We study the problem of inferring readers' identities and estimating their level of text comprehension from observations of their eye movements during reading. We develop a generative model of individual gaze patterns (scanpaths) that makes use of lexical features of the fixated words. Using this generative model, we d…
System identifies related passages for easier text comprehension.
problem Expensive and limited cross-reference resources for complex texts.
method Fine-grained topic modeling to find topically related verse pairs.
result System can produce cost-effective cross-references.
Deep learning models outperform classical methods in text classification.
problem Improving text classification accuracy using deep learning.
method Comprehensive review of deep learning models and datasets for text classification.
result Deep learning models outperform classical methods on various text classification tasks.
In text classification, dictionaries can be used to define human-comprehensible features. We propose an improvement to dictionary features called smoothed dictionary features. These features recognize document contexts instead of n-grams. We describe a principled methodology to solicit dictionary features from a teache…
Model improves BERT for answering multiple-choice questions in large texts.
problem Improving machine comprehension of large text corpora for question answering.
method Developed a model using BERT with a semantic similarity attention layer to extract key sentences.
result Outperforms leading models in MovieQA challenge with 87.79% test accuracy.
BART pretrains sequence-to-sequence models by corrupting text and reconstructing it.
problem Improving natural language generation, translation, and comprehension.
method BART uses a denoising autoencoder trained on a Transformer architecture with various noising techniques.
result BART achieves state-of-the-art performance on various NLP tasks with minimal training resources.
Interactive machine comprehension models learn through seeking relevant information.
problem Existing MRC models struggle with real-world applications due to static datasets.
method Reframe MRC datasets as interactive, partially observable environments.
result Interactive models can seek relevant information through sequential decision making.
We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the following issues: i) we explore the suitability of two different models bDA and rsDA for constructing deep autoencoders for text data at the sentence level; ii)…
New method detects text changes under dependencies, outperforming baselines.
problem Detecting structural changes in m-dependent text data. method Kernel change-point detection under m-dependence. result Consistent and weakly consistent detection of change points in m-dependent text. FUNSD dataset tackles noisy scanned forms, offering comprehensive annotations.
problem Extracting and structuring textual content from noisy scanned documents.
method Comprehensive dataset with real, fully annotated forms, including text detection, OCR, layout analysis, and entity linking.
result First publicly available dataset for form understanding, addressing challenges in noisy scanned documents.
Survey on adversarial attacks and defenses for images, graphs, and text.
problem Adversarial examples threaten the safety of deep learning applications.
method Review of adversarial attack and defense mechanisms for images, graphs, and text.
result Systematic overview of adversarial attacks and countermeasures.
A new text representation model combines CNN and VAE for better semantic extraction.
problem Difficult to effectively extract semantic features and distinguish polysemy in text data.
method Integrates CNN for feature extraction and VAE for consistent Gaussian distribution.
result The model outperforms traditional classification algorithms in text classification tasks.
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.
Successful multimodal search and retrieval requires the automatic understanding of semantic cross-modal relations, which, however, is still an open research problem. Previous work has suggested the metrics cross-modal mutual information and semantic correlation to model and predict cross-modal semantic relations of ima…
Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations of text documents due to their confounding properties such as high-dimensionality…
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.
NeuroQuery synthesizes brain mapping evidence across diverse concepts.
problem Lack of comprehensive meta-analysis of human brain mapping across different mental processes and mechanisms.
method A multivariate model that predicts the spatial distribution of neurological observations given text describing an experiment, cognitive process, or disease.
result Captures relationships and neural correlates of 7,547 neuroscience terms across 13,459 neuroimaging publications.
Introduces basics of supergeometry for PhD students.
problem Understanding the geometry of supersymmetry.
method Smooth exposition of supergeometry themes.
result Highlights the reasons behind mathematical choices.
Benchmarking AutoML for tables with text fields, achieving top performance.
problem Evaluating automated learning systems for tables with text fields.
method Publicly available benchmark with 18 datasets varying in size, types, and feature composition.
result Stack ensembling a multimodal Transformer with various tree models achieved top performance.
SoulMate links short texts through multi-aspect embeddings.
problem Linking authors of noisy, ambiguous short texts.
method Neural network-based temporal-textual framework generating author subgraphs.
result Higher performance in linking short-text authors compared to competitors.
Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.
problem Neural models' oversensitivity to adversarial question changes.
method Formulated a noisy adversarial attack to identify and exploit undersensitivity, tested with data augmentation and adversarial training.
result Undersensitivity can be exploited to mislead models, and addressing it improves model performance and robustness.
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…
German FinBERT improves financial text analysis performance.
problem Capturing domain-specific nuances in financial text.
method German FinBERT is a pre-trained German language model trained on a large corpus of financial data.
result German FinBERT outperforms standard models on finance-specific tasks.
In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and ge…
Paper proposes PP-GCN for fine-grained social event categorization.
problem Challenges in mining social events due to heterogeneous event elements and social network structures.
method Design an event meta-schema, build an HIN, propose PP-GCN, and use KIES.
result PP-GCN outperforms other techniques in social event detection and clustering.
