A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
Attention layers are sensitive to single words, improving generalization over random features.
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…
Transformers' self-attention mechanism is mapped to a generalized Potts model.
Improves dialogue response model interpretability using attention and regularization.
Enhanced neural model detects misinformation by considering author context.
Transformer++ improves neural machine translation BLEU scores.
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art …
A new method for document network embedding interprets and generalizes well.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
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 rank…
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system performance is usually measured in terms of word error rate (WER), not log-likel…
The Generative Adversarial Network (GAN) has recently been applied to generate synthetic images from text. Despite significant advances, most current state-of-the-art algorithms are regular-grid region based; when attention is used, it is mainly applied between individual regular-grid regions and a word. These approach…
Transformer models align words through attention weights, closely approximating Optimal Transport.
Model learns image-word associations from captions using contrastive learning.
Streaming ASR with transformer achieves low WER.
Transformers cluster meaningless words around leaders for sentiment analysis.
We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the m…
Attention networks show promise for both vision and language tasks, by emphasizing relationships between constituent elements through weighting functions. Such elements could be regions in an image output by a region proposal network, or words in a sentence, represented by word embedding. Thus far the learning of atten…
Dual-attention GCN improves text classification by adapting to textual complexity.
Paper introduces regularization for multi-head attention to spot keywords.
PoWER-BERT speeds up BERT inference by eliminating redundant word-vectors.
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
Approaches KL divergence for learning multi-sense word distributions.
Transformers learn topic structure through embedding and attention mechanisms.
Paper proposes a faster neural machine translation model using election methods and Q-learning.
Enhances image captioning with novel context combination methods.
With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words re…
This study compares hierarchical and non-hierarchical models for open-domain multi-turn dialog generation.
CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance sem…
Method learns audio embeddings with contextualized tags.
This paper tackles rare word problem in low-resource language pairs using NMT.
Paper uses JIVE to decompose word embeddings, improving sentiment analysis performance.
In this paper, we present a novel approach for incorporating external knowledge in Recurrent Neural Networks (RNNs). We propose the integration of lexicon features into the self-attention mechanism of RNN-based architectures. This form of conditioning on the attention distribution, enforces the contribution of the most…
Direct acoustics-to-word (A2W) models in the end-to-end paradigm have received increasing attention compared to conventional sub-word based automatic speech recognition models using phones, characters, or context-dependent hidden Markov model states. This is because A2W models recognize words from speech without any de…
Neural machine translation (NMT) systems have been shown to give undesirable translation when a small change is made in the source sentence. In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence. In particular, we ask the following question "Is it possible for an NMT…
This paper assesses biases in contextualized word representations.
Time Series Motif Discovery (TSMD) is defined as searching for patterns that are previously unknown and appear with a given frequency in time series. Another problem strongly related with TSMD is Word Segmentation. This problem has received much attention from the community that studies early language acquisition in ba…
Paper proposes multiscale self-attentive convolutions for vision and language.
Paper identifies and solves a 'scrambled translation' issue in UNMT models.
Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long term dependencies and are often regarded as the key ingredient in the success of…
Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system that exploits the parallel structures between images and sentences. In our model, …
Enhanced Transformer solves math problems better with explicit relation encoding.
Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend to areas in the memory, where each area contains a group of items that are structurally adjacent, e.g…
Extreme multi-label text classification (XMTC) addresses the problem of tagging each text with the most relevant labels from an extreme-scale label set. Traditional methods use bag-of-words (BOW) representations without context information as their features. The state-ot-the-art deep learning-based method, AttentionXML…
The paper approaches the task of handwritten text recognition (HTR) with attentional encoder-decoder networks trained on sequences of characters, rather than words. We experiment on lines of text from popular handwriting datasets and compare different activation functions for the attention mechanism used for aligning i…
This paper describes the system developed at Amobee for the WASSA 2018 implicit emotions shared task (IEST). The goal of this task was to predict the emotion expressed by missing words in tweets without an explicit mention of those words. We developed an ensemble system consisting of language models together with LSTM-…
Improved TF-IDF for word relevance in health-care social media documents.