We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.

/pdf/deep-contextualized-word-representations-11iek0hsjp.pdf

Deep contextualized word representations

Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics. In this way, contextual word embeddings can be flexibly obtained to measure contextual word similarity. We can also build document representations, which are more expressive than some widely-used document models such as latent topic models. In the experiments, we evaluate the TWE models on two tasks, contextual word similarity and text classification. The experimental results show that our models outperform typical word embedding models including the multi-prototype version on contextual word similarity, and also exceed latent topic models and other representative document models on text classification. The source code of this paper can be obtained from https://github.com/largelymfs/topical_word_embeddings.

/pdf/topical-word-embeddings-25x49xvan6.pdf

Topical word embeddings

Continuous space word embeddings learned from large, unstructured corpora have been shown to be effective at capturing semantic regularities in language. In this paper we replace LDA’s parameterization of “topics” as categorical distributions over opaque word types with multivariate Gaussian distributions on the embedding space. This encourages the model to group words that are a priori known to be semantically related into topics. To perform inference, we introduce a fast collapsed Gibbs sampling algorithm based on Cholesky decompositions of covariance matrices of the posterior predictive distributions. We further derive a scalable algorithm that draws samples from stale posterior predictive distributions and corrects them with a Metropolis–Hastings step. Using vectors learned from a domain-general corpus (English Wikipedia), we report results on two document collections (20-newsgroups and NIPS). Qualitatively, Gaussian LDA infers different (but still very sensible) topics relative to standard LDA. Quantitatively, our technique outperforms existing models at dealing with OOV words in held-out documents.

/pdf/gaussian-lda-for-topic-models-with-word-embeddings-4y5nk0j9mt.pdf

Gaussian LDA for Topic Models with Word Embeddings

Most word representation methods assume that each word owns a single semantic vector. This is usually problematic because lexical ambiguity is ubiquitous, which is also the problem to be resolved by word sense disambiguation. In this paper, we present a unified model for joint word sense representation and disambiguation, which will assign distinct representations for each word sense. 1 The basic idea is that both word sense representation (WSR) and word sense disambiguation (WSD) will benefit from each other: (1) highquality WSR will capture rich information about words and senses, which should be helpful for WSD, and (2) high-quality WSD will provide reliable disambiguated corpora for learning better sense representations. Experimental results show that, our model improves the performance of contextual word similarity compared to existing WSR methods, outperforms stateof-the-art supervised methods on domainspecific WSD, and achieves competitive performance on coarse-grained all-words WSD.

/pdf/a-unified-model-for-word-sense-representation-and-2fnqha4oq0.pdf

A Unified Model for Word Sense Representation and Disambiguation

There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type—ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its efficiency and scalability. We present new state-of-the-art results in the word similarity in context task and demonstrate its scalability by training with one machine on a corpus of nearly 1 billion tokens in less than 6 hours.

/pdf/efficient-non-parametric-estimation-of-multiple-embeddings-yk0fojez1y.pdf

Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space

There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its efficiency and scalability. We present new state-of-the-art results in the word similarity in context task and demonstrate its scalability by training with one machine on a corpus of nearly 1 billion tokens in less than 6 hours.

Jeevan Shankar

Papers

Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space

Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space