Paper tackles noisy relation classification by sentence-level reinforcement learning.
problem Noisy distant supervision in relation classification.
method Two-module approach: instance selector using reinforcement learning, relation classifier making sentence-level predictions.
result Jointly trained model optimizes instance selection and relation classification, effectively handling noisy data.
New metrics predict human sentence comprehension across languages.
problem Predicting human sentence comprehension using computational models.
method Developed sentence-level metrics using multilingual large language models.
result Achieved high accuracy in predicting human sentence reading speeds.
The study examines how character and word-level representations improve sentence-level tasks.
problem Improving the quality of word and sentence representations using character-level information.
method Feature-wise sigmoid gating mechanism for combining character and word-level representations.
result Modeling characters improves final word and sentence representations, especially for less frequent words.
CERT improves language understanding by contrastively learning sentence-level semantics.
problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.
This paper improves sentence-level sentiment analysis of financial news.
problem Blurred insights into individual sentences' sentiment in financial news.
method Distributed text representations and multi-instance learning.
result Superior predictive performance of up to 69.90%.
FinAI-BERT classifies AI disclosures in financial reports with high accuracy.
problem Systematic detection of AI-related disclosures in financial reports.
method Fine-tuned transformer-based model on a curated dataset.
result Achieved near-perfect classification performance (99.37% accuracy).
LLMs produce volatile sentence-level sentiment classifications that affect financial decision-making.
problem Volatile outputs from LLMs impact financial text understanding tasks.
method Case study on US equity market investing via news sentiment analysis.
result Volatile LLM outputs lead to significant variations in portfolio construction and returns.
BERT improved for propaganda detection with imbalanced, dissimilar data.
problem BERT struggles with dissimilar imbalanced datasets in propaganda detection.
method Cost-sensitive BERT with dissimilarity measure for imbalanced, dissimilar datasets.
result Achieved second-highest score on sentence-level propaganda classification.
FAKTA automates fact checking across media sources.
problem Automating fact checking across diverse media sources.
method Unified framework integrating document retrieval, stance detection, evidence extraction, and linguistic analysis.
result FAKTA predicts factuality and provides evidence for claims.
We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perp…
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)…
CLARA generates clinical reports from raw inputs, improving accuracy and efficiency.
problem Generating accurate and detailed clinical reports from raw inputs is time-consuming and error-prone.
method Interactive method that generates reports sentence by sentence based on doctors' anchor words and partially completed sentences.
result CLARA achieves significant improvements in report generation accuracy and efficiency.
Quantum analysis tags news for sentiment and entities.
problem Identifying bias in news reporting.
method Continuous data collection, NER and sentiment analysis.
result A corpus of tagged news articles for public use.
Mining relationships between treatment(s) and medical problem(s) is vital in the biomedical domain. This helps in various applications, such as decision support system, safety surveillance, and new treatment discovery. We propose a deep learning approach that utilizes both word level and sentence-level representations …
New method improves sentence classification using context information.
problem Classifying sentences with limited context information.
method Context-LSTM-CNN method that considers large contexts and long-range dependencies.
result Consistently improves over previous methods on two datasets.
Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a f…
Two new methods improve coherence modeling without complex machine translation.
problem Improving neural coherence modeling for better sentence ordering.
method Two novel methods combining regression and context concatenation.
result Achieves state-of-the-art Kendall-tau and positional accuracy scores.
Anti-phishing aims to detect phishing content/documents in a pool of textual data. This is an important problem in cybersecurity that can help to guard users from fraudulent information. Natural language processing (NLP) offers a natural solution for this problem as it is capable of analyzing the textual content to per…
A new method samples sequences without replacement using Gumbel-Top-k trick.
problem Sampling sequences without replacement from large domains efficiently.
method Gumbel-Top-k trick applied to Stochastic Beam Search.
result Efficient sampling with linear model evaluations in k. We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation. Therefore, the dev…
Improves NMT by sampling context from predicted sequence during training.
problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
Graph model detects fake news by analyzing sentence interactions.
problem Detecting fake news through online media.
method Graph Neural Network-based model for sentence interactions.
result Our model achieves state-of-the-art accuracy on fake news datasets.
Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or id…
Paper develops neural network for Mandarin polyphone disambiguation.
problem Homograph problem in Mandarin Chinese text-to-speech.
method Bidirectional RNN for context, prediction network for mapping embeddings to pronunciations.
result Achieves 94.69% accuracy on polyphonic character dataset.
Systematically compares methods for explaining RNN predictions.
problem Understanding the decisions of RNNs, particularly LSTMs, through relevance assignments.
method Systematic comparison of methods in various settings.
result Best method reveals linguistic phenomena in sentiment analysis.
