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

17345168 · Jun 202019922001200920182026
48 results for Named-entity recognition

Improves cross-lingual NER by projecting entities from one language to another.

problem Limited annotated corpora for named entity recognition in many languages.
method Uses machine translation twice: first for sentences, then for entities; matches based on ortho- and phonetic similarity; identifies matches using distributional statistics.
result Improves cross-lingual NER by an average of 4.1 points on 5 diverse languages.

Paper proposes neural approach for Chinese named entity recognition.

problem Challenges in Chinese named entity recognition due to context-dependency and lack of word delimiters.
method Introduces a CNN-LSTM-CRF neural architecture and a unified framework for joint training with word segmentation.
result Improves Chinese named entity recognition performance, especially with limited training data.

Greek POS Tagger and Entity Recognizer built using spaCy.

problem Developing a machine learning model for Greek language POS tagging and named entity recognition.
method Machine learning approach with spaCy platform, focusing on morphological features and token classification.
result The Greek spaCy platform improved performance in part-of-speech tagging and named entity recognition.

The paper extends influence functions to sequence tagging tasks for better model interpretability.

problem Lack of interpretability methods for sequence tagging models.
method Define and compute influence of training instance segments on test segment predictions.
result The segment influence method tracks with true influence and identifies annotation errors.

A multi-task learning framework improves BioNER performance across different entity types.

problem Limited performance of BioNER systems due to lack of training data for each entity type.
method Multi-task learning framework that collectively uses training data of different entity types.
result Substantially better performance on 15 benchmark BioNER datasets compared to state-of-the-art systems.

Proposes a method to improve deep active learning for NER tasks.

problem Weaknesses of existing deep active learning algorithms in practice.
method Estimates error decay curves of feature-defined subsets to improve sampling efficiency and robustness.
result Significantly outperforms diversification-based methods for black-box NER taggers and makes sampling more robust to labeling noise.

Improved NER on Turkish tweets using semi-supervised learning and word embeddings.

problem Named Entity Recognition on informal Turkish text types.
method Semi-supervised learning with neural networks and word embeddings.
result Achieved better F-score performances than previous Turkish NER systems.

Paper presents a method to train NER models without labelled data using weak supervision.

problem Dealing with NER performance drop in new domains without labelled data.
method Weak supervision through automatic annotation and hidden Markov model integration.
result Improvement of about 7 percentage points in entity-level F1F_1 scores.

The paper introduces uncertainty quantification for NER models.

problem Current NER models lack uncertainty measures, leading to downstream errors.
method Full-Sequence and Subsequence Conformal Prediction framework.
result The method provides formal guarantees about the reliability of model predictions.

Improved NER performance on imbalanced data.

problem Highly unbalanced training data in NER tasks.
method Adapted a neural architecture with CRF and BI-LSTM layers, using pre-trained embeddings. Introduced a two-class split to optimize performance.
result Significant improvement in performance for weak classes with minimal training data.

A multi-task learning model for slot tagging in biomedical domains.

problem Limited labeled data, memory constraints, and domain-specific slot types.
method Multi-task learning using deep bidirectional transformers.
result Outperforms previous state-of-the-art systems in efficiency and effectiveness.

BiLSTM model improves NER and negation detection in radiological reports.

problem Automating medical information extraction from radiological reports.
method Bi-directional Long Short-Term Memory (BiLSTM) neural network architecture.
result BiLSTM outperforms traditional rule-based systems for NER and negation detection.

Automated synthesis planning from scientific literature using AI.

problem Accelerate materials design and discovery by connecting scientific literature to synthesis insights.
method Word embeddings from language models, named entity recognition, conditional variational autoencoder.
result The model predicts precursors for perovskite materials using historical data.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.

Paper proposes ensemble distillation for well-calibrated structured prediction.

problem Well-calibrated predictions are hard to achieve in structured prediction.
method Ensemble distillation framework for structured prediction.
result Ensemble distillation produces well-calibrated models with similar performance and calibration benefits to ensembles.

Study shows partially-typed NER datasets can match fully-typed ones in model performance.

problem Leveraging multiple partially-typed NER datasets for training models without fully-typed annotations.
method Systematic analysis and controlled experiments comparing partially-typed and fully-typed datasets.
result Models trained with partially-typed annotations can achieve similar performance to those trained with fully-typed annotations.

BloombergGPT is a large language model trained on financial data, outperforming existing models on financial tasks.

problem Lack of specialized large language models for finance.
method Trained on a 363 billion token dataset augmented with 345 billion tokens from general datasets, using a 50 billion parameter model.
result BloombergGPT outperforms existing models on financial tasks without sacrificing performance on general LLM benchmarks.

The paper introduces a method to measure the benefits of incidental supervision signals.

problem Lack of a principled way to measure the benefits of various types of incidental supervision signals.
method Unified PAC-Bayesian motivated informativeness measure, PABI.
result Demonstrates PABI's effectiveness in quantifying the value added by various types of incidental signals.

The Gibbs sampler is one of the most popular algorithms for inference in statistical models. In this paper, we introduce a herding variant of this algorithm, called herded Gibbs, that is entirely deterministic. We prove that herded Gibbs has an O(1/T)O(1/T) convergence rate for models with independent variables and for ful…

2013-01-17abs ↗pdf ↗

Annotation errors can significantly hurt classifier performance, yet datasets are only growing noisier with the increased use of Amazon Mechanical Turk and techniques like distant supervision that automatically generate labels. In this paper, we present a robust extension of logistic regression that incorporates the po…

2013-05-21abs ↗pdf ↗

Softmax Q-distribution reveals RAML's theoretical basis in structured prediction.

problem Improving structured prediction models with reward functions.
method Introducing a novel theoretical interpretation of RAML using softmax Q-distribution.
result RAML is equivalent to estimating the softmax Q-distribution, with temperature controlling approximation error.

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop…

2016-03-21abs ↗pdf ↗

OpenTag extracts missing attribute values from product descriptions.

problem Extract missing attribute values from product descriptions.
method Developed a deep tagging model OpenTag using LSTM and CRF, with an attention mechanism and active learning.
result OpenTag discovers new attribute values with minimal human annotation, achieving high F-score.