arXiv subjects

Steven Skiena

Publications and source records attributed to Steven Skiena.

At least 19 recordsLinked to original sources

arXiv2026

Births are difficult to predict even with rich survey and full-population register data

Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine one outcome - having a child within three years - through a near-ideal setting for prediction: a data challenge where 147 researchers predicted births for Dutch residents aged 18-45, using survey data and full-population registers. Methods ranged from logistic regression to a large language model and transformers. Predictions were moderately accurate (best F1: register 0.59, survey 0.76); advanced models did not outperform classical ones; and the larger registers did not beat the survey. Simulating the stochastic biology of conception and pregnancy, we estimated a predictive ceiling (survey F1 ~ 0.86-0.94, register 0.88-0.96). Observed performance falls short of this ceiling, implicating imperfect data, methods, and unmodelled chance, while the ceiling itself shows that chance in reproduction alone sets a non-trivial limit on predicting individual lives.

cs.LG↗

arXiv2026

Embeddings of Nation-Level Social Networks

Full nation-scale social networks are now emerging from countries such as the Netherlands and Denmark, but these networks present challenging technical issues in working with large, multiplex, time-dependent networks. We report on our experiences in producing dynamic node embeddings of the population network of the Netherlands. We present (a) a layer-sensitive random walk strategy which improves on traditional flattening methods for multiplex networks, (b) a temporal alignment strategy that brings annual networks into the same embedding space, without leaking information to future years, and (c) the use of Fibonacci spirals and embedding whitening techniques for more balanced and effective partitioning. We demonstrate the effectiveness of these techniques in building embedding-based models for 13 downstream tasks.

cs.SI↗

arXiv2026

Reducing Tokenization Premiums for Low-Resource Languages

Relative to English, low-resource languages suffer from substantial tokenization premiums in modern LMs, meaning that it generally requires several times as many tokens to encode a sentence in a low-resource language than to encode the analogous sentence in English. This tokenization premium results in increased API and energy costs and reduced effective context windows for these languages. In this paper we analyze the tokenizers of ten popular LMs to better understand their designs and per-language tokenization premiums. We also propose a mechanism to reduce tokenization premiums in pre-trained models, by post-hoc additions to the token vocabulary that coalesce multi-token characters into single tokens. We apply this methodology to 12 low-resource languages, demonstrating that the original and compressed inputs often have similar last hidden states when run through the Llama 3.2 1B model.

cs.CL↗

arXiv2025

Evaluating Language Translation Models by Playing Telephone

Our ability to efficiently and accurately evaluate the quality of machine translation systems has been outrun by the effectiveness of current language models--which limits the potential for further improving these models on more challenging tasks like long-form and literary translation. We propose an unsupervised method to generate training data for translation evaluation over different document lengths and application domains by repeated rounds of translation between source and target languages. We evaluate evaluation systems trained on texts mechanically generated using both model rotation and language translation approaches, demonstrating improved performance over a popular translation evaluation system (xCOMET) on two different tasks: (i) scoring the quality of a given translation against a human reference and (ii) selecting which of two translations is generationally closer to an original source document.

cs.CL↗

arXiv2025

Gatsby Without the 'E': Crafting Lipograms with LLMs

Lipograms are a unique form of constrained writing where all occurrences of a particular letter are excluded from the text, typified by the novel Gadsby, which daringly avoids all usage of the letter 'e'. In this study, we explore the power of modern large language models (LLMs) by transforming the novel F. Scott Fitzgerald's The Great Gatsby into a fully 'e'-less text. We experimented with a range of techniques, from baseline methods like synonym replacement to sophisticated generative models enhanced with beam search and named entity analysis. We show that excluding up to 3.6% of the most common letters (up to the letter 'u') had minimal impact on the text's meaning, although translation fidelity rapidly and predictably decays with stronger lipogram constraints. Our work highlights the surprising flexibility of English under strict constraints, revealing just how adaptable and creative language can be.

