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.
Study finds optimal vocabulary size for neural machine translation.
New analysis shows optimal embedding learning rate depends on vocabulary size, not just model width.
Recommendation problems with large numbers of discrete items, such as products, webpages, or videos, are ubiquitous in the technology industry. Deep neural networks are being increasingly used for these recommendation problems. These models use embeddings to represent discrete items as continuous vectors, and the vocab…
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (R…
ANT learns sparse embeddings for large vocabularies efficiently.
Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it …
A Bloom filter approach combined with Transformer models improves accuracy for machine learning tasks on opaque IDs.
In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian spa…
Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing inp…
The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent types; and it has a large memory footprint. We propose a general technique for rep…
Paper reduces vocabulary losslessly for language model cooperation.
This study analyzes data science vocabulary changes over 13 years.
In the era of big data, learning from categorical features with very large vocabularies (e.g., 28 million for the Criteo click prediction dataset) has become a practical challenge for machine learning researchers and practitioners. We design a highly-scalable vocabulary compression algorithm that seeks to maximize the …
Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in turn determine model size, computational costs of softmax normalization, and han…
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
With the rise of social media, people can now form relationships and communities easily regardless of location, race, ethnicity, or gender. However, the power of social media simultaneously enables harmful online behavior such as harassment and bullying. Cyberbullying is a serious social problem, making it an important…
The restricted Boltzmann machine (RBM) is a flexible tool for modeling complex data, however there have been significant computational difficulties in using RBMs to model high-dimensional multinomial observations. In natural language processing applications, words are naturally modeled by K-ary discrete distributions, …
Study shows how transformers classify symbols without naming them, proving a margin-versus-collision criterion.
We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
The novel unseen classes can be formulated as the extreme values of known classes. This inspired the recent works on open-set recognition \cite{Scheirer_2013_TPAMI,Scheirer_2014_TPAMIb,EVM}, which however can have no way of naming the novel unseen classes. To solve this problem, we propose the Extreme Value Learning (E…
In this paper we demonstrate continuous noisy speech recognition using connectionist temporal classification (CTC) model on limited Chinese vocabulary using electroencephalography (EEG) features with no speech signal as input and we further demonstrate single CTC model based continuous noisy speech recognition on limit…
The study examines label smoothing to improve confidence calibration in fine-tuned LLMs.
The goal of eXtreme Multi-label Learning (XML) is to automatically annotate a given data point with the most relevant subset of labels from an extremely large vocabulary of labels (e.g., a million labels). Lately, many attempts have been made to address this problem that achieve reasonable performance on benchmark data…
This work reduces the dimensionality of text data using SVD, improving performance and computational efficiency.
Unified framework for convergence of discrete diffusion models without state space size dependence.
We focus on the problem of search in the multilingual setting. Examining the problems of next-sentence prediction and inverse cloze, we show that at large scale, instance-based transfer learning is surprisingly effective in the multilingual setting, leading to positive transfer on all of the 35 target languages and two…
This work compares and evaluates various sampling methods for neural language models.
Training-free source selection for LLM families with shared vocabularies
Abstraction is a fundamental part when learning behavioral models of systems. Usually the process of abstraction is manually defined by domain experts. This paper presents a method to perform automatic abstraction for network protocols. In particular a weakly supervised clustering algorithm is used to build an abstract…
Estimates unknown population sizes using the hypergeometric distribution.
Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design of small, low-footprint deep neural networks (DNNs) that are more appropriate fo…
In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it wi…
Markov chain Monte Carlo (MCMC) algorithms are ubiquitous in probability theory in general and in machine learning in particular. A Markov chain is devised so that its stationary distribution is some probability distribution of interest. Then one samples from the given distribution by running the Markov chain for a "lo…
Trains word embeddings from music and text data to link music contexts.
Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary i…
Scientific publications have evolved several features for mitigating vocabulary mismatch when indexing, retrieving, and computing similarity between articles. These mitigation strategies range from simply focusing on high-value article sections, such as titles and abstracts, to assigning keywords, often from controlled…
In order to successfully model Long Distance Dependencies (LDDs) it is necessary to understand the full-range of the characteristics of the LDDs exhibited in a target dataset. In this paper, we use Strictly k-Piecewise languages to generate datasets with various properties. We then compute the characteristics of the LD…
New algorithms for set union in differential privacy improve efficiency and accuracy.
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs)…
With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single embedding is learned for every word in the vocabulary, the model fails to optimally re…
Hidden Markov Models (HMMs) can be accurately approximated using co-occurrence frequencies of pairs and triples of observations by using a fast spectral method in contrast to the usual slow methods like EM or Gibbs sampling. We provide a new spectral method which significantly reduces the number of model parameters tha…
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are …
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary s…
Enhanced word embedding creates new consumer-friendly health terms.
We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new sampling strategy which significantly reduces computation while improving stability, …
Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional…
This paper shows that scientific discovery can be efficiently learned via compositional function trees, reducing the sample complexity.