While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be learned based on only context. Moreover, it is also difficult to learn the representation of the rare words due to data sparsity problem. In this work, we address these issues by learning the representations of words by integrating their intrinsic (descriptive) and extrinsic (contextual) information. To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries,Wiki link prediction, and document classification. Experiment results show that our model is powerful in both word and document modeling.
Embedding words in a vector space has gained a lot of attention in recent years. While state-of-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation is often left unclear. In this paper, we argue that word embedding can be naturally viewed as a ranking problem due to the ranking nature of the evaluation metrics. Then, based on this insight, we propose a novel framework WordRank that efficiently estimates word representations via robust ranking, in which the attention mechanism and robustness to noise are readily achieved via the DCG-like ranking losses. The performance of WordRank is measured in word similarity and word analogy benchmarks, and the results are compared to the state-of-the-art word embedding techniques. Our algorithm is very competitive to the state-of-the- arts on large corpora, while outperforms them by a significant margin when the training set is limited (i.e., sparse and noisy). With 17 million tokens, WordRank performs almost as well as existing methods using 7.2 billion tokens on a popular word similarity benchmark. Our multi-node distributed implementation of WordRank is publicly available for general usage.
We describe a method for learning word embeddings with data-dependent dimensionality. Our Stochastic Dimensionality Skip-Gram (SD-SG) and Stochastic Dimensionality Continuous Bag-of-Words (SD-CBOW) are nonparametric analogs of Mikolov et al.'s (2013) well-known 'word2vec' models. Vector dimensionality is made dynamic by employing techniques used by Cote & Larochelle (2016) to define an RBM with an infinite number of hidden units. We show qualitatively and quantitatively that SD-SG and SD-CBOW are competitive with their fixed-dimension counterparts while providing a distribution over embedding dimensionalities, which offers a window into how semantics distribute across dimensions.
In this paper, we propose a low-rank coordinate descent approach to structured semidefinite programming with diagonal constraints. The approach, which we call the Mixing method, is extremely simple to implement, has no free parameters, and typically attains an order of magnitude or better improvement in optimization performance over the current state of the art. We show that the method is strictly decreasing, converges to a critical point, and further that for sufficient rank all non-optimal critical points are unstable. Moreover, we prove that with a step size, the Mixing method converges to the global optimum of the semidefinite program almost surely in a locally linear rate under random initialization. This is the first low-rank semidefinite programming method that has been shown to achieve a global optimum on the spherical manifold without assumption. We apply our algorithm to two related domains: solving the maximum cut semidefinite relaxation, and solving a maximum satisfiability relaxation (we also briefly consider additional applications such as learning word embeddings). In all settings, we demonstrate substantial improvement over the existing state of the art along various dimensions, and in total, this work expands the scope and scale of problems that can be solved using semidefinite programming methods.
Word embedding models such as Skip-gram learn a vector-space representation for each word, based on the local word collocation patterns that are observed in a text corpus. Latent topic models, on the other hand, take a more global view, looking at the word distributions across the corpus to assign a topic to each word occurrence. These two paradigms are complementary in how they represent the meaning of word occurrences. While some previous works have already looked at using word embeddings for improving the quality of latent topics, and conversely, at using latent topics for improving word embeddings, such "two-step" methods cannot capture the mutual interaction between the two paradigms. In this paper, we propose STE, a framework which can learn word embeddings and latent topics in a unified manner. STE naturally obtains topic-specific word embeddings, and thus addresses the issue of polysemy. At the same time, it also learns the term distributions of the topics, and the topic distributions of the documents. Our experimental results demonstrate that the STE model can indeed generate useful topic-specific word embeddings and coherent latent topics in an effective and efficient way.
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 concatenation of word embeddings, learned with different context types, can yield further performance gains. As an additional contribution, we propose a new variant of the skip-gram model that learns word embeddings from weighted contexts of substitute words.
Existing approaches to automatic VerbNet-style verb classification are heavily dependent on feature engineering and therefore limited to languages with mature NLP pipelines. In this work, we propose a novel cross-lingual transfer method for inducing VerbNets for multiple languages. To the best of our knowledge, this is the first study which demonstrates how the architectures for learning word embeddings can be applied to this challenging syntactic-semantic task. Our method uses cross-lingual translation pairs to tie each of the six target languages into a bilingual vector space with English, jointly specialising the representations to encode the relational information from English VerbNet. A standard clustering algorithm is then run on top of the VerbNet-specialised representations, using vector dimensions as features for learning verb classes. Our results show that the proposed cross-lingual transfer approach sets new state-of-the-art verb classification performance across all six target languages explored in this work.
Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings learn vector representations from large corpora of text documents in an unsu- pervised fashion. This paper introduces SWESA (Supervised Word Embeddings for Sentiment Analysis), an algorithm for sentiment analysis via word embeddings. SWESA leverages document label infor- mation to learn vector representations of words from a modest corpus of text doc- uments by solving an optimization prob- lem that minimizes a cost function with respect to both word embeddings as well as classification accuracy. Analysis re- veals that SWESA provides an efficient way of estimating the dimension of the word embeddings that are to be learned. Experiments on several real world data sets show that SWESA has superior per- formance when compared to previously suggested approaches to word embeddings and sentiment analysis tasks.
Co-occurrences between two words provide useful insights into the semantics of those words. Consequently, numerous prior work on word embedding learning have used co-occurrences between two words as the training signal for learning word embeddings. However, in natural language texts it is common for multiple words to be related and co-occurring in the same context. We extend the notion of co-occurrences to cover $k(\geq\!\!2)$-way co-occurrences among a set of $k$-words. Specifically, we prove a theoretical relationship between the joint probability of $k(\geq\!\!2)$ words, and the sum of $\ell_2$ norms of their embeddings. Next, we propose a learning objective motivated by our theoretical result that utilises $k$-way co-occurrences for learning word embeddings. Our experimental results show that the derived theoretical relationship does indeed hold empirically, and despite data sparsity, for some smaller $k$ values, $k$-way embeddings perform comparably or better than $2$-way embeddings in a range of tasks.