cs.CL↗

arXiv2024

Fast and Robust Contextual Node Representation Learning over Dynamic Graphs

Real-world graphs grow rapidly with edge and vertex insertions over time, motivating the problem of efficiently maintaining robust node representation over evolving graphs. Recent efficient GNNs are designed to decouple recursive message passing from the learning process, and favor Personalized PageRank (PPR) as the underlying feature propagation mechanism. However, most PPR-based GNNs are designed for static graphs, and efficient PPR maintenance remains as an open problem. Further, there is surprisingly little theoretical justification for the choice of PPR, despite its impressive empirical performance. In this paper, we are inspired by the recent PPR formulation as an explicit $\ell_1$-regularized optimization problem and propose a unified dynamic graph learning framework based on sparse node-wise attention. We also present a set of desired properties to justify the choice of PPR in STOA GNNs, and serves as the guideline for future node attention designs. Meanwhile, we take advantage of the PPR-equivalent optimization formulation and employ the proximal gradient method (ISTA) to improve the efficiency of PPR-based GNNs upto 6 times. Finally, we instantiate a simple-yet-effective model (\textsc{GoPPE}) with robust positional encodings by maximizing PPR previously used as attention. The model performs comparably to or better than the STOA baselines and greatly outperforms when the initial node attributes are noisy during graph evolution, demonstrating the effectiveness and robustness of \textsc{GoPPE}.

cs.LG↗

arXiv2024

The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysis

Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the notion of persistent homology from topological data analysis (TDA) to measure the distances between language pairs from the shape of their unlabeled embeddings. These distances quantify the degree of non-isometry of the embeddings. To distinguish whether these differences are random training errors or capture real information about the languages, we use the computed distance matrices to construct language phylogenetic trees over 81 Indo-European languages. Careful evaluation shows that our reconstructed trees exhibit strong and statistically-significant similarities to the reference.

cs.CL↗

arXiv2023

Word Definitions from Large Language Models

Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratory study of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts. Specifically, we compare definitions from three published dictionaries to those generated from variants of ChatGPT. We show that (i) definitions from different traditional dictionaries exhibit more surface form similarity than do model-generated definitions, (ii) that the ChatGPT definitions are highly accurate, comparable to traditional dictionaries, and (iii) ChatGPT-based embedding definitions retain their accuracy even on low frequency words, much better than GloVE and FastText word embeddings.

cs.CL↗

arXiv2023

GNAT: A General Narrative Alignment Tool

Algorithmic sequence alignment identifies similar segments shared between pairs of documents, and is fundamental to many NLP tasks. But it is difficult to recognize similarities between distant versions of narratives such as translations and retellings, particularly for summaries and abridgements which are much shorter than the original novels. We develop a general approach to narrative alignment coupling the Smith-Waterman algorithm from bioinformatics with modern text similarity metrics. We show that the background of alignment scores fits a Gumbel distribution, enabling us to define rigorous p-values on the significance of any alignment. We apply and evaluate our general narrative alignment tool (GNAT) on four distinct problem domains differing greatly in both the relative and absolute length of documents, namely summary-to-book alignment, translated book alignment, short story alignment, and plagiarism detection -- demonstrating the power and performance of our methods.

cs.CL↗

arXiv2023

Analyzing Film Adaptation through Narrative Alignment

Novels are often adapted into feature films, but the differences between the two media usually require dropping sections of the source text from the movie script. Here we study this screen adaptation process by constructing narrative alignments using the Smith-Waterman local alignment algorithm coupled with SBERT embedding distance to quantify text similarity between scenes and book units. We use these alignments to perform an automated analysis of 40 adaptations, revealing insights into the screenwriting process concerning (i) faithfulness of adaptation, (ii) importance of dialog, (iii) preservation of narrative order, and (iv) gender representation issues reflective of the Bechdel test.

cs.CL↗

arXiv2023

STONYBOOK: A System and Resource for Large-Scale Analysis of Novels

Books have historically been the primary mechanism through which narratives are transmitted. We have developed a collection of resources for the large-scale analysis of novels, including: (1) an open source end-to-end NLP analysis pipeline for the annotation of novels into a standard XML format, (2) a collection of 49,207 distinct cleaned and annotated novels, and (3) a database with an associated web interface for the large-scale aggregate analysis of these literary works. We describe the major functionalities provided in the annotation system along with their utilities. We present samples of analysis artifacts from our website, such as visualizations of character occurrences and interactions, similar books, representative vocabulary, part of speech statistics, and readability metrics. We also describe the use of the annotated format in qualitative and quantitative analysis across large corpora of novels.

