The paper explores how semantic independence can be captured in text embeddings using partial orthogonality.
problem Capturing semantic independence in text embeddings.
method Developed a theory and methods based on partial orthogonality to demonstrate semantic independence.
result Partial orthogonality captures semantic independence in text embeddings.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
problem Improving performance on tasks like semantic parsing and math word problem solving.
method Graph-to-Tree Neural Networks, consisting of a graph encoder and a hierarchical tree decoder.
result Graph2Tree model outperforms or matches state-of-the-art models on neural semantic parsing and math word problem tasks.
Entropy tracking reveals class commitment transitions in diffusion models.
problem Diffusion models lack reliable methods to detect semantic structure transitions.
method Tracking class-conditional entropy of latent variables.
result Entropy isolates noise regimes critical for semantic structure formation.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
MISIM improves code similarity systems with neural learning.
problem Improving accuracy of code semantics similarity systems.
method Context-aware semantics structure and neural code similarity scoring algorithm.
result MISIM achieves 8.08% better accuracy than state-of-the-art systems.
The paper explains how continuous language models can produce discrete, interpretable meanings.
problem Semantic collapse in continuous systems of large language models.
method Formalizing large language models as Continuous State Machines (CSMs) and analyzing the associated transfer operator.
result The leading eigenfunctions of the transfer operator induce a finite number of invariant meaning basins, explaining how continuous computation can produce discrete, interpretable semantics.
Low-dimensional vectors improve semantic understanding of music and language.
problem Noise in shared semantics due to individual brain biases.
method Jointly model multiple brains to learn low-dimensional vector embeddings.
result These embeddings outperform high-dimensional fMRI data in music and language classification.
Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities an…
Study shows mutual information can reward structure learning agents without expert systems.
problem Designing rewards for structure learning agents in natural language environments.
method Revisited Information Theory of unsupervised induction of phrase-structure grammars, using random sets of linguistic samples.
result Empirical evidence that simulated semantic structures can be distinguished from random ones by mutual information among their constituents.
Paper improves short text clustering by integrating semantic relationships into Optimal Transport.
problem Erroneous pseudo-labels caused by neglecting semantic consistency in existing OT methods.
method Designs an instance-level attention mechanism to capture semantic relationships and integrates them into the OT formulation.
result Generates reliable pseudo-labels that improve clustering accuracy.
Paper proposes structured semantic perturbations to improve adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method Manipulates semantic attributes via disentangled latent codes.
result Demonstrates the effectiveness of structured semantic perturbations.
This work benchmarks neural embeddings for link prediction in evolving knowledge graphs.
problem Evaluating the robustness of neural embeddings in changing knowledge graphs.
method Proposes an open-source evaluation pipeline using relation-centric connectivity measures.
result Demonstrates the importance of simulating embedding accuracy for frequently updated knowledge graphs.
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …
Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or word vectors, as the bridge. However, due to the mutually disjoint of training (see…
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with …
Unsupervised scheme ranks sentences in text documents based on semantic importance.
problem Ranking sentences in text documents without labeled data.
method Extracts essential words and phrases, constructs semantic phrase and sentence graphs, applies PageRank, combines scores, and optimizes for topic diversity.
result SSR outperforms individual judges and compares favorably with combined rankings on benchmarks.
New method neutralizes gender bias in word embeddings without losing semantic information.
problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.
The paper explores how AI systems use information geometry to encode semantic structure.
problem How AI systems encode semantic structure into geometric representation spaces.
method Focuses on softmax distributions and develops dual steering method for robust concept manipulation.
result Dual steering optimally modifies target concepts while minimizing off-target changes.
Semantic segmentation was seen as a challenging computer vision problem few years ago. Due to recent advancements in deep learning, relatively accurate solutions are now possible for its use in automated driving. In this paper, the semantic segmentation problem is explored from the perspective of automated driving. Mos…
It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. However, due to the obscured and indescribable black box model of neural networks, it is very difficult to design its architecture, interpret its …
End-to-end learning framework for tree-structured data.
problem Learning models struggle with tree-structured data due to lack of fixed-length vectors.
method Developed a novel framework for generic semantic tree-structured data of arbitrary topology.
result Framework yields comparable performance to standard models with dedicated feature-vectors and outperforms in compositional data.
In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are good at capturing the local structure of a word sequence - both semantic and syn…
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are the theoretical principles governing the ability of neural networks to acquire, or…
SEMASIA provides a large dataset of latent representations for model comparison.
problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.
New framework detects near vs. far out-of-distribution samples for AI safety.
problem Binary OOD detection fails to distinguish between semantically close and distant unknown risks.
method Ternary classification based on Low-Entropy Semantic Manifolds and Semantic Surprise Vector.
result Framework achieves state-of-the-art performance on ternary OOD detection task.
SOM-VQ tokenizes discrete models with semantic structure and navigable topology.
problem Lack of semantic structure in vector quantized representations limits interpretable human control.
method Combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit topology.
result SOM-VQ produces more learnable token sequences and provides an explicit navigable geometry in code space.
