A survey on text classification algorithms: From text to predictions
In recent years, the exponential growth of digital documents has been met by rapid progress
in text classification techniques. Newly proposed machine learning algorithms leverage the …
in text classification techniques. Newly proposed machine learning algorithms leverage the …
A survey on session-based recommender systems
Recommender systems (RSs) have been playing an increasingly important role for informed
consumption, services, and decision-making in the overloaded information era and digitized …
consumption, services, and decision-making in the overloaded information era and digitized …
Chatgpt beyond english: Towards a comprehensive evaluation of large language models in multilingual learning
Over the last few years, large language models (LLMs) have emerged as the most important
breakthroughs in natural language processing (NLP) that fundamentally transform research …
breakthroughs in natural language processing (NLP) that fundamentally transform research …
Unsupervised speech recognition
Despite rapid progress in the recent past, current speech recognition systems still require
labeled training data which limits this technology to a small fraction of the languages spoken …
labeled training data which limits this technology to a small fraction of the languages spoken …
[PDF][PDF] Multilingual denoising pre-training for neural machine translation
Y Liu - arXiv preprint arXiv:2001.08210, 2020 - fq.pkwyx.com
This paper demonstrates that multilingual denoising pre-training produces significant
performance gains across a wide variety of machine translation (MT) tasks. We present …
performance gains across a wide variety of machine translation (MT) tasks. We present …
Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation
Much recent progress in applications of machine learning models to NLP has been driven
by benchmarks that evaluate models across a wide variety of tasks. However, these broad …
by benchmarks that evaluate models across a wide variety of tasks. However, these broad …
Cross-lingual language model pretraining
Recent studies have demonstrated the efficiency of generative pretraining for English
natural language understanding. In this work, we extend this approach to multiple …
natural language understanding. In this work, we extend this approach to multiple …
How neural networks extrapolate: From feedforward to graph neural networks
We study how neural networks trained by gradient descent extrapolate, ie, what they learn
outside the support of the training distribution. Previous works report mixed empirical results …
outside the support of the training distribution. Previous works report mixed empirical results …
[图书][B] The alignment problem: How can machines learn human values?
B Christian - 2021 - books.google.com
'Vital reading. This is the book on artificial intelligence we need right now.'Mike Krieger,
cofounder of Instagram Artificial intelligence is rapidly dominating every aspect of our …
cofounder of Instagram Artificial intelligence is rapidly dominating every aspect of our …
[PDF][PDF] Unsupervised cross-lingual representation learning at scale
A Conneau - arXiv preprint arXiv:1911.02116, 2019 - fq.pkwyx.com
This paper shows that pretraining multilingual language models at scale leads to significant
performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer …
performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer …