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

count % of corpus

8 results for “LSTM-CRF”

Bidirectional LSTM-CRF for Clinical Concept Extractionstat.ML

Paper proposes a streamlined approach to clinical concept extraction using LSTM-CRF.

problem Automated extraction of concepts from clinical records for clinical research.

method Bidirectional LSTM with CRF decoding initialized with general-purpose word embeddings.

result Experimental results outperform all recent methods and rank closely to the best submission from the original i2b2/VA challenge.

clinical concept extraction LSTM-CRF word embeddings i2b2/VA challenge natural language processing

2016-11-25abs ↗pdf ↗

Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentationcs.CL

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.

Chinese named entity recognition CNN-LSTM-CRF word segmentation context-dependency word delimiters

2019-04-26abs ↗pdf ↗

FGN: Fusion Glyph Network for Chinese Named Entity Recognitioncs.CL

FGN improves Chinese NER by integrating glyph information and interactive context.

problem Chinese named entity recognition is challenging due to the complexity of characters and their glyphs.

method FGN uses a novel CGS-CNN structure to capture glyph and interactive information, and a sliding window method to fuse BERT and glyph representations.

result FGN achieves state-of-the-art performance on four NER datasets, improving over previous methods.

Chinese NER glyph information interactive context CNN BERT

2020-01-15abs ↗pdf ↗

Melodic Phrase Segmentation By Deep Neural Networkscs.LG

Deep neural networks improve music phrase segmentation.

problem Automated melodic phrase detection and segmentation in music.

method Adapted various neural network architectures to symbolic music representation, addressing sparse labeling problem.

result CNN-CRF architecture performs best, offering finer segmentation and faster training.

music information retrieval deep learning neural networks melodic phrase segmentation sequential labeling

2018-11-14abs ↗pdf ↗

On the Vietnamese Name Entity Recognition: A Deep Learning Method Approachcs.CL

Deep learning model improves Vietnamese NER accuracy.

problem Vietnamese named entity recognition (NER) accuracy.

method Combining Bi-LSTM and CRF with word embeddings and semantic features.

result Achieved state-of-the-art NER results on VLSP2016 dataset.

Vietnamese NER Deep Learning Bi-LSTM CRF Word2Vec

2019-11-18abs ↗pdf ↗

Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversationcs.CL

Improved SAR in asynchronous conversations using neural models and unlabeled data.

problem Lack of labeled data for SAR in asynchronous conversations.

method Hierarchical LSTM-CRF model, semi-supervised learning with word embeddings, adversarial training.

result Adversarial training improves SAR performance by leveraging labeled data from synchronous domains.

speech act recognition asynchronous conversation semi-supervised learning adversarial training word embeddings

2019-04-01abs ↗pdf ↗

Adaptive Name Entity Recognition under Highly Unbalanced Datacs.CL

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.

Named Entity Recognition NER Unbalanced Data Conditional Random Field Bi-directional LSTM

2020-03-10abs ↗pdf ↗

Factored Latent-Dynamic Conditional Random Fields for Single and Multi-label Sequence Modelingcs.LG

FLDCRF improves sequence labeling performance with latent dynamics interactions.

problem Sequence labeling with improved performance and latent dynamics interactions.

method Factored Latent-Dynamic Conditional Random Fields (FLDCRF) with multiple latent dynamics interactions.

result FLDCRF outperforms state-of-the-art models across multiple datasets.

Conditional Random Fields Latent Dynamics Sequence Modeling Labeling Performance Multi-label

2019-11-09abs ↗pdf ↗