[图书][B] Neural network methods in natural language processing
Y Goldberg - 2017 - books.google.com
Neural networks are a family of powerful machine learning models and this book focuses on
their application to natural language data. The first half of the book (Parts I and II) covers the …
their application to natural language data. The first half of the book (Parts I and II) covers the …
Demographic inference and representative population estimates from multilingual social media data
Social media provide access to behavioural data at an unprecedented scale and granularity.
However, using these data to understand phenomena in a broader population is difficult due …
However, using these data to understand phenomena in a broader population is difficult due …
Neural sequence learning models for word sense disambiguation
A Raganato, CD Bovi, R Navigli - Proceedings of the 2017 …, 2017 - aclanthology.org
Abstract Word Sense Disambiguation models exist in many flavors. Even though supervised
ones tend to perform best in terms of accuracy, they often lose ground to more flexible …
ones tend to perform best in terms of accuracy, they often lose ground to more flexible …
Dynet: The dynamic neural network toolkit
We describe DyNet, a toolkit for implementing neural network models based on dynamic
declaration of network structure. In the static declaration strategy that is used in toolkits like …
declaration of network structure. In the static declaration strategy that is used in toolkits like …
[PDF][PDF] The SIGMORPHON 2016 shared task—morphological reinflection
R Cotterell, C Kirov, J Sylak-Glassman… - Proceedings of the …, 2016 - aclanthology.org
Abstract The 2016 SIGMORPHON Shared Task was devoted to the problem of
morphological reinflection. It introduced morphological datasets for 10 languages with …
morphological reinflection. It introduced morphological datasets for 10 languages with …
CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages
R Cotterell, C Kirov, J Sylak-Glassman… - arXiv preprint arXiv …, 2017 - arxiv.org
The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation
required systems to be trained and tested in each of 52 typologically diverse languages. In …
required systems to be trained and tested in each of 52 typologically diverse languages. In …
UniMorph 2.0: universal morphology
C Kirov, R Cotterell, J Sylak-Glassman… - arXiv preprint arXiv …, 2018 - arxiv.org
The Universal Morphology UniMorph project is a collaborative effort to improve how NLP
handles complex morphology across the world's languages. The project releases annotated …
handles complex morphology across the world's languages. The project releases annotated …
Morphological inflection generation with hard monotonic attention
R Aharoni, Y Goldberg - arXiv preprint arXiv:1611.01487, 2016 - arxiv.org
We present a neural model for morphological inflection generation which employs a hard
attention mechanism, inspired by the nearly-monotonic alignment commonly found between …
attention mechanism, inspired by the nearly-monotonic alignment commonly found between …
Recurrent neural networks in linguistic theory: Revisiting Pinker and Prince (1988) and the past tense debate
C Kirov, R Cotterell - … of the Association for Computational Linguistics, 2018 - direct.mit.edu
Can advances in NLP help advance cognitive modeling? We examine the role of artificial
neural networks, the current state of the art in many common NLP tasks, by returning to a …
neural networks, the current state of the art in many common NLP tasks, by returning to a …
[PDF][PDF] MED: The LMU system for the SIGMORPHON 2016 shared task on morphological reinflection
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016
Shared Task on Morphological Reinflection as well as an extended analysis of how different …
Shared Task on Morphological Reinflection as well as an extended analysis of how different …