Skip to search formSkip to main contentSkip to account menu

Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition

The task, annotation process and dataset statistics are outlined, and a high-level overview of the participating systems for each shared task is provided.
View on ACL (opens in a new tab)

ONENET: Joint domain, intent, slot prediction for spoken language understanding

This work presents a unified neural network that jointly performs domain, intent, and slot predictions in spoken language understanding systems and adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task.
View on IEEE (opens in a new tab)

Frustratingly Easy Neural Domain Adaptation

A natural generalization of the feature augmentation method that uses K + 1 LSTMs where one model captures global patterns across all K domains and the remaining K models capture domain-specific information is proposed.
View on ACL (opens in a new tab)

Adversarial Adaptation of Synthetic or Stale Data

This work uses and builds on several recent advances in neural domain adaptation such as adversarial training and domain separation network to propose a new effective adversarialTraining scheme, which yields clear improvement over strong baselines in both supervised and unsupervised adaptation scenarios.
View on ACL (opens in a new tab)

Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources

Evaluating on POS datasets from 14 languages in the Universal Dependencies corpus, it is shown that the proposed transfer learning model improves the POS tagging performance of the target languages without exploiting any linguistic knowledge between the source language and the target language.
View on ACL (opens in a new tab)

New Transfer Learning Techniques for Disparate Label Sets

This work proposes a solution based on label embeddings induced from canonical correlation analysis (CCA) that reduces the problem to a standard domain adaptation task and allows use of a number of transfer learning techniques.
View on ACL (opens in a new tab)

Domain Attention with an Ensemble of Experts

A weighted combination of the K domain experts’ feedback along with its own opinion to make predictions on the new domain is described, which significantly outperforms baselines that do not use domain adaptation and also performs better than the full retraining approach.
View on ACL (opens in a new tab)

Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates

A neural joint learning model for domain classification and OOD detection is introduced, where dynamic class weighting is used during the model training to satisfice a given OOD false acceptance rate (FAR) while maximizing the domain classification accuracy.
View PDF on arXiv (opens in a new tab)

Training a Korean SRL System with Rich Morphological Features

This paper creates a novel training source by semantically annotating a Korean corpus containing fine-grained morphological and syntactic information and develops a supervised SRL model by leveraging morphological features of Korean that tend to correspond with semantic roles.
View on ACL (opens in a new tab)

An overview of end-to-end language understanding and dialog management for personal digital assistants

An overview of the language understanding and dialog management capabilities of PDAs, focusing particularly on Cortana, Microsoft's PDA, is provided, and how the quality of user experiences are measured end-to-end is described.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)