Papers with machine learning technologies

4 papers
Self-supervised Representation Learning for Speech Processing (2022.naacl-tutorials)

Copied to clipboard

Challenge: Self-supervised representation learning (SSL) uses proxy supervised learning tasks to obtain training data from unlabeled corpora.
Approach: They propose to survey the latest SSL techniques, tools, datasets, and performance achievement in speech processing to scale up current machine learning technologies.
Outcome: The proposed tutorial is highly relevant to the special theme of ACL about language diversity.
The D-WISE Tool Suite: Multi-Modal Machine-Learning-Powered Tools Supporting and Enhancing Digital Discourse Analysis (2023.acl-demo)

Copied to clipboard

Challenge: The D-WISE Tool Suite addresses limitations of current DH tools due to the ever-increasing amount of heterogeneous, unstructured, and multi-modal data in which discourses of contemporary societies are encoded.
Approach: They propose to use D-WISE Tool Suite to analyze heterogeneous, unstructured, and multi-modal data in the Digital Humanities (DH)
Outcome: The proposed tool leverages state-of-the-art machine learning technologies from Natural Language Processing and Com-puter Vision to ensure its usability for modernDH research.
Designing Multilingual Interactive Agents using Small Dialogue Corpora (2020.lrec-1)

Copied to clipboard

Challenge: a new study aims to develop a design framework for multilingual interactive agents . large amounts of data and language resources are needed to develop most key components .
Approach: They propose a general design framework for multilingual interactive agents in specialized domains with small or non-existent dialogue corpora.
Outcome: The proposed framework integrates external language services for supporting multilingual functions and realizes context-aware dialogue generation under the situation of small corpora.
MDACE: MIMIC Documents Annotated with Code Evidence (2023.acl-long)

Copied to clipboard

Challenge: Computer-Assisted Coding (CAC) systems are required to provide supporting textual evidence to justify billing codes.
Approach: They propose a dataset for evidence/rationale extraction on an extreme multi-label classification task over long medical documents.
Outcome: The proposed dataset can be used to evaluate evidence extraction methods for CAC systems, as well as the accuracy and interpretability of deep learning models for multi-label classification.

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