Year: 2018
Type: conference-paper
Abstract: Answer Sentence Selection (ASS) is one of the steps typically involved in Question Answering, a hard task for natural language \nprocessing since full solutions would require both natural language understanding and world knowledge. We present a new approach to tackle \nASS, based on a Cross-Attentive Convolutional Neural Network. The \napproach was designed for competing in the Fujitsu AI-NLP challenge \nFujitsu [4], which evaluates systems on their performance on the SelQA[7] \ndataset. This dataset was created on purpose as a benchmark to stress \nthe ability of systems to go beyond simple word co-occurrence criteria. \nOur submission achieved the top score in the challenge.
Authors: Alessio Gravina, Federico Rossetto, Silvia Severini, Giuseppe Attardi
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Nvidia, Università di Pisa
OpenAlex ID: W2902815016