相关论文: PMI Matrix Approximations with Applications to Neu…

Word representation is fundamental in NLP tasks, because it is precisely from the coding of semantic closeness between words that it is possible to think of teaching a machine to understand text. Despite the spread of word embedding…

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…

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based…

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative embeddings are derived from user-defined negative prompts,…

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that have been replaced…

Uncontextualized word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Given the historical success of word embeddings in NLP, we propose a retrospective on some of…

In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This…

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…

ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP…

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word…

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…

Word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Uncontextualized word embeddings are used in many NLP tasks today, especially in resource-limited settings where…

Training energy-based models (EBMs) with noise-contrastive estimation (NCE) is theoretically feasible but practically challenging. Effective learning requires the noise distribution to be approximately similar to the target distribution,…

Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources. While this is easy for humans, the present neural methods that rely on learned word embeddings…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and…

Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper…

In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we…