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
Exploring sentence informativeness
TL;DR: The experiments show that using the classifiers’ predictions to train word embeddings has an impact on embedding quality, and it is concluded that these two measures correspond to different notions of informativeness.
Book ChapterDOI
On the Impact of the Length of Subword Vectors on Word Embeddings
TL;DR: The experiments on two datasets with respect to two tasks show that the proposed model outperforms 6 baselines, which confirms the hypothesis that better word embeddings can be learned by representing words and subwords by different lengths of vectors.
Distributional initialization of neural networks
TL;DR: The main idea is to initialize a NN that learns embeddings with sparse distributional vectors that are precomputed for rare words from a given corpus, which suggests that training with word2vec is stable and reliable.
Journal ArticleDOI
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator
TL;DR: In this paper , the authors proposed an end-to-end contextual ASR using graph neural network (GNN) encodings based on the tree-constrained pointer generator method.
Dissertation
Morphological segmentation : an unsupervised method and application to Keyword Spotting
TL;DR: A new unsupervised algorithm for morphological segmentation that utilizes pseudo-semantic information, in addition to orthographic cues, is presented that makes use of the semantic signals from continuous word vectors, trained on huge corpora of raw text data.
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.