Riemannian Optimization for Skip-Gram Negative Sampling
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Yandex LLC（Yandex有限责任公司）；SBDA Group（SBDA集团）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Institute of Numerical Mathematics, Russian Academy of Sciences（俄罗斯科学院数值数学研究所）
Alexander Fonarev, Oleksii Hrinchuk, Gleb Gusev, Pavel Serdyukov, Ivan Oseledets
Skip-Gram Negative Sampling (SGNS) word embedding model, well known by its implementation in "word2vec" software, is usually optimized by stochastic gradient descent. However, the optimization of SGNS objective can be viewed as a problem of searching for a good matrix with the low-rank constraint. The most standard way to solve this type of problems is to apply Riemannian optimization framework to optimize the SGNS objective over the manifold of required low-rank matrices. In this paper, we propose an algorithm that optimizes SGNS objective using Riemannian optimization and demonstrates its superiority over popular competitors, such as the original method to train SGNS and SVD over SPPMI matrix.
We show that the skip-gram embedding of any word can be decomposed into two subvectors which roughly correspond to semantic and syntactic roles of the word.
The paper proves that the number of k-skip-n-grams for a corpus of size $L$ is $$\frac{Ln + n + k' - n^2 - nk'}{n} \cdot \binom{n-1+k'}{n-1}$$ where $k' = \min(L - n + 1, k)$.
Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained popularity in various areas of natural language processing, because it seems to capture syntactic and semantic information about words without any explicit supervision in this respect. We propose SubGram, a refinement of the Skip-gram model to consider also the word structure during the training process, achieving large gains on the Skip-gram original test set.
Recently proposed Skip-gram model is a powerful method for learning high-dimensional word representations that capture rich semantic relationships between words. However, Skip-gram as well as most prior work on learning word representations does not take into account word ambiguity and maintain only single representation per word. Although a number of Skip-gram modifications were proposed to overcome this limitation and learn multi-prototype word representations, they either require a known number of word meanings or learn them using greedy heuristic approaches. In this paper we propose the Ad…
To improve the generalization of the representations for natural language processing tasks, words are commonly represented using vectors, where distances among the vectors are related to the similarity of the words. While word2vec, the state-of-the-art implementation of the skip-gram model, is widely used and improves the performance of many natural language processing tasks, its mechanism is not yet well understood. In this work, we derive the learning rules for the skip-gram model and establish their close relationship to competitive learning. In addition, we provide the global optimal solut…
Institute for Natural Language Processing, University of Stuttgart（斯图加特大学自然语言处理研究所）
We simulate first- and second-order context overlap and show that Skip-Gram with Negative Sampling is similar to Singular Value Decomposition in capturing second-order co-occurrence information, while Pointwise Mutual Information is agnostic to it. We support the results with an empirical study finding that the models react differently when provided with additional second-order information. Our findings reveal a basic property of Skip-Gram with Negative Sampling and point towards an explanation of its success on a variety of tasks.
In this paper, we introduce a variation of the skip-gram model which jointly learns distributed word vector representations and their way of composing to form phrase embeddings. In particular, we propose a learning procedure that incorporates a phrase-compositionality function which can capture how we want to compose phrases vectors from their component word vectors. Our experiments show improvement in word and phrase similarity tasks as well as syntactic tasks like dependency parsing using the proposed joint models.
This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives. Existing methods of neural word embeddings, including SGNS, are multi-pass algorithms and thus cannot perform incremental model update. To address this problem, we present a simple incremental extension of SGNS and provide a thorough theoretical analysis to demonstrate its validity. Empirical experiments demonstrated the correctness of the theoretical analysis as well as the practical usefulness of the incremental algorithm.
Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned embeddings are real number vectors, which are obscure to human. In this paper, we propose an Image-Enhanced Skip-Gram Model to learn grounded word embeddings by representing the word vectors in the same hyper-plane with image vectors. Experiments show that the image vectors and word embeddings learned by our model are highly correlated, which indicates that our …
Battelle Health and Analytics（巴特尔健康与分析）；Battelle Cyber Innovations（巴特尔网络创新）
We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding methods, and extend it to higher dimensional models.
Predicting Mild Cognitive Impairment (MCI) is currently a challenge as existing diagnostic criteria rely on neuropsychological examinations. Automated Machine Learning (ML) models that are trained on verbal utterances of MCI patients can aid diagnosis. Using a combination of skip-gram features, our model learned several linguistic biomarkers to distinguish between 19 patients with MCI and 19 healthy control individuals from the DementiaBank language transcript clinical dataset. Results show that a model with compound of skip-grams has better AUC and could help ML prediction on small MCI data s…
Institute for Web Science and Technologies（网络科学与技术研究所）；University of Koblenz-Landau（科布伦茨-兰道大学）；Typology GbR
We introduce a novel approach for building language models based on a systematic, recursive exploration of skip n-gram models which are interpolated using modified Kneser-Ney smoothing. Our approach generalizes language models as it contains the classical interpolation with lower order models as a special case. In this paper we motivate, formalize and present our approach. In an extensive empirical experiment over English text corpora we demonstrate that our generalized language models lead to a substantial reduction of perplexity between 3.1% and 12.7% in comparison to traditional language mo…
We present a novel family of language model (LM) estimation techniques named Sparse Non-negative Matrix (SNM) estimation. A first set of experiments empirically evaluating it on the One Billion Word Benchmark shows that SNM $n$-gram LMs perform almost as well as the well-established Kneser-Ney (KN) models. When using skip-gram features the models are able to match the state-of-the-art recurrent neural network (RNN) LMs; combining the two modeling techniques yields the best known result on the benchmark. The computational advantages of SNM over both maximum entropy and RNN LM estimation are pro…
Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value vector space, which have obtained high performance in NLP tasks. However, most of the existing models assume the result trained by one of them are perfect correct and used as prior knowledge for improving the other model. Some other models use the information trained from external large corpus to help improving smaller corpus. In this paper, we aim to build…
Center for Mind/Brain Sciences（心智/脑科学中心）；University of Trento（特伦托大学）
We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account. Like SKIP-GRAM, our multimodal models (MMSKIP-GRAM) build vector-based word representations by learning to predict linguistic contexts in text corpora. However, for a restricted set of words, the models are also exposed to visual representations of the objects they denote (extracted from natural images), and must predict linguistic and visual features jointly. The MMSKIP-GRAM models achieve good performance on a variety of semantic benchmarks. Moreover, since they propagate visual information to …
Mikolov et al. (2013a) observed that continuous bag-of-words (CBOW) word embeddings tend to underperform Skip-gram (SG) embeddings, and this finding has been reported in subsequent works. We find that these observations are driven not by fundamental differences in their training objectives, but more likely on faulty negative sampling CBOW implementations in popular libraries such as the official implementation, word2vec.c, and Gensim. We show that after correcting a bug in the CBOW gradient update, one can learn CBOW word embeddings that are fully competitive with SG on various intrinsic and e…
This work studies the representational mapping across multimodal data such that given a piece of the raw data in one modality the corresponding semantic description in terms of the raw data in another modality is immediately obtained. Such a representational mapping can be found in a wide spectrum of real-world applications including image/video retrieval, object recognition, action/behavior recognition, and event understanding and prediction. To that end, we introduce a simplified training objective for learning multimodal embeddings using the skip-gram architecture by introducing convolution…
University of Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Coffreo（Coffreo公司）
We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification scenarios with thousands of classes has not been extensively researched, partially due to hardware limitations. In this work, we examine efficient composition functions to obtain document-level from word-level embeddings and we subsequently investigate their combination with the traditional one-hot-encoding representations. By presenting empirical evidence on large,…
We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network based approaches to learning distributed word representation. We first point out the ambiguity issue undermining the SGNS model, in the sense that the word vectors can be entirely distorted without changing the objective value. To resolve the issue, we investigate the intrinsic structures in solution that a good word embedding model should deliver. Motivated by this, we rectify the SGNS model with quadratic regularization, and show that this simple modification suffices to structure the solution in the desire…
Recent work has demonstrated that embeddings of tree-like graphs in hyperbolic space surpass their Euclidean counterparts in performance by a large margin. Inspired by these results and scale-free structure in the word co-occurrence graph, we present an algorithm for learning word embeddings in hyperbolic space from free text. An objective function based on the hyperbolic distance is derived and included in the skip-gram negative-sampling architecture of word2vec. The hyperbolic word embeddings are then evaluated on word similarity and analogy benchmarks. The results demonstrate the potential …
In this report, we propose a new application for twitter data called \textit{job detection}. We identify people's job category based on their tweets. As a preliminary work, we limited our task to identify only IT workers from other job holders. We have used and compared both simple bag of words model and a document representation based on Skip-gram model. Our results show that the model based on Skip-gram, achieves a 76\% precision and 82\% recall.
