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.

168,742 papers · 148 categories

Trend · papers per month

148297445593 · Jun 202019922001200920172026
48 results for NLP datasets

QUACKIE creates a new benchmark for NLP interpretability.

problem Evaluating NLP interpretability methods is challenging due to biased ground truths.
method Formulated a custom classification task from question-answering datasets, generating unbiased ground truths.
result Demonstrated the effectiveness of current interpretability methods on the new benchmark.

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP datasets that HUBERT, but not BERT, is able to learn and leverage. We validate …

2019-10-25abs ↗pdf ↗

A benchmark for NLP models trained on text datasets.

problem Limited access to high-performance clusters for NAS experiments.
method Created a search space for recurrent neural networks on text datasets and trained 14k architectures.
result Demonstrated the potential of precomputed NAS results for NLP.

The paper uses geometry to assess how hard examples are for NLP models.

problem Challenges in NLP datasets and classifiers, especially with shallow features.
method Information geometry to quantify example difficulty, exploring BERT, CNN, and fasttext.
result Deep learning models are vulnerable to word substitutions in difficult examples.

In this paper we consider the problem of Gaussian process classifier (GPC) model selection with different Leave-One-Out (LOO) Cross Validation (CV) based optimization criteria and provide a practical algorithm using LOO predictive distributions with such criteria to select hyperparameters. Apart from the standard avera…

2012-06-26abs ↗pdf ↗

We address the problem of graph classification based only on structural information. Inspired by natural language processing techniques (NLP), our model sequentially embeds information to estimate class membership probabilities. Besides, we experiment with NLP-like variational regularization techniques, making the mode…

2019-02-07abs ↗pdf ↗

COCKATIEL explains neural net models on NLP tasks by identifying meaningful concepts.

problem Transformer models are complex and hard to interpret.
method COCKATIEL uses NMF and sensitivity analysis to identify and rank concepts used by the model.
result COCKATIEL provides accurate and meaningful explanations without affecting model performance.

Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-t…

2019-08-15abs ↗pdf ↗

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce tech…

2018-01-18abs ↗pdf ↗

Question semantic similarity (Q2Q) is a challenging task that is very useful in many NLP applications, such as detecting duplicate questions and question answering systems. In this paper, we present the results and findings of the shared task (Semantic Question Similarity in Arabic). The task was organized as part of t…

2019-09-12abs ↗pdf ↗

Improved language model for French clinical reports achieves state-of-the-art performance in medical NLP tasks.

problem Lack of specialized language models for French clinical reports.
method Adapted a general pre-trained language model (CamemBERT) to French clinical reports using a corpus of 21M reports.
result Pretrained and fine-tuned models improved F1-score by 3 percentage points on APMed task.

TX-Ray analyzes and quantifies model knowledge transfer in NLP.

problem Insufficient methods for explaining and quantifying model knowledge transfer in NLP.
method Modified computer vision explainability principle to NLP, visualizing feature preference distributions.
result TX-Ray reveals how self-supervised models learn linguistic abstractions and improves generalization.

This paper improves NLP interpretability by using sentence segments instead of words.

problem Limitations of word-based sampling in explaining complex BERT models.
method Using sentence segments as elementary building blocks for NLP interpretability.
result Improved fidelity of the explainer on a benchmark classification task.

Improved financial sentiment analysis using LLMs with retrieval augmentation.

problem Limited performance of traditional NLP models in financial sentiment analysis.
method Retrieval-augmented Large Language Models (LLMs) with instruction tuning.
result Achieved 15% to 48% performance gain in accuracy and F1 score.

Researchers develop method to protect against 'weight poisoning' attacks on pre-trained models.

problem The security threat of downloading untrusted pre-trained weights that can be manipulated after fine-tuning.
method RIPPLe regularization method and Embedding Surgery initialization procedure.
result Demonstrated that weight poisoning attacks are possible even with limited knowledge of the dataset and fine-tuning procedure.

Generative model evaluates text emotion intensity, outperforming classification.

problem Limitations of discrete emotion classification in applied domains.
method Fine-tuning generative language models to output continuous emotion intensity scores.
result Generative model outperforms classification baselines and reveals generalization capabilities.

This thesis identifies share buybacks and predicts their impact on stock performance.

problem Recognizing and predicting the impact of share buybacks on stock performance.
method NLP approaches for automated detection of share buybacks, machine learning models for prediction.
result Most companies underperform after a share buyback, but some significantly outperform.

BERT outperforms traditional machine learning in text classification tasks.

problem Comparing BERT to traditional machine learning methods for text classification.
method Empirical testing of BERT against TF-IDF-based machine learning models in various scenarios.
result BERT demonstrates superior performance and independence from text features.

Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The success of neural embeddings has prompted significant amounts of research into appli…

2017-05-29abs ↗pdf ↗

The paper improves cryptocurrency price forecasting using deep learning and NLP on financial, blockchain, and social media data.

problem Improving cryptocurrency price forecasting accuracy and profitability.
method Integrates financial, blockchain, and social media data; applies BART MNLI model for sentiment analysis; uses deep learning NLP models; compares with traditional methods; uses local extrema as predictive targets.
result Significantly improves forecasting accuracy and profitability of cryptocurrency price predictions.

This study uses NLP to predict stock performance based on analyst reports.

problem Predicting stock performance using textual information from analyst reports.
method Natural language processing (NLP) and a customized BERT deep learning model for Chinese text.
result Strong positive sentiment in analyst reports increases excess return and intraday volatility, while strong negative sentiment increases volatility and trading volume but decreases excess return.