Results 1 to 10 of about 22,528 (91)
Post-Authorship Attribution Using Regularized Deep Neural Network
Applied Sciences, 2022 Post-authorship attribution is a scientific process of using stylometric features to identify the genuine writer of an online text snippet such as an email, blog, forum post, or chat log. It has useful applications in manifold domains, for instance, in a
Abiodun Modupe +3 more
doaj +1 more source
Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources [PDF]
, 2020 In this work, we present an effective method for semantic specialization of word vector representations. To this end, we use traditional word embeddings and apply specialization methods to better capture semantic relations between words. In our approach,
Biesialska, Magdalena +2 more
core +2 more sources
Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features [PDF]
, 2017 The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well.
Gupta, Prakhar +2 more
core +3 more sources
Compact Personalized Models for Neural Machine Translation
, 2018 We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with minimal or no reduction in ...
DeNero, John +2 more
core +1 more source
, 2017 NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supervision.
Felbo, Bjarke +4 more
core +1 more source
Learning Dynamic Feature Selection for Fast Sequential Prediction
, 2015 We present paired learning and inference algorithms for significantly reducing computation and increasing speed of the vector dot products in the classifiers that are at the heart of many NLP components.
McCallum, Andrew +3 more
core +1 more source
Better, Faster, Stronger Sequence Tagging Constituent Parsers [PDF]
, 2019 Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents ...
Abdou, Mostafa +2 more
core +3 more sources
Using the Output Embedding to Improve Language Models
, 2017 We study the topmost weight matrix of neural network language models. We show that this matrix constitutes a valid word embedding. When training language models, we recommend tying the input embedding and this output embedding.
Press, Ofir, Wolf, Lior
core +1 more source
, 2020 Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks.
Chen, Weizhu +5 more
core +1 more source
Transfer Learning for Speech and Language Processing [PDF]
, 2015 Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in another language ...
Wang, Dong, Zheng, Thomas Fang
core +1 more source