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.
Forward translation improves neural machine translation for sentences originally in source language.
Microsoft Research Asia won first place in 8 out of 11 WMT19 language directions.
CERT improves language understanding by contrastively learning sentence-level semantics.
Study uses attention-based method to detect different types of online harassment.
In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. To ensure that the model generates content compatible sentences, we introduce a reconstruction…
Paper proposes a new neural machine translation method for wave data.
Task-agnostic data augmentation shows little benefit for pretrained transformers.
Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspe…
This paper uses LLMs and cycle consistency for better machine translation evaluation.
BART pretrains sequence-to-sequence models by corrupting text and reconstructing it.