This paper describes a preliminary study for producing and distributing a large-scale database of embeddings from the Portuguese Twitter stream. We start by experimenting with a relatively small sample and focusing on three challenges: volume of training data, vocabulary size and intrinsic evaluation metrics. Using a single GPU, we were able to scale up vocabulary size from 2048 words embedded and 500K training examples to 32768 words over 10M training examples while keeping a stable validation loss and approximately linear trend on training time per epoch. We also observed that using less than 50\% of the available training examples for each vocabulary size might result in overfitting. Results on intrinsic evaluation show promising performance for a vocabulary size of 32768 words. Nevertheless, intrinsic evaluation metrics suffer from over-sensitivity to their corresponding cosine similarity thresholds, indicating that a wider range of metrics need to be developed to track progress.
Lexical entailment, such as hyponymy, is a fundamental issue in the semantics of natural language. This paper proposes distributional semantic models which efficiently learn word embeddings for entailment, using a recently-proposed framework for modelling entailment in a vector-space. These models postulate a latent vector for a pseudo-phrase containing two neighbouring word vectors. We investigate both modelling words as the evidence they contribute about this phrase vector, or as the posterior distribution of a one-word phrase vector, and find that the posterior vectors perform better. The resulting word embeddings outperform the best previous results on predicting hyponymy between words, in unsupervised and semi-supervised experiments.
In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the segments, and are close to other vectors in the embedding space if their corresponding segments are semantically similar. The design of the proposed model is based on the RNN Encoder-Decoder framework, and borrows the methodology of continuous skip-grams for training. The learned vector representations are evaluated on 13 widely used word similarity benchmarks, and achieved competitive results to that of GloVe. The biggest advantage of the proposed model is its capability of extracting semantic information of audio segments taken directly from raw speech, without relying on any other modalities such as text or images, which are challenging and expensive to collect and annotate.
Learning by contrasting positive and negative samples is a general strategy adopted by many methods. Noise contrastive estimation (NCE) for word embeddings and translating embeddings for knowledge graphs are examples in NLP employing this approach. In this work, we view contrastive learning as an abstraction of all such methods and augment the negative sampler into a mixture distribution containing an adversarially learned sampler. The resulting adaptive sampler finds harder negative examples, which forces the main model to learn a better representation of the data. We evaluate our proposal on learning word embeddings, order embeddings and knowledge graph embeddings and observe both faster convergence and improved results on multiple metrics.
In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the underlying spoken words, and are close to other vectors in the embedding space if their corresponding underlying spoken words are semantically similar. The proposed model can be viewed as a speech version of Word2Vec. Its design is based on a RNN Encoder-Decoder framework, and borrows the methodology of skipgrams or continuous bag-of-words for training. Learning word embeddings directly from speech enables Speech2Vec to make use of the semantic information carried by speech that does not exist in plain text. The learned word embeddings are evaluated and analyzed on 13 widely used word similarity benchmarks, and outperform word embeddings learned by Word2Vec from the transcriptions.
비정형 텍스트는 소매업의 제품 리뷰부터 의료 분야의 간호 기록에 이르기까지 다양한 도메인에서 의사결정권자에게 풍부한 데이터 소스를 제공합니다. 이 정보를 활용하기 위해 단어는 일반적으로 행렬 분해와 같은 비지도 학습 알고리즘을 통해 단어 임베딩(word embeddings, 단어 간의 의미적 관계를 인코딩하는 벡터)으로 변환됩니다. 그러나 학습 데이터가 제한된 새로운 도메인에서 단어 임베딩을 학습하는 것은 어려울 수 있는데, 이는 새로운 도메인에서 단어의 의미나 사용법이 달라질 수 있기 때문입니다. 예를 들어, 'positive'라는 단어는 일반적으로 긍정적인 감정을 나타내지만, 환자가 특정 질병에 대해 양성 반응을 보였음을 의미할 수 있으므로 의료 기록에서는 종종 부정적인 감정을 나타냅니다. 실제로 우리는 소수의 도메인 특정 단어만이 새로운 의미를 가질 것으로 기대합니다. 우리는 그룹 희소 페널티(group-sparse penalty)를 통해 이러한 구조를 활용하여, 대규모 텍스트 말뭉치(예: 위키피디아)와 제한된 도메인 특정 텍스트 데이터를 결합함으로써 도메인 특정 단어 임베딩을 효율적으로 전이 학습할 수 있는 직관적인 2단계 추정기를 제안합니다. 우리는 전이 학습 추정기의 일반화 오차를 한정하고, 도메인 간에 소수의 임베딩만 변경되는 경우 훨씬 적은 도메인 특정 데이터로도 높은 정확도를 달성할 수 있음을 증명합니다. 또한, 표준 정규화 조건 하에서 우리의 비볼록 목적 함수가 식별하는 모든 국소 최솟값이 전역 최솟값과 통계적으로 구별할 수 없음을 증명하여, 해당 추정기를 효율적으로 계산할 수 있음을 시사합니다. 우리의 결과는 그룹 희소 행렬 분해에 대한 첫 번째 한계(bounds)를 제공하며, 이는 그 자체로도 독립적인 관심사가 될 수 있습니다. 우리는 자연어 처리(NLP) 분야의 최첨단 미세조정 휴리스틱과 비교하여 우리의 접근 방식을 실증적으로 평가합니다.