cs.CL↗

arXiv2023

Prosody Analysis of Audiobooks

Recent advances in text-to-speech have made it possible to generate natural-sounding audio from text. However, audiobook narrations involve dramatic vocalizations and intonations by the reader, with greater reliance on emotions, dialogues, and descriptions in the narrative. Using our dataset of 93 aligned book-audiobook pairs, we present improved models for prosody prediction properties (pitch, volume, and rate of speech) from narrative text using language modeling. Our predicted prosody attributes correlate much better with human audiobook readings than results from a state-of-the-art commercial TTS system: our predicted pitch shows a higher correlation with human reading for 22 out of the 24 books, while our predicted volume attribute proves more similar to human reading for 23 out of the 24 books. Finally, we present a human evaluation study to quantify the extent that people prefer prosody-enhanced audiobook readings over commercial text-to-speech systems.

cs.SD↗

arXiv2023

Accelerating Personalized PageRank Vector Computation

Personalized PageRank Vectors are widely used as fundamental graph-learning tools for detecting anomalous spammers, learning graph embeddings, and training graph neural networks. The well-known local FwdPush algorithm approximates PPVs and has a sublinear rate of $O\big(\frac{1}{\alpha\epsilon}\big)$. A recent study found that when high precision is required, FwdPush is similar to the power iteration method, and its run time is pessimistically bounded by $O\big(\frac{m}{\alpha} \log\frac{1}{\epsilon}\big)$. This paper looks closely at calculating PPVs for both directed and undirected graphs. By leveraging the linear invariant property, we show that FwdPush is a variant of Gauss-Seidel and propose a Successive Over-Relaxation based method, FwdPushSOR to speed it up by slightly modifying FwdPush. Additionally, we prove FwdPush has local linear convergence rate $O\big(\tfrac{\text{vol}(S)}{\alpha} \log\tfrac{1}{\epsilon}\big)$ enjoying advantages of two existing bounds. We also design a new local heuristic push method that reduces the number of operations by 10-50 percent compared to FwdPush. For undirected graphs, we propose two momentum-based acceleration methods that can be expressed as one-line updates and speed up non-acceleration methods by$\mathcal{O}\big(\tfrac{1}{\sqrt{\alpha}}\big)$. Our experiments on six real-world graph datasets confirm the efficiency of FwdPushSOR and the acceleration methods for directed and undirected graphs, respectively.

cs.DS↗

arXiv2023

Does it pay to optimize AUC?

The Area Under the ROC Curve (AUC) is an important model metric for evaluating binary classifiers, and many algorithms have been proposed to optimize AUC approximately. It raises the question of whether the generally insignificant gains observed by previous studies are due to inherent limitations of the metric or the inadequate quality of optimization. To better understand the value of optimizing for AUC, we present an efficient algorithm, namely AUC-opt, to find the provably optimal AUC linear classifier in $\mathbb{R}^2$, which runs in $\mathcal{O}(n_+ n_- \log (n_+ n_-))$ where $n_+$ and $n_-$ are the number of positive and negative samples respectively. Furthermore, it can be naturally extended to $\mathbb{R}^d$ in $\mathcal{O}((n_+n_-)^{d-1}\log (n_+n_-))$ by calling AUC-opt in lower-dimensional spaces recursively. We prove the problem is NP-complete when $d$ is not fixed, reducing from the \textit{open hemisphere problem}. Experiments show that compared with other methods, AUC-opt achieves statistically significant improvements on between 17 to 40 in $\mathbb{R}^2$ and between 4 to 42 in $\mathbb{R}^3$ of 50 t-SNE training datasets. However, generally the gain proves insignificant on most testing datasets compared to the best standard classifiers. Similar observations are found for nonlinear AUC methods under real-world datasets.

