flaviopinzarrone / question-answering

Second assignment for NLP course of the Master’s Degree in Artificial Intelligence

Question-Answering

Authors:

• Yuri Noviello
• Enrico Pallotta
• Flavio Pinzarrone
• Giuseppe Tanzi

Second assignement for the "Natural Language Processing" course of the Artificial Intelligence master's degree at University of Bologna.

Abstract

Conversational question answering is a task in natural language processing where the goal is to generate a natural language response to a question based on a given context and previous conversation history. Transformer-based models have recently shown promise in this task due to their ability to handle long-range dependencies and encode rich contextual information. In this report we present results on the task achieved using seq2seq transformer-based models with DistilRoBERTa and BERT-tiny, fine-tuned on the CoQA dataset.

Dataset

CoQA is a large-scale dataset for building Conversational Question Answering systems. CoQA contains 127,000+ questions with answers collected from 8000+ conversations. Each conversation is collected by pairing two crowdworkers to chat about a passage in the form of questions and answers. The unique features of CoQA include:

• the questions are conversational;
• the answers can be free-form text;
• each answer also comes with an evidence subsequence highlighted in the passage;
• the passages are collected from seven diverse domains.

Resources and references

• Pytorch
• HuggingFace
• CoQA dataset