historical periodicals of the music domain. MHERCL contains named entities under-represented or absent in the most famous KBs. We experiment with several State-of-the-Art models on the Entity Linking (EL) task and show that MHERCL is a challenging dataset for all of them. We propose a novel unsupervised EL model and a method to extend supervised entity linkers by using Knowledge Graphs (KGs) to tackle the main difficulties posed by historical documents. Our experiments reveal that relying on unsupervised techniques and improving models with logical constraints based on KGs and heuristics to predict NIL entities (entities not represented in the KB of reference) results in better EL performance on historical documents.
Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm, which predicts the future trajectory by using a fixed duration of historical frames. These methods make the predictions independently even at adjacent time steps, which leads to potential instability and temporal inconsistency. As successive time steps have largely overlapping historical frames, their forecasting should have intrinsic correlation, such as overlapping predicted trajectories should be consistent, or be different but share the same motion goal depending on the road situation. Motivated by this, in this work, we introduce HPNet, a novel dynamic trajectory forecasting method. Aiming for stable and accurate trajectory forecasting, our method leverages not only historical frames including maps and agent states, but also historical predictions. Specifically, we newly design a Historical Prediction Attention module to automatically encode the dynamic relationship between successive predictions. Besides, it also extends the attention range beyond the currently visible window benefitting from the use of historical predictions. The pro
Massive-scale historical document collections are crucial for social science research. Despite increasing digitization, these documents typically lack unique cross-document identifiers for individuals mentioned within the texts, as well as individual identifiers from external knowledgebases like Wikipedia/Wikidata. Existing entity disambiguation methods often fall short in accuracy for historical documents, which are replete with individuals not remembered in contemporary knowledgebases. This study makes three key contributions to improve cross-document coreference resolution and disambiguation in historical texts: a massive-scale training dataset replete with hard negatives - that sources over 190 million entity pairs from Wikipedia contexts and disambiguation pages - high-quality evaluation data from hand-labeled historical newswire articles, and trained models evaluated on this historical benchmark. We contrastively train bi-encoder models for coreferencing and disambiguating individuals in historical texts, achieving accurate, scalable performance that identifies out-of-knowledgebase individuals. Our approach significantly surpasses other entity disambiguation models on our his
This paper compares historical annotations by humans and Large Language Models. The findings reveal that both exhibit some cultural bias, but Large Language Models achieve a higher consensus on the interpretation of historical facts from short texts. While humans tend to disagree on the basis of their personal biases, Large Models disagree when they skip information or produce hallucinations. These findings have significant implications for digital humanities, enabling large-scale annotation and quantitative analysis of historical data. This offers new educational and research opportunities to explore historical interpretations from different Language Models, fostering critical thinking about bias.
Our recent approach to the Finkelberg-Kazhdan-Lusztig equivalence theorem centers on the construction of a fiber functor associated with the categories in the equivalence theorem, which in turn explains the underlying algebraic and analytic structure of the corresponding weak Hopf algebra in a new sense. We provide a non-technical and historical overview of the core arguments behind our proof, discuss these structural properties, and its applications to rigidity and unitarizability of braided fusion categories arising from conformal field theory. We conclude proposing some natural directions for future research.
When incorporating historical control data into the analysis of current randomized controlled trial data, it is critical to account for differences between the datasets. When the cause of the difference is an unmeasured factor and adjustment for observed covariates only is insufficient, it is desirable to use a dynamic borrowing method that reduces the impact of heterogeneous historical controls. We propose a nonparametric Bayesian approach for borrowing historical controls that are homogeneous with the current control. Additionally, to emphasize the resolution of conflicts between the historical controls and current control, we introduce a method based on the dependent Dirichlet process mixture. The proposed methods can be implemented using the same procedure, regardless of whether the outcome data comprise aggregated study-level data or individual participant data. We also develop a novel index of similarity between the historical and current control data, based on the posterior distribution of the parameter of interest. We conduct a simulation study and analyze clinical trial examples to evaluate the performance of the proposed methods compared to existing methods. The proposed
Trackers that follow Siamese paradigm utilize similarity matching between template and search region features for tracking. Many methods have been explored to enhance tracking performance by incorporating tracking history to better handle scenarios involving target appearance variations such as deformation and occlusion. However, the utilization of historical information in existing methods is insufficient and incomprehensive, which typically requires repetitive training and introduces a large amount of computation. In this paper, we show that by providing a tracker that follows Siamese paradigm with precise and updated historical information, a significant performance improvement can be achieved with completely unchanged parameters. Based on this, we propose a historical prompt network that uses refined historical foreground masks and historical visual features of the target to provide comprehensive and precise prompts for the tracker. We build a novel tracker called HIPTrack based on the historical prompt network, which achieves considerable performance improvements without the need to retrain the entire model. We conduct experiments on seven datasets and experimental results dem
In recent years, the hope to confirm the existence of dark matter by experimentally detecting it has diminished significantly. After more than 30 years of experimental searches, many of the most promising candidates have since been ruled out, leaving the epistemic and scientific condition of dark matter in a state of suspension. In efforts to improve the epistemic justification for the dark-matter hypothesis, physicists have turned to philosophical arguments and historical narratives. In this paper, I explicate two such strategies -- explanatory unification and historical continuity -- applied in the context of dark matter. I argue that greater care and attention should be invested in the explanatory arguments to increase their strength, and that a survey of primary historical sources in astronomy renders the historical evidence for the continuity of dark matter substantially weaker. The quality and rigor of the philosophical and historical arguments which physicists are constructing could be substantially improved by increasing interdisciplinary practices.
New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic--``Historical Learning: Learning Models with Learning History'', which learns better neural models with the help of their learning history during its optimization, from three detailed aspects: Historical Type (what), Functional Part (where) and Storage Form (how). To our best knowledge, it is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks. The discussions with related topics like recurrent/memory networks, ensemble learning, and reinforcement learning are demonstrated. We also expose future challenges of this topic and encourage the community to pay attention to the think of historical learning principles when designing algorithms. The paper list related to historical learning is available at \url{https://github.com/Martinser/Awesome-Historical-Learning.}