Interactive game approach extracts action graphs from specialized text.
problem Action graph extraction from specialized procedural text.
method Interpreting procedural text as game instructions, using a learning agent to simulate and execute the procedure.
result Framework complements existing approaches and enables richer learning.
Let Mod(Sg) denote the mapping class group of the closed orientable surface Sg of genus g≥2, and let f∈Mod(Sg) be of finite order. We give an inductive procedure to construct an explicit hyperbolic structure on Sg that realizes f as an isometry. In other words, this procedure yield…
Proposes CLRS-Text, a new benchmark for evaluating LM reasoning capabilities.
problem Lack of transferable benchmarks for evaluating reasoning capabilities of language models.
method Developed a textual version of the CLRS benchmark, generating diverse algorithmic tasks.
result Demonstrates a novel challenge for the LM reasoning community and validates prior work.
XR-Transformer accelerates XMC by recursively fine-tuning on multi-resolution objectives.
problem Efficiently classifying texts with large label sets.
method Recursive multi-resolution fine-tuning of transformers.
result XR-Transformer achieves 20x faster training time and 54% Precision@1 on Amazon-3M.
The paper addresses causal estimation for text data with apparent overlap violations.
problem Estimating causal effects from text data with unknown confounders and apparent overlap.
method Uses supervised representation learning to create a representation that preserves confounding information while eliminating predictive information, satisfying overlap assumptions.
result Shows how to obtain robust causal estimation in the presence of apparent overlap violations.
The version of Marsden-Ratiu reduction theorem for Nambu-Poisson manifolds by a regular distribution has been studied by Ibaˊn~ez et al. In this paper we show that the reduction is always ensured unless the distribution is zero. Next we extend the more general Falceto-Zambon Poisson reduct…
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
Survey on reproducibility and distortion issues in text clustering and topic modeling.
problem Reproducibility and misleading cluster geometry in unsupervised learning for text categorization.
method Systematic literature review of text clustering and topic modeling from 2011-2022.
result Outliers and initialization issues are significant factors in text clustering and topic modeling.
This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time tmix of a finite reversible ergodic Markov chain at a prescribed confidence level. The interval is computed from a single finite-length sample path from the Markov chain, and does not require t…
Proposes a method to ensure low losses across all subpopulations in large datasets.
problem Standard practice of minimizing average loss fails to guarantee low losses across all subpopulations in heterogeneous datasets.
method Convex procedure that controls worst-case performance over all subpopulations of a given size with finite-sample convergence guarantees.
result Empirically, the worst-case procedure learns models that do well against unseen subpopulations.
Teaches advanced differential topology to master students with minimal background.
problem Teaching complex differential topology concepts to students with limited mathematical background.
method Cut-and-paste procedures, transversality, cobordism rings.
result Topics can be treated with 'bare hands' using simple mathematical tools.
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical…
Training-free method improves text-to-image generation quality.
problem Error accumulation in simultaneous token updates of masked diffusion models.
method Training-free self-correction framework exploiting inductive biases.
result Significantly improved generation quality on text-to-image tasks.
APo-VAE generates text in hyperbolic space for better hierarchical representation.
problem Lack of hierarchical structure in Euclidean embeddings for natural language.
method Adversarial Poincare Variational Autoencoder (APo-VAE) in hyperbolic latent space.
result APo-VAE outperforms Euclidean VAEs in capturing latent language hierarchies.
RecoBERT uses a language model to recommend items from catalogs.
problem Harnessing language models for text-based item recommendations.
method RecoBERT is a BERT-based approach that learns specialized language models for item recommendations without requiring labeled data.
result RecoBERT outperforms other techniques in inferring item similarities from textual catalogs.
This paper proposes an efficient method to train word embeddings for large corpora without synchronization.
problem Training word embeddings for large text corpora is computationally expensive and requires synchronization.
method Partition the input space instead of the vocabulary size, using asynchronous training without parameter synchronization.
result Comparable and up to 45% performance improvement in NLP benchmarks with 1/10 the training time.
ProtoryNet interprets text sequences using prototype trajectories for better understanding.
problem Improving text classification interpretability and accuracy.
method ProtoryNet uses prototype trajectories to interpret text sequences, with prototype pruning for better interpretability.
result ProtoryNet outperforms baseline models and reduces performance gap compared to black-box models.
New algorithm speeds up determinantal point process sampling.
problem Efficiently sampling from determinantal point processes with minimal preprocessing and sampling costs.
method Introducing a Poisson random variable to control subset probabilities, reducing the number of rows to poly(d) for sampling.
result The new algorithm achieves poly(d) sampling time, independent of n, without distorting probabilities.
Detects changes in topic proportions over time in large text datasets.
problem Unsupervised detection of structural changes in topic distributions over time.
method Specialised temporal topic model with changepoint detection, approximate inference using sample splitting and likelihood ratio statistic.
result Automated detection of changepoints in topic proportions, facilitating interpretable results.
In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding"). The approach is particularly well-suited for extracting large nu…
Improved text-to-image alignment using iterative VQA feedback.
problem Misalignment between text prompts and generated images, especially for complex inputs.
method Decompose complex prompts into assertions, evaluate each using VQA, combine scores iteratively.
result Significantly higher correlation with human ratings compared to CLIP, BLIP scores.
The paper examines conditions for commuting conjugates of finite-order mapping classes.
problem Conditions for commuting conjugates of finite-order mapping classes.
method Derived necessary and sufficient conditions for commuting conjugates.
result Conditions for the primitivity of finite-order mapping classes.
Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameter…
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
We describe a simple and efficient procedure for approximating the Lévy measure of a Gamma(α,1) random variable. We use this approximation to derive a finite sum-representation that converges almost surely to Ferguson's representation of the Dirichlet process based on arrivals of a homogeneous Poisson process.…
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new clas…
Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.
problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.
Paper develops an efficient online watermark detection for AI-generated text.
problem Detecting AI-generated text from human-written content efficiently.
method Rao-Blackwellized e-processes for anytime-valid inference in streaming generation.
result The method enables recursive token-level evidence updates without storing full history.
We consider the scenario where the parameters of a probabilistic model are expected to vary over time. We construct a novel prior distribution that promotes sparsity and adapts the strength of correlation between parameters at successive timesteps, based on the data. We derive approximate variational inference procedur…
We establish spectral theorems for random walks on mapping class groups of connected, closed, oriented, hyperbolic surfaces, and on Out(FN). In both cases, we relate the asymptotics of the stretching factor of the diffeomorphism/automorphism obtained at time n of the random walk to the Lyapunov exponent of …
New method improves text classification without labeled target data.
problem Improving text classification under domain shift without labeled target data.
method Diversity-based generalization using multi-head attention with diversity constraints.
result Method matches state-of-the-art performance without labeled target data.
This paper presents a new approach to non-parametric cluster analysis called Adaptive Weights Clustering (AWC). The idea is to identify the clustering structure by checking at different points and for different scales on departure from local homogeneity. The proposed procedure describes the clustering structure in term…
Unified framework for online LLM watermark detection using e-processes.
problem Detecting AI-generated text from human-written content in online settings.
method Unified framework based on e-processes for anytime-valid hypothesis testing on independence.
result Proposed methods achieve competitive performance in watermark detection.
The paper connects hyperbolic Dehn surgery and Higgs bundles to construct model objects in representation varieties.
problem Constructing model objects in representation varieties for Higgs bundles.
method Reviewing hyperbolic Dehn surgery and bending procedures, and applying them to Higgs bundles.
result Explicit examples of model objects in representation varieties are produced.
The starting point of this article is the question "How to retrieve fingerprints of rhythm in written texts?" We address this problem in the case of Brazilian and European Portuguese. These two dialects of Modern Portuguese share the same lexicon and most of the sentences they produce are superficially identical. Yet t…
This research uses deep learning to automatically classify UN resolutions.
problem Manual labeling of UN documents is too time-consuming.
method Utilizes pre-trained deep learning models without traditional training.
result Shows effectiveness in classifying UN resolutions by SDGs.
Improved handwriting recognition for historical documents with minimal labeled data.
problem Challenges in recognizing historical documents, especially lack of text-line annotations.
method Trained a deep CRNN system on 10% labeled data, augmented with crafted multiscale data, and applied model-based normalization.
result Achieved second best result in ICDAR2017 competition on publicly available READ dataset.
SILBO optimizes high-dimensional Bayesian optimization using semi-supervised embedding learning.
problem Bayesian optimization struggles with high-dimensional search spaces.
method SILBO uses semi-supervised dimension reduction to find a low-dimensional space for iterative optimization.
result SILBO outperforms existing methods on high-dimensional Bayesian optimization tasks.
Paper develops a method to compare generative models using KL divergence.
problem Lack of principled uncertainty quantification for generative models.
method Employ Kullback-Leibler divergence to measure generative model distance.
result Effective coverage rates and higher power compared to kernel-based methods.
XL-Editor improves sentence post-editing using XLNet's variable-length insertion probability.
problem Post-editing sentences to refine generated text.
method XL-Editor trains XLNet to estimate variable-length insertion probabilities and apply post-editing operations.
result XL-Editor outperforms XLNet on text insertion and deletion tasks, and achieves significant style transfer improvements.
We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents. The model accommodates a variety of response types. We derive an approximate maximum-likelihood procedure for parameter estimation, which relies on variational methods to handle intractable posterior expectations. Pre…
ScoreGAN uses GANs with IGM to detect bot-generated reviews based on text and scores.
problem Lack of labeled data and bot-generated reviews in fraud review detection.
method ScoreGAN incorporates review text and scores into a GAN framework for data augmentation and detection.
result ScoreGAN outperforms existing methods by 7% and 5% on Yelp and TripAdvisor datasets.
Anonymizing company names in financial news improves trading performance, contrary to initial expectations.
problem Look-ahead and distraction biases in sentiment analysis of financial news.
method Investigated trading strategies based on original and anonymized headlines, comparing performance.
result Anonymized headlines outperform original in-sample, suggesting distraction effect is stronger.
This text is a survey on cross-validation. We define all classical cross-validation procedures, and we study their properties for two different goals: estimating the risk of a given estimator, and selecting the best estimator among a given family. For the risk estimation problem, we compute the bias (which can also be …
Multi-label text classification is a popular machine learning task where each document is assigned with multiple relevant labels. This task is challenging due to high dimensional features and correlated labels. Multi-label text classifiers need to be carefully regularized to prevent the severe over-fitting in the high …
Grapheme ASR improves with G2G model that corrects spelling errors.
problem Rare long-tail words in non-phonemic languages like English.
method Train G2G model on text-to-speech data to rewrite character sequences into phonetically consistent forms.
result Reduces Word Error Rate by 3% to 11% over a strong graphemic baseline.
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
New algorithm samples determinantal point processes with sublinear preprocessing time.
problem Sampling from determinantal point processes efficiently with small expected subset size.
method Proposes an algorithm with sublinear preprocessing and independent sampling cost.
result Achieves sublinear preprocessing time and independent sampling cost.