Verbal metonymy has received relatively scarce attention in the field of computational linguistics despite the fact that a model to accurately paraphrase metonymy has applications both in academia and the technology sector. The method described in this paper makes use of data from the British National Corpus in order to create word vectors, find instances of verbal metonymy and generate potential paraphrases. Two different ways of creating word vectors are evaluated in this study: Continuous bag of words and Skip-grams. Skip-grams are found to outperform the Continuous bag of words approach. F…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Georgia Institute of Technology（佐治亚理工学院）；University of California San Diego（加州大学圣地亚哥分校）
Set expansion aims to expand a small set of seed entities into a complete set of relevant entities. Most existing approaches assume the input seed set is unambiguous and completely ignore the multi-faceted semantics of seed entities. As a result, given the seed set {"Canon", "Sony", "Nikon"}, previous models return one mixed set of entities that are either Camera Brands or Japanese Companies. In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet. We propose an …
The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less relevant words could be in the context window, hindering the SG model from learning a better quality representation. In this paper, we propose an enhanced version of the SG that leverages context information to produce word representation. The proposed model, Contextual Skip-gram, is designed to predict contextual words with both the center words and the con…
Recently, several works in the domain of natural language processing presented successful methods for word embedding. Among them, the Skip-Gram with negative sampling, known also as word2vec, advanced the state-of-the-art of various linguistics tasks. In this paper, we propose a scalable Bayesian neural word embedding algorithm. The algorithm relies on a Variational Bayes solution for the Skip-Gram objective and a detailed step by step description is provided. We present experimental results that demonstrate the performance of the proposed algorithm for word analogy and similarity tasks on six…
Federal University of Pernambuco（伯南布哥联邦大学）；Federal University of Sergipe（塞尔希培联邦大学）
Natural language processing models have attracted much interest in the deep learning community. This branch of study is composed of some applications such as machine translation, sentiment analysis, named entity recognition, question and answer, and others. Word embeddings are continuous word representations, they are an essential module for those applications and are generally used as input word representation to the deep learning models. Word2Vec and GloVe are two popular methods to learn word embeddings. They achieve good word representations, however, they learn representations with limite…
In this paper, we propose a novel information criteria-based approach to select the dimensionality of the word2vec Skip-gram (SG). From the perspective of the probability theory, SG is considered as an implicit probability distribution estimation under the assumption that there exists a true contextual distribution among words. Therefore, we apply information criteria with the aim of selecting the best dimensionality so that the corresponding model can be as close as possible to the true distribution. We examine the following information criteria for the dimensionality selection problem: the A…
Eliciting semantic similarity between concepts in the biomedical domain remains a challenging task. Recent approaches founded on embedding vectors have gained in popularity as they risen to efficiently capture semantic relationships The underlying idea is that two words that have close meaning gather similar contexts. In this study, we propose a new neural network model named MeSH-gram which relies on a straighforward approach that extends the skip-gram neural network model by considering MeSH (Medical Subject Headings) descriptors instead words. Trained on publicly available corpus PubMed MED…
University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）
We introduce a method for embedding words as probability densities in a low-dimensional space. Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods, in our Bayesian model we generate it from a word-specific prior density for each occurrence of a given word. Intuitively, for each word, the prior density encodes the distribution of its potential 'meanings'. These prior densities are conceptually similar to Gaussian embeddings. Interestingly, unlike the Gaussian embeddings, we can also obtain context-specific densities: they …
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
Artificial neural networks are a state-of-the-art solution for many problems in natural language processing. What can we learn about language and meaning from the way artificial neural networks represent it? Word representations obtained from the Skip-gram variant of the word2vec model exhibit interesting semantic properties. This is usually explained by referring to the general distributional hypothesis, which states that the meaning of the word is given by the contexts where it occurs. We propose a more specific approach based on Frege's holistic and functional approach to meaning. Taking Tu…
IBM Watson（IBM沃森）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Bar-Ilan University（巴伊兰大学）；Google（谷歌）
We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks. Our results suggest that while intrinsic tasks tend to exhibit a clear preference to particular types of contexts and higher dimensionality, more careful tuning is required for finding the optimal settings for most of the extrinsic tasks that we considered. Furthermore, for these extrinsic tasks, we find that once the benefit from increasing the embedding dimensionality is mostly exhausted, simple concaten…
Idiap Research Institute（Idiap研究所）；Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Facebook AI Research（Facebook人工智能研究院）
The bag-of-words (BOW) model is the common approach for classifying documents, where words are used as feature for training a classifier. This generally involves a huge number of features. Some techniques, such as Latent Semantic Analysis (LSA) or Latent Dirichlet Allocation (LDA), have been designed to summarize documents in a lower dimension with the least semantic information loss. Some semantic information is nevertheless always lost, since only words are considered. Instead, we aim at using information coming from n-grams to overcome this limitation, while remaining in a low-dimension spa…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability. In this paper, we aim to improve word embeddings by 1) incorporating more contextual information from existing pre-trained models into the Skip-gram framework, which we call Context-to-Vec; 2) proposing a post-processing retrofitting method for static embeddings independent of training by e…
University of Science and Technology of China（中国科学技术大学）；Tencent YouTu Lab（腾讯优图实验室）
The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and avoid over-correction, previous sequence-to-sequence (seq2seq) models generate results from scratch, which are not guaranteed to follow the original sentence structure and may suffer from the over-correction problem. In the meantime, the recently proposed sequence tagging models can overcome the over-correction problem by only generating edit operations, but…
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）；Atypon Systems（Atypon系统公司）
Word embedding models such as the skip-gram learn vector representations of words' semantic relationships, and document embedding models learn similar representations for documents. On the other hand, topic models provide latent representations of the documents' topical themes. To get the benefits of these representations simultaneously, we propose a unifying algorithm, called neural embedding allocation (NEA), which deconstructs topic models into interpretable vector-space embeddings of words, topics, documents, authors, and so on, by learning neural embeddings to mimic the topic models. We s…
We describe Sparse Non-negative Matrix (SNM) language model estimation using multinomial loss on held-out data. Being able to train on held-out data is important in practical situations where the training data is usually mismatched from the held-out/test data. It is also less constrained than the previous training algorithm using leave-one-out on training data: it allows the use of richer meta-features in the adjustment model, e.g. the diversity counts used by Kneser-Ney smoothing which would be difficult to deal with correctly in leave-one-out training. In experiments on the one billion words…
The Global Vectors for word representation (GloVe), introduced by Jeffrey Pennington et al. is reported to be an efficient and effective method for learning vector representations of words. State-of-the-art performance is also provided by skip-gram with negative-sampling (SGNS) implemented in the word2vec tool. In this note, we explain the similarities between the training objectives of the two models, and show that the objective of SGNS is similar to the objective of a specialized form of GloVe, though their cost functions are defined differently.
University of Glagow（格拉斯哥大学）；Shanghai Jiao Tong University（上海交通大学）
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skipgram model without a proper negative sampler. By performing an insightful analysis from the stochastic gradient descent (SGD) learning perspective, we demonstrate that, both theoretically and intuitively, negative samples with larger inner product scores are more informative than…
Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the same tasks, recommendation applications tend to use the same already tuned hyperparameters values, even if optimal hyperparameters values are often known to be data and task dependent. We thus investigate the marginal importance of each hyperparameter in a recommendation setting …
