Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

1223 · Apr 201819922001200920182026
33 results for Persian wordnet

Paper builds a Persian wordnet using supervised learning.

problem Creating an accurate Persian wordnet.
method Used a Persian corpus and bi-lingual dictionary to generate initial links. Trained a classification system on a set of correct instances to discriminate correct from incorrect links.
result Achieved state-of-the-art results with a precision of 91.18%.

Study classifies Persian speech acts for better understanding of text intent.

problem Understanding the intended function of Persian texts.
method Dictionary-based statistical technique using WordNet for SA recognition.
result Proposed method achieved state-of-the-art accuracy of 0.95 for Persian SA classification.

Pars-ABSA dataset for Persian aspect-based sentiment analysis.

problem Lack of public dataset for Persian aspect-based sentiment analysis.
method Manually annotated dataset with 5,114 positive, 3,061 negative, and 1,827 neutral samples.
result State-of-the-art performance of deep learning methods on Pars-ABSA compared to similar English datasets.

Paper proposes a deep learning method to measure domain similarity in Persian texts.

problem Measuring the similarity between different domains of Persian text descriptions.
method Built a dataset of paired texts, used word embeddings and deep neural networks to score similarity, trained on GPU.
result Best model achieved an F1 score of 0.9865.

Deep transfer learning from Persian handwriting improves offline signature verification.

problem Challenges in offline signature verification, especially with skilled forgeries and limited training data.
method Transfer learning approach from Persian handwriting to multi-language OSV, using Residual CNNs for feature learning and SVMs for verification.
result Significant improvement in Equal Error Rate (EER) on UT-Sig dataset (9.80% EER), surpassing state-of-the-art methods.

The paper predicts TSE stocks using social media sentiment and volume.

problem Predicting Tehran Stock Exchange (TSE) variables using social media data.
method Hybrid sentiment analysis combining lexicon-based and learning-based methods; built a sentiment lexicon for Persian language.
result Sentiment and volume of online comments are useful for predicting TSE stocks.

GCTM integrates GCN into topic models for better topic learning from data streams.

problem Learning hidden topics from short and noisy data streams with concept drift.
method Proposes a graph convolutional topic model (GCTM) that learns from a knowledge graph and old data.
result Significantly better performance in probabilistic predictive measures and topic coherence.

Extends linear representation hypothesis to categorical and hierarchical concepts in LLMs.

problem Representing concepts without natural contrasts in large language models.
method Formalizes linear representation hypothesis for categorical and hierarchical concepts, proving relationships between concept hierarchy and representation geometry.
result Validated theoretical results on large language models, estimating representations for 900+ concepts.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

A new method compares image classifiers using adaptive sampling of natural images.

problem Evaluation of image classifiers on small, fixed test sets may not generalize to real-world images.
method Adaptive sampling from a large corpus of unlabeled images to maximize classifier discrepancies measured by WordNet hierarchy.
result Human labeling of model-dependent image sets reveals relative classifier performance.

Hierarchical density embeddings capture word relationships with uncertainty.

problem Capturing semantic relationships and uncertainty in word embeddings.
method Learn hierarchical representations through probability density encapsulation, using simple loss functions and distance metrics.
result State-of-the-art performance on WordNet and Hyperlex datasets.

ZSL-KG learns class representations from common sense knowledge graphs.

problem Predicting classes without labeled examples using semantic class representations.
method TrGCN, a novel transformer graph convolutional network, embeds nodes from common sense knowledge graphs in a vector space.
result ZSL-KG improves over existing methods on five out of six zero-shot benchmark datasets.

Tag2Vec learns tag representations in hybrid networks with semantic and hierarchical information.

problem Lack of semantic and hierarchical information in tag networks.
method Tag2Vec model that combines nodes and tags into hybrid networks, using parameterized random walks and hyperbolic Skip-gram model.
result Tag2Vec outperforms other models in learning rich semantic tag representations.

This paper tackles rare word problem in low-resource language pairs using NMT.

problem Rare word problem in neural machine translation, especially for low-resource languages.
method Three solutions: enhanced source context, morphology learning, and wordnet synonyms.
result Significant improvements in BLEU scores (+1.0 points) on English-Vietnamese and Japanese-Vietnamese.

Hyperbolic embeddings reduce dimensions for hierarchical data with high precision.

problem Embedding hierarchical data structures like synonym or type hierarchies efficiently.
method Combinatorial construction and hyperbolic multidimensional scaling (h-MDS) for metric spaces.
result Hyperbolic embeddings achieve high precision with few dimensions, e.g., 0.989 MAP with only 2 dimensions on WordNet.

Algorithm transfers visual concepts to answer out-of-vocabulary questions.

problem Leveraging off-the-shelf visual and linguistic data for out-of-vocabulary answers in visual question answering.
method Unsupervised task discovery for learning task conditional visual classifier, then transferring to visual question answering models.
result Algorithm generalizes to out-of-vocabulary answers successfully.

ENN neural network learns logical syllogisms using Euler diagrams.

problem Traditional neural networks struggle with logical reasoning, especially syllogisms.
method ENN represents logical relations as Euler diagrams, optimizing syllogism structures with a novel back-propagation algorithm.
result ENN can precisely represent and reason with all 24 syllogism structures.

The paper constructs financial sentiment factors using NLP for the Chinese market.

problem Evaluating sentiment in the Chinese financial market.
method Crawling news and comments, applying NLP techniques, building a finance-specific lexicon, and adjusting the sentiment factor.
result The adjusted sentimental factor has a strong correlation with the Chinese market, especially during crises.

Interactive image retrieval system learns from user feedback and unlabeled data.

problem Efficiently retrieve relevant images with minimal user interaction.
method Combines active learning and graph-based semi-supervised learning (GSSL) to use unlabeled data.
result High F1 scores with few relevance feedback rounds on large datasets.

Proposes AML loss function for TransE to improve link prediction in knowledge graphs.

problem Low performance of TransE due to insufficient scores of positive triples.
method Introduces Adaptive Margin Loss (AML) to automatically adjust margin during training.
result AML improves TransE's performance on link prediction tasks in knowledge graphs.