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.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “NLU”

CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcs.LG

CLUTRR benchmarks NLU systems' ability to infer logical rules from text.

problem NLU models' failure to generalize systematically and robustly.

method CLUTRR suite requires inference of kinship relations from short stories, evaluating generalization and robustness.

result Graph-based models outperform state-of-the-art NLU models in generalization and robustness.

NLU Inductive Reasoning Benchmark Logical Rules Graph Neural Networks

2019-08-16abs ↗pdf ↗

Accelerated Large Batch Optimization of BERT Pretraining in 54 minutescs.LG

Accelerates BERT pretraining from 3 days to 54 minutes.

problem Long training time of BERT due to large mini-batch sizes.

method LANS method and learning rate scheduler for large mini-batch training.

result Achieved fastest BERT training time of 54 minutes.

BERT large batch acceleration learning rate mini-batch

2020-06-24abs ↗pdf ↗

A New Concept of Deep Reinforcement Learning based Augmented General Sequence Tagging Systemcs.LG

In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed. The new system contains two parts: a deep neural network (DNN) based sequence tagging model and a deep reinforcement learning (DRL) based augmented tagger. The augmented tagger helps improve system performance …

2018-12-26abs ↗pdf ↗

The Immersion of Directed Multi-graphs in Embedding Fields. Generalisationscs.LG

This paper generalizes graph representation for diverse data types.

problem Representing and querying hybrid data types in a unified way.

method Introducing a directed Tensor-Typed Multi-Graph with embeddings.

result Unified representation for visual, linguistic, and auditory data.

Tensor-Typed Multi-Graph Hybrid Data Types Machine Learning Cross-Domain Queries Latent Spaces

2020-04-28abs ↗pdf ↗

MT-BioNER: Multi-task Learning for Biomedical Named Entity Recognition using Deep Bidirectional Transformerscs.CL

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.

multi-task learning transformers slot tagging biomedical named entity recognition

2020-01-24abs ↗pdf ↗