Aliaksei Severyn

Distributional Neural Networks for Automatic Resolution of Crossword Puzzles

2015

Aliaksei Severyn, Massimo Nicosia, Gianni Barlacchi, Alessandro Moschitti. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2015.

Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision

2017 · arXiv (Cornell University)

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic …

EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start

2022 · arXiv (Cornell University)

We present EdiT5 - a novel semi-autoregressive text-editing model designed to combine the strengths of non-autoregressive text-editing and autoregressive decoding. EdiT5 is faster during inference than conventional sequence-to-sequence (seq2seq) models, while being capable of modelling …

Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

2015

Learning a similarity function between pairs of objects is at the core of learning to rank approaches. In information retrieval tasks we typically deal with query-document pairs, in question answering -- question-answer pairs. However, before …

Twitter Sentiment Analysis with Deep Convolutional Neural Networks

2015

This paper describes our deep learning system for sentiment analysis of tweets. The main contribution of this work is a new model for initializing the parameter weights of the convolutional neural network, which is crucial …

Globally Normalized Transition-Based Neural Networks

2016

Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, Michael Collins. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016.

Neural Ranking Models with Weak Supervision

2017

Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of …

On Accurate Evaluation of GANs for Language Generation

2018 · arXiv (Cornell University)

Generative Adversarial Networks (GANs) are a promising approach to language generation. The latest works introducing novel GAN models for language generation use n-gram based metrics for evaluation and only report single scores of the best …

Gemini: A Family of Highly Capable Multimodal Models

2023 · arXiv (Cornell University)

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging …