Search Results for author:
Found 12 papers, 6 papers with code
Multi-Step Dialogue Workflow Action Prediction
In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task.
GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
Further, we experiment with two variations: (1) fine-tuning gist models for each dataset and (2) multi-task training a single model on a large collection of datasets.
On the Effectiveness of Offline RL for Dialogue Response Generation
A common training technique for language models is teacher forcing (TF).
Submodular Minimax Optimization: Finding Effective Sets
Despite the rich existing literature about minimax optimization in continuous settings, only very partial results of this kind have been obtained for combinatorial settings.
Domain Private Transformers for Multi-Domain Dialog Systems
Large, general purpose language models have demonstrated impressive performance across many different conversational domains.
CEREAL: Few-Sample Clustering Evaluation
We adapt existing approaches from the few-sample model evaluation literature to actively sub-sample, with a learned surrogate model, the most informative data points for annotation to estimate the evaluation metric.
Identifying Mislabeled Data using the Area Under the Margin Ranking
Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled.
Metric Learning for Dynamic Text Classification
However, in many real-world applications the label set is frequently changing.
Detecting Noisy Training Data with Loss Curves
This paper introduces a new method to discover mislabeled training samples and to mitigate their impact on the training process of deep networks.
Importance Weighted Generative Networks
Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution.
Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
In many machine learning applications, it is important to explain the predictions of a black-box classifier.
Restricted Strong Convexity Implies Weak Submodularity
Our results extend the work of Das and Kempe (2011) from the setting of linear regression to arbitrary objective functions.
