Getting to production with few-shot natural language generation models

P Heidari, A Einolghozati, S Jain, S Batra… - Proceedings of the …, 2021 - aclanthology.org
In this paper, we study the utilization of pre-trained language models to enable few-
shotNatural Language Generation (NLG) in task-oriented dialog systems. We introduce a …

Conversational answer generation and factuality for reading comprehension question-answering

S Peshterliev, B Oguz, D Chatterjee, H Inan… - arxiv preprint arxiv …, 2021 - arxiv.org
Question answering (QA) is an important use case on voice assistants. A popular approach
to QA is extractive reading comprehension (RC) which finds an answer span in a text …

An Answer Verbalization Dataset for Conversational Question Answerings over Knowledge Graphs

E Kacupaj, K Singh, M Maleshkova… - arxiv preprint arxiv …, 2022 - arxiv.org
We introduce a new dataset for conversational question answering over Knowledge Graphs
(KGs) with verbalized answers. Question answering over KGs is currently focused on …

Knowledge extraction from unstructured data

A Sakor - 2023 - repo.uni-hannover.de
Data availability is becoming more essential, considering the current growth of web-based
data. The data available on the web are represented as unstructured, semi-structured, or …

Conversational Question Answering over Knowledge Graphs with Answer Verbalization

E Kacupaj - 2022 - bonndoc.ulb.uni-bonn.de
In recent years, publicly available knowledge graphs (KG) have been broadly adopted as a
source of knowledge in several tasks such as entity linking, relation extraction, and question …

[PDF][PDF] OPPORTUNITIES AND CHALLENGES OF DEEP LEARNING IMPLEMENTATION IN SOCIAL MEDIA

N VAIČIULIS - 2022 - epublications.vu.lt
During the last twenty years, artificial intelligence has been experiencing its biggest
popularity growth ever. Major changes happened around the year 2000. As mentioned by …