Open AccessProceedings Article
Better Word Representations with Recursive Neural Networks for Morphology
Thang Luong,Richard Socher,Christopher D. Manning +2 more
- pp 104-113
Reads0
Chats0
TLDR
This paper combines recursive neural networks, where each morpheme is a basic unit, with neural language models to consider contextual information in learning morphologicallyaware word representations and proposes a novel model capable of building representations for morphologically complex words from their morphemes.Abstract:
Vector-space word representations have been very successful in recent years at improving performance across a variety of NLP tasks. However, common to most existing work, words are regarded as independent entities without any explicit relationship among morphologically related words being modeled. As a result, rare and complex words are often poorly estimated, and all unknown words are represented in a rather crude way using only one or a few vectors. This paper addresses this shortcoming by proposing a novel model that is capable of building representations for morphologically complex words from their morphemes. We combine recursive neural networks (RNNs), where each morpheme is a basic unit, with neural language models (NLMs) to consider contextual information in learning morphologicallyaware word representations. Our learned models outperform existing word representations by a good margin on word similarity tasks across many datasets, including a new dataset we introduce focused on rare words to complement existing ones in an interesting way.read more
Citations
More filters
Proceedings ArticleDOI
The POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word Embeddings
TL;DR: The introduction of ‘POLAR’ — a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials and shows that the interpretable dimensions selected by the framework align with human judgement.
Proceedings ArticleDOI
How to represent a word and predict it, too: improving tied architectures for language modelling
TL;DR: This work proposes a simple modification to neural language models that decouples the hidden state from the word embedding prediction, leading to comparable or better results compared to previous tied models and models without tying, with a much smaller number of parameters.
Proceedings ArticleDOI
Orthogonality of Syntax and Semantics within Distributional Spaces
Jeff Mitchell,Mark Steedman +1 more
TL;DR: It is demonstrated that learning from word-order and morphological structure within English Wikipedia text to enable this decomposition can produce substantial improvements on semantic-similarity, posinduction and word-analogy tasks.
DissertationDOI
Semantic decomposition and marker passing in an artificial representation of meaning
TL;DR: This thesis investigates the use of the theory of Natural Semantic Metalanguage (NSM) to build an artificial representation of meaning and shows that theUse of NSM for creating a semantic graph out of different information sources can be utilized as a basis for Marker Passing algorithms.
Proceedings ArticleDOI
Mapping Unseen Words to Task-Trained Embedding Spaces
TL;DR: The authors use a multi-loss objective function to map from initial embeddings to task-specific embedding space, via a multilayer objective function, and demonstrate its use for improved dependency parsing and downstream improvements on sentiment analysis.
References
More filters
Journal ArticleDOI
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
Journal ArticleDOI
A neural probabilistic language model
TL;DR: The authors propose to learn a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences, which can be expressed in terms of these representations.
Journal Article
Natural Language Processing (Almost) from Scratch
TL;DR: A unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling is proposed.
Proceedings ArticleDOI
A unified architecture for natural language processing: deep neural networks with multitask learning
Ronan Collobert,Jason Weston +1 more
TL;DR: This work describes a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense using a language model.
Proceedings Article
Recurrent neural network based language model
TL;DR: Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.