Papers by Annalena Aicher

4 papers
User Interest Modelling in Argumentative Dialogue Systems (2022.lrec-1)

Copied to clipboard

Challenge: Existing studies on user interest in dialogue systems depend on explicit user feedback.
Approach: They propose a model to implicitly estimate user interest during argumentative dialogues based on semantically clustered data.
Outcome: The proposed model achieves a classification accuracy of 74.9% and tested with different Artificial Neural Networks (ANN) which new argument would fit the user interest best.
Towards Modelling Self-imposed Filter Bubbles in Argumentative Dialogue Systems (2022.lrec-1)

Copied to clipboard

Challenge: In order to overcome this “self-imposed filter bubble” (SFB), it is crucial to identify influential indicators for the user’s SFB, namely Reflective User Engagement (RUE), Personal Relevance ranking of content-related subtopics as well as False (FK) and True Knowledge (TK).
Approach: They propose to model an SFB by focusing on four indicators for the user's Reflective User Engagement (RUE), their Personal Relevance ranking of content-related subtopics and their False (FK) and True Knowledge (TK) indicators are based on the responses of 202 users of an online argumentative dialogue system BEA.
Outcome: The proposed system aims to break the self-imposed filter bubble (SFB) by identifying indicators for the user's SFB .
Towards Speech-only Opinion-level Sentiment Analysis (2022.lrec-1)

Copied to clipboard

Challenge: Existing systems that estimate user preferences only in static manners or exploit interaction history are inadequate to accurately assess user preferences.
Approach: They propose to integrate rank consistent ordinal regression into a speech-only sentiment prediction task performed by ResNet-like systems and use speaker verification extractors trained on larger datasets as low-level feature extractor.
Outcome: The proposed system beats state-of-the-art unimodal systems on multimodal Opinion Sentiment and Emotion Intensity databases.
Towards Building a Spoken Dialogue System for Argument Exploration (2022.lrec-1)

Copied to clipboard

Challenge: Argumentative dialogue systems lack a robust natural language understanding framework for complex tasks . drop-down menus hinder the application of natural language learning approaches .
Approach: They propose to integrate a natural language understanding framework into an argumentative dialogue system.
Outcome: The proposed system is compared to a baseline system using a drop-down menu . the drop- down menu convinces, but the willingness to use it is significantly higher .

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