A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty. The past decade has seen major advances in many perception tasks such as visual ob…
Improved text-to-image and multimodal understanding through adaptive generation order optimization.
problem Determining optimal generation sequences in text-to-image synthesis and multimodal understanding.
method Introduced a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order.
result Learning the control block substantially improves text-to-image alignment and multimodal understanding in DLMs.
Proposes RTL model for sentiment classification and key word detection in online reviews.
problem Sentiment classification and key word detection in online reviews for hospitality industry.
method Regularized Text Logistic (RTL) regression model.
result RTL model achieves satisfactory classification performance and identifies key word features.
AI aids in mathematics research and problem-solving.
problem Complex mathematical problems and discoveries.
method Explains AI principles and diverse applications in math.
result AI assists in discovering patterns, proving theorems, and challenging conjectures.
Survey on GANs for generating visual arts, music, and literature.
problem Tackles the challenge of generating art using GANs.
method Uses generative adversarial networks (GANs) to generate visual arts, music, and literary text.
result Performance comparison and description of various GAN architectures presented.
A new sliced IGW distance for Gromov-Wasserstein alignment.
problem Scalability issues in Gromov-Wasserstein alignment for high-dimensional problems.
method Proposed a sliced IGW distance with rotational invariance.
result Natural rotational invariance of the sliced IGW distance.
Paper augments neural nets with logic for improved performance.
problem Training neural networks with declarative knowledge without extra parameters.
method Systematically compiles logical statements into computation graphs that augment neural networks.
result Knowledge-augmented networks significantly improve performance, especially in low-data scenarios.
Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the input length, and all inputs are read regardless of their importance. Efforts to…
Generative text classifiers are most vulnerable to membership inference attacks.
problem Privacy threat from Membership Inference Attacks on generative text classifiers.
method Comprehensive empirical evaluation of generative, discriminative, and pseudo-generative classifiers across various datasets.
result Generative classifiers explicitly modeling P(X,Y) are most vulnerable to membership leakage. BTZSC benchmarks zero-shot text classification across diverse models.
problem Systematically comparing zero-shot text classification across various models.
method Comprehensive benchmark of 22 datasets, comparing NLI cross-encoders, embedding models, rerankers, and instruction-tuned LLMs.
result Rerankers and instruction-tuned LLMs outperform NLI cross-encoders, with rerankers setting a new state-of-the-art.
Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in …
This paper presents details of our winning solutions to the task IV of NIPS 2017 Competition Track entitled Classifying Clinically Actionable Genetic Mutations. The machine learning task aims to classify genetic mutations based on text evidence from clinical literature with promising performance. We develop a novel mul…
Framework integrates financial and annual report data for better corporate credit ratings.
problem Lack of insights from non-financial data in credit rating models.
method Uses FinBERT to extract features from annual reports and combines them with financial data.
result Improves credit rating accuracy by 8-12%.
Paper shows pretrained models can categorize Thai social media content effectively.
problem Lack of labeled data for Thai social media content classification.
method Pretrained language models on a large noisy Thai social media corpus, fine-tuned for downstream tasks.
result State-of-the-art results achieved on Thai social text categorization tasks.
Few-step distillation improves T2I models without real images or CFG trade-offs.
problem Challenges in accelerating T2I models with high-resolution and CFG.
method Score identity distillation (SiD) for few-step generation, with adversarial loss and new guidance strategies.
result State-of-the-art performance on SDXL at 1024x1024 resolution, robust to real images absence.
The paper proposes a variational autoencoder for discrete data analysis.
problem Sparse, high-dimensional, and overdispersed discrete data analysis.
method Variational autoencoder based on negative-binomial distribution.
result The proposed models achieve significantly better performance on text analysis, collaborative filtering, and multi-label learning compared to state-of-the-art baselines.
The paper presents a systematic review of state-of-the-art approaches to identify patient cohorts using electronic health records. It gives a comprehensive overview of the most commonly de-tected phenotypes and its underlying data sets. Special attention is given to preprocessing of in-put data and the different modeli…
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
Paper presents LLM-enhanced contract metadata extraction.
problem Automatic detection and annotation of legal clauses in contracts.
method Integration of publicly available and proprietary datasets with advanced LLM methodologies.
result Substantial improvements in clause identification accuracy and efficiency.
Introduces Q-structures for mechanics using advanced geometry.
problem Challenges in classical differential geometric constructions in mechanics.
method Explains the use of Q-structures and differential graded manifolds.
result Q-structure preserving integrators can be useful in mechanics.
Lipper synthesizes speech from silent videos, improving over single-view methods.
problem Lipreading as text classification is limited; multi-view approach needed.
method Multi-view lipreading as a regression task, producing speech from silent videos.
result Improvement in speech reconstruction with multi-view silent videos.
Unified QuesNet learns comprehensive representations for diverse test questions.
problem Lack of labeled data for test questions in online learning systems.
method Unified framework and two-level hierarchical pre-training algorithm for unsupervised learning of heterogeneous question representations.
result QuesNet effectively learns comprehensive question representations and outperforms existing methods.
LIDS assesses LLM summaries with interpretable key words.
problem Challenges in evaluating the quality of LLM summaries.
method BERT-SVD-based direction metric and SOFARI for key word extraction.
result LIDS provides interpretable key words for layered themes.