Model predicts trade volume changes from financial filings.
problem Improving financial market understanding through machine learning.
method Hierarchical Reformer model trained on SEDAR filings.
result Model can predict trade volume changes without explicit training.
Unified model for sequence labeling and classification.
problem Efficiently perform multiple sequence labeling tasks.
method Generative framework with shared natural language output space.
result Significant improvements in few-shot and low-resource slot labeling.
Motivated by Supervised Opinion Analysis, we propose a novel framework devoted to Structured Output Learning with Abstention (SOLA). The structure prediction model is able to abstain from predicting some labels in the structured output at a cost chosen by the user in a flexible way. For that purpose, we decompose the p…
SuTaT creates dialogue summaries for tete-a-tetes without labeled data.
problem Lack of high-quality paired dialogue-summary data.
method Unsupervised model for tete-a-tetes, modeling customer and agent roles separately.
result SuTaT outperforms on automatic and human evaluations.
Transfer learning improves sentiment classification using XR framework.
problem Lack of labeled data for deep learning.
method XR framework applied to transfer learning between related tasks, using expected label proportions.
result Improved performance on aspect-based sentiment classification.
This work shows cosine similarity is equivalent to Pearson correlation for word vectors, but not all vectors are suitable for cosine.
problem The use of cosine similarity for semantic textual similarity is often taken for granted, despite its limitations.
method Characterized cases where Pearson correlation is unfit and introduced rank correlation as an alternative.
result Pearson correlation is equivalent to cosine similarity for many word vectors but not all, and rank correlation can improve performance.
Proposes a graph-based text representation for improved sentiment analysis.
problem Lack of effective methods to encode semantic relations in textual data for sentiment analysis.
method Sentence-level graph-based text representation with deep neural network.
result Significantly outperforms existing sentiment analysis approaches on benchmark datasets.
Improves NMT performance on diverse datasets without forgetting.
problem Catastrophic forgetting in NMT models on heterogeneous datasets.
method Non-parametric n-gram level retrieval combined with expressive neural network.
result Gains on all evaluation sets on a heterogeneous dataset.
Improved text generation using transferable rewards from related tasks.
problem Non-differentiable task-specific scores limit the use of policy gradient methods in text generation.
method Transferable Reward Learner that uses model-based rewards for sentence-level and phrase-level similarity.
result Improved performance on semantic evaluation measures in image captioning tasks.
New method improves interpretability of text adversarial examples.
problem Generating interpretable adversarial examples in text is challenging.
method Sparse Projected Gradient Descent (SPGD) with directional and sparsity constraints.
result Improves interpretability and likelihood of adversarial examples compared to state-of-the-art methods.
Transformer models improve financial sentiment measurement.
problem Capturing nuanced sentiment from financial news articles.
method Transformer-based language models for sentiment classification and aggregation.
result Transformer models outperform traditional dictionary-based methods in sentiment classification.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invarian…
This paper assesses biases in contextualized word representations.
problem Analyzing biases in contextualized word representations.
method Proposes assessing bias at the contextual word level, capturing contextual effects of bias.
result Demonstrates evidence of bias in contextual word models, including racial bias and exacerbated effects for intersectional minorities.
A new algorithm RTO integrates DPO and PPO for RLHF, improving performance.
problem Learning from sparse, sentence-level rewards in RLHF.
method Modeling RLHF as MDP, introducing RTO that learns token-wise reward function.
result RTO outperforms PPO on benchmarks by 7.5 points on AlpacaEval 2 and 4.1 points on Arena-Hard.
BERT improves machines' ethical and moral decision-making.
problem Teaching machines ethical and moral choices.
method Applying BERT to human texts to extract moral bias scores.
result BERT improves the moral compass of machines.
PreBit predicts Bitcoin price movements using social media and financial data.
problem Predicting extreme price movements of Bitcoin due to its volatility and speculative trading.
method Hybrid model combining FinBERT embeddings of Twitter content with candlestick data and technical indicators.
result The hybrid model can predict significant market movements with a profitable trading strategy.
Proposes BU-SPO method to improve text classification robustness.
problem Vulnerability of deep models in text classification.
method Bigram and unigram based adaptive Semantic Preservation Optimization (BU-SPO) method.
result Achieves highest attack success rates and semantic similarity by changing the smallest number of words.
Automates summarizing federal grant audits with machine learning.
problem Manual analysis of large federal grant audits is time-consuming and error-prone.
method Sentence clustering, k-means, proximity to centroids, human input for refinement.
result Automated summaries are comparable to human-generated ones using ROUGE metric.