Papers by Killian Levacher

4 papers
Know Who Your Friends Are: Understanding Social Connections from Unstructured Text (N18-5)

Copied to clipboard

Challenge: Having an understanding of interpersonal relationships is helpful in many contexts.
Approach: They propose a system that extracts qualitative and quantitative information from texts and aggregates it to provide a condensed view of relationships.
Outcome: The proposed system extracts qualitative and quantitative information elements about interactions and aggregates those to provide a condensed view of relationships.
Towards Automated Extraction of Business Constraints from Unstructured Regulatory Text (C18-2)

Copied to clipboard

Challenge: a system for machine-driven annotations of legal documents is currently undergoing user trials within our organization.
Approach: a system for machine-driven annotations of legal documents is presented . the system is currently undergoing user trials within our organization.
Outcome: the proposed system is currently undergoing user trials within our organization.
The ADELE Corpus of Dyadic Social Text Conversations:Dialog Act Annotation with ISO 24617-2 (L18-1)

Copied to clipboard

Challenge: Recent studies have focused on task-based or instrumental dialogs, but there is increasing interest in social or interactional dialogs.
Approach: They describe a corpus of 193 dyadic text dialogs based on a novel 'getting to know you' social dialog elicitation paradigm and propose additional acts to better cover greeting and leavetaking.
Outcome: The proposed actions cover greeting and leavetaking, and the proposed acts improve the interaction between the dialogs and spoken language.
Decision Conversations Decoded (N18-5)

Copied to clipboard

Challenge: a system that tracks the decision process is aimed at group decision making facilitation . the system tracks the options being considered, why they are proposed, by whom and with whose support.
Approach: They propose a system that tracks the decision process and organizes collective thoughts into a summary . the system is based on the scientific field of Decision Analysis .
Outcome: The proposed system can help identify agreement and dissent or recommend an alternative based on this information.

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