Twente-BMS-NLP at PerspectiveArg 2024: Combining Bi-Encoder and Cross-Encoder for Argument Retrieval
Year: 2024
Type: conference-paper
Abstract: The paper describes our system for the Perspective Argument Retrieval Shared Task.The shared task consists of three scenarios in which relevant political arguments have to be retrieved based on queries (Scenario 1).In Scenario 2 explicit socio-cultural properties are provided and in Scenario 3 implicit socio-cultural properties within the arguments have to be used.We combined a Bi-Encoder and a Cross-Encoder to retrieve relevant arguments for each query.For the third scenario, we extracted linguistic features to predict socio-demographic labels as a separate task.However, the socio-demographic match task proved challenging due to the constraints of argument lengths and genres.The described system won both tracks (relevance and diversity) of the shared task.
Authors: Leixin Zhang, Daniel Braun
Institution: University of Twente
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4402671007