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.
Optimal text-based indices track VIX and inflation.
To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter, i.e., learning to act optimally when valid actions are known in advance. In thi…
RecoBERT uses a language model to recommend items from catalogs.
Improved RL for TBGs by pruning irrelevant tokens and bootstrapping.
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose …
Study shows text-based news veracity models don't generalize across U.S. and U.K.
MoleculeSTM learns from molecule structures and texts for better drug design.
New text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories of interest from large collections of text. We introduce a conceptual framework for making causal inferences with discovered measures as a treatment or outcome. Our framewo…
This thesis evaluates text-based vs audio-based classification of mental health interviews.
Q*BERT learns to navigate text-based games by building a knowledge graph.
GENs model generates sparse graphs from text-based inputs, achieving high validity.
Paper tackles treatment leakage in text-based causal inference, proposing methods to mitigate bias.
KG-A2C agent learns natural language IF games by reasoning and constraining action spaces.
Study improves cryptocurrency price prediction using unlabeled text data.
Paper proposes HGAT for detecting fake news on HIN.
Paper proposes ICCN to learn correlations between text, audio, and video for multimodal sentiment analysis.
Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adver…
TBIP uses texts to quantify lawmakers' political positions.
Study enhances cryptocurrency sentiment analysis using TikTok and Twitter data.
SWIFT learns intrinsic rewards from LLM hidden states for efficient best-of-N sampling.
While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously hard to optimize. With the emerging field of Text-Based Games (TBGs), re…
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination…
Industry datasets used for text classification are rarely created for that purpose. In most cases, the data and target predictions are a by-product of accumulated historical data, typically fraught with noise, present in both the text-based document, as well as in the targeted labels. In this work, we address the quest…
This study reviews text-based stock market analysis methods.
Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity in embedding space is not optimized in the learning. In this paper we propose a …
Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based models like convolutional networks, while text-based models are still evolving. The…
Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds. We focus on the challenging real-world problem of action-graph extraction from material science papers, where language is highly specialized and data annotation is expensive and scarce. We propose a novel approach, T…
Simplified image clustering achieves competitive results without text-based embeddings.
We have applied the Zipf method to extract the exponent for seven financial indices (DAX, FTSE; DJIA, NASDAQ, S&P500; Hang-Seng and Nikkei 225), after having translated the signals into a text based on two letters. We follow considerations based on the signal Hurst exponent and the notion of a time dependent Zipf …
Research on social-media platforms has tended to rely on textual analysis to perform research tasks. While text-based approaches have significantly increased our understanding of online behavior and social dynamics, they overlook features on these platforms that have grown in prominence in the past few years: click-bas…
Traditional methods outperform LLMs in forecasting corporate credit ratings.
Model uses LLM features to predict stock returns effectively.
Deep learning model improves Vietnamese NER accuracy.
NegToMe uses images to guide text-based models away from unwanted visual elements.
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from -- the intermediate representations learned by text-based neural classifiers. The …
The recent surge of text-based online counseling applications enables us to collect and analyze interactions between counselors and clients. A dataset of those interactions can be used to learn to automatically classify the client utterances into categories that help counselors in diagnosing client status and predictin…
OptFormer learns universal HPO from diverse datasets.
Adversarial tweets can fool stock prediction models, causing financial loss.
Paper explores using LLMs for zero-shot reinforcement learning in continuous spaces.
The group affect or emotion in an image of people can be inferred by extracting features about both the people in the picture and the overall makeup of the scene. The state-of-the-art on this problem investigates a combination of facial features, scene extraction and even audio tonality. This paper combines three addit…
ChatGPT enhances GNN for stock movement prediction.
In this paper we present MLaut (Machine Learning AUtomation Toolbox) for the python data science ecosystem. MLaut automates large-scale evaluation and benchmarking of machine learning algorithms on a large number of datasets. MLaut provides a high-level workflow interface to machine algorithm algorithms, implements a l…
Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges…
Unified framework improves NLP tasks by converting diverse problems into text-to-text format.
Paper evaluates using app images for classification, improving accuracy.
Study earnings calls to predict stock price movements, finding them more predictive than traditional data.
Study combines chit-chat and goal-oriented dialogue in fantasy games.
Extracts credit-relevant information from earnings calls.