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.
QUACKIE creates a new benchmark for NLP interpretability.
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 …
New pruning method retains model expressiveness for NLP tasks.
Improved NLP performance with fewer parameters and less data using conditional multi-task learning.
SusGen-GPT improves financial NLP and ESG report generation.
BERT outperforms traditional machine learning in text classification tasks.
COCKATIEL explains neural net models on NLP tasks by identifying meaningful concepts.
Survey on using large models to train smaller datasets in NLP.
Optimal Word2Vec hyper-parameters improve NLP tasks.
SCROLLS benchmarks long text NLP tasks, improving existing models.
BERTino is a lightweight Italian DistilBERT model for NLP tasks.
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…
BigBird improves transformer performance on NLP tasks with longer sequences.
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
This paper presents several strategies that can improve neural network-based predictive methods for MOOC student course trajectory modeling, applying multiple ideas previously applied to tackle NLP (Natural Language Processing) tasks. In particular, this paper investigates LSTM networks enhanced with two forms of regul…
Study recommends PLM choices for minimizing calibration error in NLP tasks.
This paper improves NLP interpretability by using sentence segments instead of words.
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, …
Significant advances have been made in Natural Language Processing (NLP) modelling since the beginning of 2018. The new approaches allow for accurate results, even when there is little labelled data, because these NLP models can benefit from training on both task-agnostic and task-specific unlabelled data. However, the…
New findings show BERT subnetworks can train independently and transfer to various tasks.
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…
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learnin…
LLM Pro Finance Suite enhances financial NLP with instruction-tuned models.
RoBERTa outperforms other pre-trained models in NER tasks.
Deep neural network models have recently achieved state-of-the-art performance gains in a variety of natural language processing (NLP) tasks (Young, Hazarika, Poria, & Cambria, 2017). However, these gains rely on the availability of large amounts of annotated examples, without which state-of-the-art performance is rare…
This paper predicts legal proceedings status using NLP and machine learning.
Improved language model for French clinical reports achieves state-of-the-art performance in medical NLP tasks.
Study shows fairness metrics are unreliable for small datasets in NLP tasks.
Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to langua…
Extracting information from electronic health records (EHR) is a challenging task since it requires prior knowledge of the reports and some natural language processing algorithm (NLP). With the growing number of EHR implementations, such knowledge is increasingly challenging to obtain in an efficient manner. We address…
Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we propose transfer with adapter modules. Adapter modules yield a compact and extens…
This work explains why GANs are less used for NLP tasks.
The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping the optimization process (Frankle & Carbin, 2019). Intriguingly, this phenomenon suggests that initial…
HuSpaCy offers an industrial-grade Hungarian NLP toolkit.
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thus, for TX-Ray, we modify the established computer vision explainability principle…
Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…
SpanishTinyRoBERTa distills large Spanish models into efficient question-answering models.
Task-agnostic data augmentation shows little benefit for pretrained transformers.
First derived from human intuition, later adapted to machine translation for automatic token alignment, attention mechanism, a simple method that can be used for encoding sequence data based on the importance score each element is assigned, has been widely applied to and attained significant improvement in various task…
Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks. If sparsity is important for NLP, might well-trained neural models naturally become roughly sparse? Using the Taxi-Euclidean norm to measure sparsity, we find …
Cryptonite tests NLP models with cryptic crossword clues.
Supervised machine learning (ML) algorithms are aimed at maximizing classification performance under available energy and storage constraints. They try to map the training data to the corresponding labels while ensuring generalizability to unseen data. However, they do not integrate meaning-based relationships among la…
BERTopic enhances stock market prediction by analyzing sentiment in topic models.
Combines foundation models with weak supervision to improve NLP and video tasks.
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…
Language Rectified Flow improves diffusion language generation by simplifying complex steps.
Researchers develop a method to interpret GNNs by identifying unnecessary edges in NLP models.
While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and time-consuming. Active Learning (AL) strategies reduce the need for huge volumes of labeled…