Глубокие нейронные модели
Related Papers
Measuring the Information Content of Financial News
AbstractMeasuring the information content of news text is useful for decision makers in their investments since news information can influence the intrinsic values of companies. We propose a model to …...
Human or Neural Translation?
AbstractDeep neural models tremendously improved machine translation. In this context, we investigate whether distinguishing machine from human translations is still feasible. We trained and applied 18 classifiers under two settings: …...
Scientific Keyphrase Identification and Classification by Pre-Trained Language Models Intermediate Task Transfer Learning
AbstractScientific keyphrase identification and classification is the task of detecting and classifying keyphrases from scholarly text with their types from a set of predefined classes. This task has a wide …...
Learning from Noisy Labels for Entity-Centric Information Extraction
AbstractRecent information extraction approaches have relied on training deep neural models. However, such models can easily overfit noisy labels and suffer from performance degradation. While it is very costly to …...
A Survey in Automatic Irony Processing: Linguistic, Cognitive, and Multi-X Perspectives
AbstractIrony is a ubiquitous figurative language in daily communication. Previously, many researchers have approached irony from linguistic, cognitive science, and computational aspects. Recently, some progress have been witnessed in automatic …...
Deep Learning for Text Style Transfer: A Survey
AbstractText style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It …...
Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing
AbstractDeep neural models have become the mainstream in answer selection, yielding state-of-the-art performance. However, these models tend to rely on spurious correlations between prediction labels and input features, which in …...
Schema Encoding for Transferable Dialogue State Tracking
AbstractDialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset …...
This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text
AbstractThe use of deep neural models for diagnosis prediction from clinical text has shown promising results. However, in clinical practice such models must not only be accurate, but provide doctors …...
AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction
AbstractDeep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as …...
Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection
AbstractClassic approaches to content moderation typically apply a rule-based heuristic approach to flag content. While rules are easily customizable and intuitive for humans to interpret, they are inherently fragile and …...