A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors

arXiv.org Artificial Intelligence

Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la carte embedding, a simple and general alternative to the usual word2vec-based approaches for building such representations that is based upon recent theoretical results for GloVe-like embeddings. Our method relies mainly on a linear transformation that is efficiently learnable using pretrained word vectors and linear regression. This transform is applicable on the fly in the future when a new text feature or rare word is encountered, even if only a single usage example is available. We introduce a new dataset showing how the a la carte method requires fewer examples of words in context to learn high-quality embeddings and we obtain state-of-the-art results on a nonce task and some unsupervised document classification tasks.


Estimator Vectors: OOV Word Embeddings based on Subword and Context Clue Estimates

arXiv.org Machine Learning

Estimator Vectors: OOV Word Embeddings based on Subword and Context Clue Estimates Raj Patel Carlotta Domeniconi † Abstract Semantic representations of words have been successfully extracted from unlabeled corpuses using neural network models like word2vec. These representations are generally high quality and are computationally inexpensive to train, making them popular. However, these approaches generally fail to approximate out of vocabulary (OOV) words, a task humans can do quite easily, using word roots and context clues. This paper proposes a neural network model that learns high quality word representations, subword representations, and context clue representations jointly. Learning all three types of representations together enhances the learning of each, leading to enriched word vectors, along with strong estimates for OOV words, via the combination of the corresponding context clue and subword embeddings. Our model, called Estimator Vectors (EV), learns strong word embed-dings and is competitive with state of the art methods for OOV estimation. 1 Introduction Semantic representations of words are useful for many natural language processing (NLP) tasks. While there exists many ways to learn them, models like word2vec [11] and GloVe [15] have been shown to be very efficient at producing high quality word embeddings. These embeddings not only capture similarity between words, but also capture some algebraic relationships between words. These models, though, also have some downsides. One major drawback is that they can only learn embeddings for words in the vocabulary, determined by the corpus they were trained on. Although common words are typically captured, most existing approaches are unable to learn the meaning of new words, known as out of vocabulary (OOV) words, a task humans can do easily.


Learning Semantic Representations for Novel Words: Leveraging Both Form and Context

arXiv.org Artificial Intelligence

Word embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data. The general problem setting is that word embeddings are induced on an unlabeled training corpus and then a model is trained that embeds novel words into this induced embedding space. Currently, two approaches for learning embeddings of novel words exist: (i) learning an embedding from the novel word's surface-form (e.g., subword n-grams) and (ii) learning an embedding from the context in which it occurs. In this paper, we propose an architecture that leverages both sources of information - surface-form and context - and show that it results in large increases in embedding quality. Our architecture obtains state-of-the-art results on the Definitional Nonce and Contextual Rare Words datasets. As input, we only require an embedding set and an unlabeled corpus for training our architecture to produce embeddings appropriate for the induced embedding space. Thus, our model can easily be integrated into any existing NLP system and enhance its capability to handle novel words.


Correcting the Common Discourse Bias in Linear Representation of Sentences using Conceptors

arXiv.org Machine Learning

Distributed representations of words, better known as word embeddings, have become important building blocks for natural language processing tasks. Numerous studies are devoted to transferring the success of unsupervised word embeddings to sentence embeddings. In this paper, we introduce a simple representation of sentences in which a sentence embedding is represented as a weighted average of word vectors followed by a soft projection. We demonstrate the effectiveness of this proposed method on the clinical semantic textual similarity task of the BioCreative/OHNLP Challenge 2018.


Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings

arXiv.org Machine Learning

One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the supervised and semi-supervised settings. The best results were obtained by combining region embeddings in the form of LSTM and convolution layers trained on unlabeled data. The results indicate that on this task, embeddings of text regions, which can convey complex concepts, are more useful than embeddings of single words in isolation. We report performances exceeding the previous best results on four benchmark datasets.