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

count % of corpus

3 results for “seq-to-seq”

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcs.CL

Paper improves text-to-SQL models with schema-aware denoising.

problem Text-to-SQL models struggle with schema linking and grammar correctness.

method Adapts transformer-based seq-to-seq model with SeaD denoising objectives and clause-sensitive decoding.

result Improves seq-to-seq model performance on WikiSQL benchmark.

text-to-SQL schema-aware denoising transformer seq-to-seq

2021-05-17abs ↗pdf ↗

Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesiscs.LG

This paper examines data transfer methods to improve off-the-shelf Transformer models for retrosynthesis.

problem Improving prediction models for retrosynthesis using small datasets.

method Systematic examination of data transfer approaches on end-to-end generative models.

result Pre-training plus fine-tuning boosts the accuracy of a Transformer baseline, achieving state-of-the-art results.

retrosynthesis Transformer data transfer generative models chemical prediction

2020-10-02abs ↗pdf ↗

Not All Attention Is Needed: Gated Attention Network for Sequence Datacs.LG

GA-Net selectively attends to parts of a sequence for text classification.

problem Inefficient global attention mechanisms on long sequences.

method Gated Attention Network (GA-Net) using an auxiliary network to dynamically select and attend to important parts of the sequence.

result GA-Net achieves better performance with less computation and interpretability.

attention mechanisms dynamic network sequence data text classification neural networks

2019-12-01abs ↗pdf ↗