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.
Research improves federated text models for next word prediction.
Language models help text classification tasks by predicting next words.
Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context l…
Proving that next-token prediction makes language models generate coherent long documents.
Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as second…
Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates in the softmax layer…
Paper introduces a benchmark for predicting bankruptcy from text data.
Models of bags of words typically assume topic mixing so that the words in a single bag come from a limited number of topics. We show here that many sets of bag of words exhibit a very different pattern of variation than the patterns that are efficiently captured by topic mixing. In many cases, from one bag of words to…
It is common in modern prediction problems for many predictor variables to be counts of rarely occurring events. This leads to design matrices in which many columns are highly sparse. The challenge posed by such "rare features" has received little attention despite its prevalence in diverse areas, ranging from natural …
This paper takes a step towards theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec. We start from basic probabilistic assumptions on the nature of word vectors, context vectors, and text generation. These assumptions are well supported either empirically o…
Paper trains language models without memorizing user data.
User-generated reviews can be decomposed into fine-grained segments (e.g., sentences, clauses), each evaluating a different aspect of the principal entity (e.g., price, quality, appearance). Automatically detecting these aspects can be useful for both users and downstream opinion mining applications. Current supervised…
Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, w…
We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs. Using several examples, we show that the network can associate distant causes and effects in a discrete stochastic process, predict partially-observable higher-order sequences, and enable a DQN a…
We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while training a model. GROVER first starts from conventional training process, and th…
CNN predicts stock fluctuations using company news headlines.
Local adaptation improves federated learning models.
Paper presents ECL dataset for multi-modal bankruptcy prediction.
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…
The problem is sequence prediction in the following setting. A sequence x1,..., xn,... of discrete-valued observations is generated according to some unknown probabilistic law (measure) mu. After observing each outcome, it is required to give the conditional probabilities of the next observation. The measure mu belongs…
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN),…
This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning representations of words called Multiview Latent Semantic Analysis (MVLSA). By incorporating u…
LLMs encode latent topic distributions, suggesting Bayesian inference.
Community detection is a fundamental task in social network analysis. In this paper, first we develop an endorsement filtered user connectivity network by utilizing Heider's structural balance theory and certain Twitter triad patterns. Next, we develop three Nonnegative Matrix Factorization frameworks to investigate th…
In this paper, we try to explore the evolution of language through case calculations. First, we chose the novels of eleven British writers from 1400 to 2005 and found the corresponding works; Then, we use the natural language processing tool to construct the corresponding eleven corpora, and calculate the respective wo…
The abstract explains how word and relation representations capture semantic meaning.
Which song will Smith listen to next? Which restaurant will Alice go to tomorrow? Which product will John click next? These applications have in common the prediction of user trajectories that are in a constant state of flux over a hidden network (e.g. website links, geographic location). What users are doing now may b…
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleti…
Self-supervised learning improves by predicting known information, reducing labeled data needs.
We show that the predictability of letters in written English texts depends strongly on their position in the word. The first letters are usually the least easy to predict. This agrees with the intuitive notion that words are well defined subunits in written languages, with much weaker correlations across these units t…
Reinforcement learning after next-token prediction aids in learning from diverse sequence lengths.
Stock prediction has always been attractive area for researchers and investors since the financial gains can be substantial. However, stock prediction can be a challenging task since stocks are influenced by a multitude of factors whose influence vary rapidly through time. This paper proposes a novel approach (Word2Vec…
A new approach predicts next observations without explicit decoding for better control.
This study tackles mutual fund portfolio prediction, focusing on novel items.
Enhances image captioning with novel context combination methods.
In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of losses into prior hidden states and inputs held in memory. This allows gradients to f…
Law explains how LLMs learn to predict next tokens.
The paper distinguishes between conditional and marginal processes in language models and discusses conditions for usefulness.
The study explores how Transformers predict the next token in a sequence.
This paper examines how different decoding algorithms for LLMs align with various goals.
Model predicts next destination for users based on past trips and features.
This paper proposed a method for stock prediction. In terms of feature extraction, we extract the features of stock-related news besides stock prices. We first select some seed words based on experience which are the symbols of good news and bad news. Then we propose an optimization method and calculate the positive po…
Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work…
Identification of high affinity drug-target interactions is a major research question in drug discovery. Proteins are generally represented by their structures or sequences. However, structures are available only for a small subset of biomolecules and sequence similarity is not always correlated with functional similar…
Taureau uses Twitter sentiment analysis to predict stock market movement.
End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words directly may be helpful instead. However, training with word-level supervision can be …
Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover, their relative accuracy is highly sensitive to the dataset at hand, thus requiring…
Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels w…