SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the leng…
ZeroSCROLLS benchmarks zero-shot natural language understanding over long texts.
problem Evaluate natural language understanding models over long texts without training data.
method Adapt six tasks from SCROLLS benchmark and add four new datasets, including novel aggregation tasks.
result Claude outperforms ChatGPT, and GPT-4 achieves highest average score.
Improved Mamba model for long-range sequence tasks.
problem Mamba's poor performance on long-range sequential tasks.
method Proposed B2S6, combining block-wise selective dynamics and channel-specific bias.
result Empirically, B2S6 outperforms S4 and S4D on LRA tasks.
Model criticism tool evaluates text coherence and structure in generated long-form text.
problem Evaluate the high-level structure of generated text for coherence, coreference, and topicality.
method Apply model criticism in latent space to compare real and generated data distributions.
result Transformer-based models struggle with maintaining structural coherence and coreference.
System identifies language of transliterated text.
problem Users struggle to understand non-native language transliterated text.
method Feature extraction of phonetic syllables using LSTM network.
result System accurately identifies language of transliterated text.
New method predicts nonfactuality in LLM responses using semantic isotropy.
problem Assessing trustworthiness of long-form LLM responses efficiently.
method Semantic isotropy of text embeddings on the unit sphere.
result Higher semantic isotropy correlates with lower factual consistency.
Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes longer. Current language models often struggle to keep track of coherence for long pi…
We apply text analysis approaches for a specialized search engine for 3D CAD models and associated products. The main goals are to distinguish between actual product descriptions and other text on a website, as well as to decide whether a given text is or contains a product name. For this we use paragraph vectors for t…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing l…
Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
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…
Proposes a flexible neural recommendation framework for better prediction performance.
problem Data sparsity, cold start problem, and long-tail distribution in recommendations.
method A modular neural recommendation framework that includes a neural collaborative filtering part and a text processing part as a regularizer.
result Achieves better prediction performance than state-of-the-art text-aware methods using a simple text processing approach.
Shorter adversarial prompts help protect LLMs from jailbreak attacks.
problem Protecting large language models from jailbreak attacks with long adversarial suffixes.
method Adversarial training on shorter adversarial suffixes to defend against longer adversarial suffixes.
result Aligning LLMs on shorter adversarial suffixes can effectively defend against jailbreak attacks with longer suffixes.
A novel method extracts topological features from word embeddings for text classification.
problem High dimensional and noisy text representations in natural language processing.
method Persistent homology for topological data analysis on word embeddings.
result Topological features outperform conventional text mining features on long textual documents.
Paper introduces new indicators for forecasting crude oil prices using short news headlines.
problem Forecasting crude oil prices from short, noisy news headlines using LDA.
method Developed two novel indicators for topic and sentiment from short text data, and applied AdaBoost.RT.
result AdaBoost.RT with the proposed indicators outperforms benchmarks in crude oil forecasting.
Proves Payne conjecture for buckling and membrane eigenvalues.
problem Proving Payne conjecture for buckling and membrane eigenvalues.
method Analytical proof for buckling and membrane eigenvalues.
result Proves Payne conjecture for n-dimensional case (n≥2). Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical mod…
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and …
Paper fine-tunes a language model to predict long-term stock buy signals.
problem Predicting long-term stock price movements with narrative text.
method Fine-tuning a small language model on 10-K reports for buy/sell decisions.
result Buy signals generated from 10-K text are most precise at 6 and 9 months, providing 4.8-9% improvement over random selection.
The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We emp…
Paper calculates topological complexity of robot movement in narrow aisles.
problem Determining minimum number of scenarios for robot movement in a narrow strip.
method Examined cohomology ring of ordered configuration space to find lower bound.
result Lower bound for minimum number of cases in robot movement program.
Unified Long-Moody and Katz methods for constructing local systems.
problem Constructing representations of braid groups and local systems.
method Katz-Long-Moody functor unifying Long-Moody and Katz methods.
result Extends Katz algorithm to various topological spaces.
This thesis evaluates text-based vs audio-based classification of mental health interviews.
problem Classifying psychiatric illness using text-based methods.
method Design and evaluate a text classification network on mental health interviews, using belabBERT.
result Text-based classification is a strong alternative to audio-based methods.
This paper fine-tunes LLMs for stock return prediction using financial news.
problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.
One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we…
DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.
problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.
Dual-attention GCN improves text classification by adapting to textual complexity.
problem Challenges in learning discriminative features from texts due to graph variants.
method Proposes a dual-attention GCN with connection-attention and hop-attention mechanisms.
result Achieves state-of-the-art performance on text classification tasks.
TRM improves long-horizon LLM RL by masking divergent sequences.
problem Long-horizon reinforcement learning with LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
TRM improves long-horizon reinforcement learning for LLMs by masking divergent sequences.
problem Long-horizon reinforcement learning for LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical…
Study enhances cryptocurrency sentiment analysis using TikTok and Twitter data.
problem Lack of comprehensive sentiment analysis in cryptocurrency markets.
method Multimodal analysis of TikTok and Twitter data using large language models.
result TikTok's video sentiment influences speculative assets and short-term trends.
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph compone…
AMI framework improves text generation by optimizing mutual information between source and target.
problem Previous MI approaches ignored the backward network, leading to loose variational bounds.
method AMI is a saddle point optimization framework that iteratively promotes and demotes generated instances.
result AMI significantly outperforms baselines on various text generation tasks.
Study proposes a multimodal model for cardiovascular risk prediction using EHRs.
problem Lack of comprehensive risk prediction from EHRs due to unstructured text.
method Proposes a multimodal BiLSTM model integrating structured and unstructured EHR data.
result Proposed BiLSTM model outperforms other DNN architectures in cardiovascular risk prediction.
NoLBERT avoids lookback and lookahead biases for better econometric inference.
problem Information leakage in language models affects econometric inference.
method Pretrained on text from 1976-1995, avoiding lookback and lookahead biases.
result NoLBERT outperforms domain-specific baselines and predicts higher profit growth.
FINCH dataset enables financial Text-to-SQL tasks, improving model evaluation.
problem Lack of a large-scale financial dataset for Text-to-SQL tasks.
method Curated financial dataset (FINCH), benchmarking reasoning and language models.
result Proposed FINCH Score for more accurate financial model evaluation.
Proposes a new RNN for language generation capturing long-range dependencies.
problem Capturing long-range word dependencies and sentence order in text corpora.
method Recurrent Hierarchical Topic-Guided RNN with dynamic deep topic model.
result Outperforms larger-context RNN-based language models and learns interpretable topics.
This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are rigorously derived and backed by long-standing theory. The methods, decision tree…
Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components. Updating only these task-specific modules then allows the model to be adapted to low-data tasks for as many steps as necessary without ris…
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…
The paper predicts financial markets using news text and semantic network analysis.
problem Predicting financial markets with news data.
method Semantic network analysis of news text to assess economic keywords' importance.
result The index captures financial market phases and predicts returns and volatilities.
The paper proposes a new framework to generate synthetic data with human-like imperfections to prevent model collapse.
problem Model collapse due to statistical optimization of synthetic data.
method Introduces Prompt-driven Cognitive Computing Framework (PMCSF) with Cognitive State Decoder (CSD) and Cognitive Text Encoder (CTE).
result The framework generates text with cognitive imperfections, reducing maximum drawdown and delivering defensive alpha.
RNNs are crucial for text and speech tasks, explained in this overview.
problem Understanding RNNs for advanced AI tasks.
method Overview of RNN concepts and recent advances.
result Fundamentals and recent techniques in RNNs.
New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.
problem Learning optimal policy for average reward in uniformly ergodic MDPs.
method Developed an estimator with sample complexity of O(|S||A|t_{mix}ε^{-2}).
result First algorithm to match lower bound of existing literature.
ICP improves text infilling and POS tagging with valid confidence sets.
problem Statistical reliability of machine learning predictions.
method Inductive conformal prediction algorithms for text infilling and POS tagging.
result Valid set-valued predictions with small size for real-world applications.
Study integrates climate and text data to improve credit default prediction.
problem Improving credit risk assessment for mSEs with limited financial histories.
method Multimodal framework using LSTM, GRU, and transformer models.
result Integration of multiple data modalities improves credit default prediction.
Bayesian Neural Networks detect gravitational wave events with high accuracy and real-time potential.
problem Detecting and identifying the full duration of compact binary coalescence events in gravitational wave data.
method Integrating Bayesian approach into a CLDNN classifier that combines CNN and LSTM for event detection and uncertainty estimation.
result Successfully detected all seven BBH events in LIGO Livingston O2 data with high accuracy.