cs.CG↗

arXiv2022

Provable Fairness for Neural Network Models using Formal Verification

Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from training data. Typical approaches to achieve fairness revolve around efforts to clean or curate training data, with post-hoc statistical evaluation of the fairness of the model on evaluation data. In contrast, we propose techniques to \emph{prove} fairness using recently developed formal methods that verify properties of neural network models.Beyond the strength of guarantee implied by a formal proof, our methods have the advantage that we do not need explicit training or evaluation data (which is often proprietary) in order to analyze a given trained model. In experiments on two familiar datasets in the fairness literature (COMPAS and ADULTS), we show that through proper training, we can reduce unfairness by an average of 65.4\% at a cost of less than 1\% in AUC score.

cs.LG↗

arXiv2022

Hierarchies over Vector Space: Orienting Word and Graph Embeddings

Word and graph embeddings are widely used in deep learning applications. We present a data structure that captures inherent hierarchical properties from an unordered flat embedding space, particularly a sense of direction between pairs of entities. Inspired by the notion of \textit{distributional generality}, our algorithm constructs an arborescence (a directed rooted tree) by inserting nodes in descending order of entity power (e.g., word frequency), pointing each entity to the closest more powerful node as its parent. We evaluate the performance of the resulting tree structures on three tasks: hypernym relation discovery, least-common-ancestor (LCA) discovery among words, and Wikipedia page link recovery. We achieve average 8.98\% and 2.70\% for hypernym and LCA discovery across five languages and 62.76\% accuracy on directed Wiki-page link recovery, with both substantially above baselines. Finally, we investigate the effect of insertion order, the power/similarity trade-off and various power sources to optimize parent selection.

cs.CL↗

arXiv2022

Subset Node Anomaly Tracking over Large Dynamic Graphs

Tracking a targeted subset of nodes in an evolving graph is important for many real-world applications. Existing methods typically focus on identifying anomalous edges or finding anomaly graph snapshots in a stream way. However, edge-oriented methods cannot quantify how individual nodes change over time while others need to maintain representations of the whole graph all time, thus computationally inefficient. This paper proposes \textsc{DynAnom}, an efficient framework to quantify the changes and localize per-node anomalies over large dynamic weighted-graphs. Thanks to recent advances in dynamic representation learning based on Personalized PageRank, \textsc{DynAnom} is 1) \textit{efficient}: the time complexity is linear to the number of edge events and independent on node size of the input graph; 2) \textit{effective}: \textsc{DynAnom} can successfully track topological changes reflecting real-world anomaly; 3) \textit{flexible}: different type of anomaly score functions can be defined for various applications. Experiments demonstrate these properties on both benchmark graph datasets and a new large real-world dynamic graph. Specifically, an instantiation method based on \textsc{DynAnom} achieves the accuracy of 0.5425 compared with 0.2790, the best baseline, on the task of node-level anomaly localization while running 2.3 times faster than the baseline. We present a real-world case study and further demonstrate the usability of \textsc{DynAnom} for anomaly discovery over large-scale graphs.

cs.SI↗

arXiv2022

Time Window Frechet and Metric-Based Edit Distance for Passively Collected Trajectories

The advances of modern localization techniques and the wide spread of mobile devices have provided us great opportunities to collect and mine human mobility trajectories. In this work, we focus on passively collected trajectories, which are sequences of time-stamped locations that mobile entities visit. To analyse such trajectories, a crucial part is a measure of similarity between two trajectories. We propose the time-window Frechet distance, which enforces the maximum temporal separation between points of two trajectories that can be paired in the calculation of the Frechet distance, and the metric-based edit distance which incorporates the underlying metric in the computation of the insertion and deletion costs. Using these measures, we can cluster trajectories to infer group motion patterns. We look at the $k$-gather problem which requires each cluster to have at least $k$ trajectories. We prove that k-gather remains NP-hard under edit distance, metric-based edit distance and Jaccard distance. Finally, we improve over previous results on discrete Frechet distance and show that there is no strongly sub-quadratic time with approximation factor less than $1.61$ in two dimensional setting unless SETH fails.

cs.CG↗