The paper measures semantic information production in generative models using information theory.
problem Measuring when semantic decisions are made during generative model training.
method Using an online formula for the optimal Bayesian classifier, the paper estimates conditional entropy and determines time intervals for highest information transfer.
result Semantic information transfer is highest in intermediate stages of diffusion, with different classes making decisions at different times.
SASSL improves self-supervised learning by preserving image structure.
problem Distorted augmented samples in self-supervised learning.
method Neural Style Transfer to decouple semantic and stylistic attributes.
result Boosts ImageNet top-1 accuracy by up to 2 percentage points.
SAVeD detects dataset versions without metadata, improving accuracy and separation.
problem Difficulty in identifying similar versions of structured datasets.
method Contrastive learning with modified SimCLR pipeline, generating and contrasting augmented table views.
result SAVeD achieves higher accuracy and separation scores on unseen tables.
Faster, context-aware topic modeling approach unveiled.
problem Slow and heavy preprocessing in topic modeling.
method Conceptualizes topics as independent axes, decomposes embeddings using ICA.
result 4.5x faster than BERTopic on average, with diverse and coherent topics.
Online voting is an emerging feature in social networks, in which users can express their attitudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content …
Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.
problem Topic modeling weaknesses, including needing known topics, stop words, and custom settings.
method Joint document and word semantic embedding to find topic vectors automatically.
result Top2Vec finds more informative and representative topics than probabilistic models.
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily generalize in this way, e.g. by applying known grammatical rules to novel words.…
The abstract explains how word and relation representations capture semantic meaning.
problem Understanding how word and relation representations capture semantic meaning.
method Theoretical justification and extension of geometric relationships between word embeddings and knowledge graph representations.
result The geometric relationships between word embeddings correspond to semantic relations between words and entities in knowledge graphs.
We present a framework for translating unlabeled images from one domain into analog images in another domain. We employ a progressively growing skip-connected encoder-generator structure and train it with a GAN loss for realistic output, a cycle consistency loss for maintaining same-domain translation identity, and a s…
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
problem Lack of explicit geometric information in 3D semantic segmentation models.
method Introduces GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into existing 3D segmentation pipelines.
result Consistent performance gains across multiple benchmarks, including up to +11.5% mIoU on TS40K with PTV3.
We present a novel method named Latent Semantic Imputation (LSI) to transfer external knowledge into semantic space for enhancing word embedding. The method integrates graph theory to extract the latent manifold structure of the entities in the affinity space and leverages non-negative least squares with standard simpl…
Optimizes contrastive learning with individualized temperatures for better performance on imbalanced datasets.
problem The common practice of using a global temperature parameter ignores the varying semantic similarity across different anchor data.
method Proposes a new robust contrastive loss inspired by distributionally robust optimization (DRO) and an efficient stochastic algorithm for automatic temperature individualization.
result Our method automatically learns a suitable temperature for each sample, improving performance on imbalanced datasets.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
CAggNet improves medical image segmentation by fusing coarse and fine features.
problem Medical image segmentation accuracy and efficiency.
method Crossing Aggregation Network with nested skip connections and weighted aggregation.
result CAggNet achieves more accurate and efficient segmentation compared to existing methods.
Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks. In real networks, nodes may have multiple tags but existing methods ignore the abundant semantic and hierarchical information of tags. This information is useful to many network applications and usually very sta…
Intelligence emerges from stabilizing invariant cycles in memory.
problem Understanding the nature of intelligence and its emergence.
method Structural-dynamical account rooted in a topological closure law: \(\partial^2=0\).
result Memory-amortized inference (MAI) mechanism that implements SbS \(
ightarrow\) CCUP.
Generative model creates realistic scenes from pixel-wise labels.
problem Creating photo-realistic scenes from pixel-wise labels.
method Semantic bottleneck GAN model combining conditional and unconditional generation networks.
result Model outperforms state-of-the-art models in unsupervised image synthesis.
TLMG4Eth combines language and graph models for Ethereum fraud detection.
problem Current fraud detection methods fail to consider semantic and similarity patterns in Ethereum transactions.
method TLMG4Eth uses a transaction language model and graph-based methods to capture semantic, similarity, and structural features.
result TLMG4Eth detects anomalies in Ethereum transactions more effectively than existing methods.
Proposes Structuring AutoEncoders to learn structured latent spaces.
problem Traditional Autoencoders fail to discover semantic structure in raw data.
method Enhances traditional Autoencoders using weak supervision to form a structured latent space.
result Structured latent space allows for more efficient data representation and tasks like classification.
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance on a variety of computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. In this paper, we examine whether CNNs are capable of learning the semantics…
Enhances machine learning interpretability using category theory.
problem Improving machine learning interpretability and social implementation.
method Develops a categorical framework for structured understanding of supervised learning.
result Introduces the Gauss-Markov Adjunction for clarifying residuals and parameters.