Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSparse Attention with Linear Units
109
0
0.0
(
0
)
Added by
Biao Zhang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than previously proposed sparse attention mechanisms. We apply ReLA to the Transformer and conduct experiments on five machine translation tasks. ReLA achieves translation performance comparable to several strong baselines, with training and decoding speed similar to that of the vanilla attention. Our analysis shows that ReLA delivers high sparsity rate and head diversity, and the induced cross attention achieves better accuracy with respect to source-target word alignment than recent sparsified softmax-based models. Intriguingly, ReLA heads also learn to attend to nothing (i.e. switch off) for some queries, which is not possible with sparsified softmax alternatives.
rate research
Read More
Characters do not convey meaning, but sequences of characters do. We propose an unsupervised distributional method to learn the abstract meaning-bearing units in a sequence of characters. Rather than segmenting the sequence, this model discovers continuous representations of the objects in the sequence, using a recently proposed architecture for object discovery in images called Slot Attention. We train our model on different languages and evaluate the quality of the obtained representations with probing classifiers. Our experiments show promising results in the ability of our units to capture meaning at a higher level of abstraction.
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of irrelevant information in the context. To tackle the problem, we propose a novel model called textbf{Explicit Sparse Transformer}. Explicit Sparse Transformer is able to improve the concentration of attention on the global context through an explicit selection of the most relevant segments. Extensive experimental results on a series of natural language processing and computer vision tasks, including neural machine translation, image captioning, and language modeling, all demonstrate the advantages of Explicit Sparse Transformer in model performance. We also show that our proposed sparse attention method achieves comparable or better results than the previous sparse attention method, but significantly reduces training and testing time. For example, the inference speed is twice that of sparsemax in Transformer model. Code will be available at url{https://github.com/lancopku/Explicit-Sparse-Transformer}
We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. Previous work addresses the problem by training an attention-based sequence-to-sequence model that maps source speech spectrograms into target spectrograms. To tackle the challenge of modeling continuous spectrogram features of the target speech, we propose to predict the self-supervised discrete representations learned from an unlabeled speech corpus instead. When target text transcripts are available, we design a multitask learning framework with joint speech and text training that enables the model to generate dual mode output (speech and text) simultaneously in the same inference pass. Experiments on the Fisher Spanish-English dataset show that predicting discrete units and joint speech and text training improve model performance by 11 BLEU compared with a baseline that predicts spectrograms and bridges 83% of the performance gap towards a cascaded system. When trained without any text transcripts, our model achieves similar performance as a baseline that predicts spectrograms and is trained with text data.
Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs themselves, suggesting this assumption may not have merit. We build on the recent work exploring the interpretability of attention; we design a set of experiments to help us understand how sparsity affects our ability to use attention as an explainability tool. On three text classification tasks, we verify that only a weak relationship between inputs and co-indexed intermediate representations exists -- under sparse attention and otherwise. Further, we do not find any plausible mappings from sparse attention distributions to a sparse set of influential inputs through other avenues. Rather, we observe in this setting that inducing sparsity may make it less plausible that attention can be used as a tool for understanding model behavior.
This paper proposes a fast and accurate method for sparse regression in the presence of missing data. The underlying statistical model encapsulates the low-dimensional structure of the incomplete data matrix and the sparsity of the regression coefficients, and the proposed algorithm jointly learns the low-dimensional structure of the data and a linear regressor with sparse coefficients. The proposed stochastic optimization method, Sparse Linear Regression with Missing Data (SLRM), performs an alternating minimization procedure and scales well with the problem size. Large deviation inequalities shed light on the impact of the various problem-dependent parameters on the expected squared loss of the learned regressor. Extensive simulations on both synthetic and real datasets show that SLRM performs better than competing algorithms in a variety of contexts.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
