Papers with multi-task learning method

9 papers
End-to-End Learning of Task-Oriented Dialogs (N18-4)

Copied to clipboard

Challenge: Dissertation addresses the limitations of conventional task-oriented dialog systems . conventions of such systems include a complex pipeline and dialog state tracking .
Approach: They propose a neural network based dialog system that can robustly track dialog state . they propose offline training and online interactive learning methods to improve efficiency .
Outcome: The proposed system can track dialog state, interface with knowledge bases, and integrate structured query results into system responses to successfully complete task-oriented dialog.
Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models (2020.coling-main)

Copied to clipboard

Challenge: Existing knowledge graph completion methods are lacking in ranking metrics such as Hits@k . despite the high performance, the proposed method is still behind state-of-the-art models.
Approach: They propose a multi-task learning method that integrates relational and relevance ranking tasks with target link prediction to improve ranking performance.
Outcome: The proposed method improves ranking performance but still behind state-of-the-art models in Hits@k and Mean Rank metrics.
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling (2021.emnlp-main)

Copied to clipboard

Challenge: Existing CSRL parsers struggle to handle conversational structural information.
Approach: They propose a conversational semantic role labeling task which explicitly encodes speaker dependent information and proposes a multi-task learning method to further improve the model.
Outcome: The proposed model outperforms baselines on benchmark datasets on conversation-based tasks.
Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification (2021.naacl-main)

Copied to clipboard

Challenge: Currently, most work on targeted sentiment analysis is focused on improving the overall results.
Approach: They propose a multi-task learning method to incorporate information from syntactic and semantic auxiliary tasks to create English-language models that are more robust to linguistic phenomena.
Outcome: The proposed method improves on negation and speculation datasets but there is room for improvement.
Multi-Task Learning for Japanese Predicate Argument Structure Analysis (N19-1)

Copied to clipboard

Challenge: Recent work ignores event-nouns or builds a single model for solving both tasks . however, there are interactions between predicates and event-nons, making it difficult to target only predicate.
Approach: They propose a multi-task learning method that targets event-nouns . their results improve performance of both PASA and ENASA tasks .
Outcome: The proposed model improves both PASA and ENASA tasks compared to a single-task model . it is the first work to employ neural networks in ENASA .
RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods focus on sentencelevel event extraction (SEE), but they are inconsistent with actual situations.
Approach: They propose a document-level event extraction framework which can model relation dependencies by a relation-augmented Attention Transformer.
Outcome: The proposed framework can achieve state-of-the-art performance on two public datasets.
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to integrate knowledge graph (KG) with neural machine translation (NMT) have two problems: knowledge under-utilization and granularity mismatch.
Approach: They propose a multi-task learning method on sub-entity granularity to combine machine translation and knowledge reasoning tasks.
Outcome: The proposed method significantly outperforms baseline models on translation tasks and handling the entities.
BanditMTL: Bandit-based Multi-task Learning for Text Classification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods to regularize task variance are unexplored in multi-task text classification.
Approach: They propose a multi-task learning method based on adversarial multi-armed bandit to regularize the task variance by means of a mirror gradient ascent-descent algorithm.
Outcome: The proposed method achieves state-of-the-art in multi-task text classification.
Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection (D19-1)

Copied to clipboard

Challenge: Existing methods for detecting fake news use shared features as complementarity features without selection.
Approach: They propose a sifted multi-task learning method with a selected sharing layer for fake news detection.
Outcome: The proposed method boosts the F1-score by more than 0.87%, 1.31% on two public and widely used competition datasets.

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