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
Computational Models for Morphology
TL;DR: Different computational models that can be used to solve morphological problems are examined, including dictionary based systems, finite state transducers, rule based systems and applying classification methods.
Journal ArticleDOI
Leveraging Web Semantic Knowledge in Word Representation Learning
TL;DR: This paper first constructs a semantic similarity graph, which is referred as semantic knowledge, based on a large collection of semantic lists extracted from the web using several pre-defined HTML tag patterns, and introduces an efficient joint word representation learning model to capture semantics from both semantic knowledge and text corpora.
Proceedings ArticleDOI
Improving Open Directory Project-Based Text Classification with Hierarchical Category Embedding
TL;DR: This paper proposes Hierarchical Category embedding (HC embedding) to generate distributed representations of hierarchical categories based on the implicit representation model and develops a new semantic similarity method to integrate HC embedding with the large-scale text classification.
Journal ArticleDOI
A Knowledge-Enriched Ensemble Method for Word Embedding and Multi-Sense Embedding
TL;DR: This paper propose a knowledge-enriched ensemble method to combine information from both knowledge graphs and pre-trained word embeddings, which is shown to outperform the state-of-the-art models in word analogy, word similarity and several downstream tasks.
Proceedings ArticleDOI
BoFGAN: Towards A New Structure of Backward-or-Forward Generative Adversarial Nets
TL;DR: A Backward-or-Forward Generative Adversarial Nets model (BoFGAN) is proposed to address the problem of hard constraints on the language generation tasks and demonstrates the effectiveness and rationality of the model.
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.