Papers by György Szarvas

5 papers
The Multilingual Amazon Reviews Corpus (2020.emnlp-main)

Copied to clipboard

Challenge: The corpus contains reviews in English, Japanese, German, French, Spanish, and Chinese, which were collected between 2015 and 2019 .
Approach: They propose to use mean absolute error (MAE) instead of classification accuracy for this task since MAE accounts for ordinal nature of the ratings.
Outcome: The proposed model uses mean absolute error (MAE) instead of classification accuracy since MAE accounts for ordinal nature of the ratings.
Deploying a Retrieval based Response Model for Task Oriented Dialogues (2022.emnlp-industry)

Copied to clipboard

Challenge: a task-oriented dialogue system needs high conversational capability and can be easily adaptable to changing situations.
Approach: They propose a retrieval-based conversational model that can rank a large set of responses . they propose supervised training and fine-tuning on limited data collected through a human-in-the-loop platform .
Outcome: The proposed model can scale to rank a large set of responses in real-world situations.
Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systems (2024.findings-emnlp)

Copied to clipboard

Challenge: Task-oriented Dialog (ToD) systems have to solve multiple subgoals to accomplish user goals, whereas feedback is often obtained only at the end of the dialog.
Approach: They propose an iterative training approach that uses subgoals to improve task-oriented dialog systems.
Outcome: The proposed approach improves on a popular ToD benchmark by combining fine-tuning and preference learning steps.
Few Shot Rationale Generation using Self-Training with Dual Teachers (2023.findings-acl)

Copied to clipboard

Challenge: Existing models that generate free-text explanations for annotated labels are expensive and require a large annotation dataset.
Approach: They propose a self-training approach leveraging both labeled and unlabeled data to further improve few-shot models by combining teacher models and a multi-tasking student model.
Outcome: The proposed model improves on three public datasets and can generate a free-text explanation for predicted labels.
Calibrating Imbalanced Classifiers with Focal Loss: An Empirical Study (2022.emnlp-industry)

Copied to clipboard

Challenge: Imbalanced data distributions can cause models to overfit to majority classes and output unreliable (mostly overconfident) predictions.
Approach: They propose to streamline the model development and deployment using focal loss to address imbalanced data distributions.
Outcome: The proposed model training with focal loss improves calibration and accuracy compared to standard cross-entropy loss.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations