[HTML][HTML] Evaluating the state-of-the-art of end-to-end natural language generation: The e2e nlg challenge
This paper provides a comprehensive analysis of the first shared task on End-to-End Natural
Language Generation (NLG) and identifies avenues for future research based on the results …
Language Generation (NLG) and identifies avenues for future research based on the results …
Long and diverse text generation with planning-based hierarchical variational model
Existing neural methods for data-to-text generation are still struggling to produce long and
diverse texts: they are insufficient to model input data dynamically during generation, to …
diverse texts: they are insufficient to model input data dynamically during generation, to …
Robust (controlled) table-to-text generation with structure-aware equivariance learning
Controlled table-to-text generation seeks to generate natural language descriptions for
highlighted subparts of a table. Previous SOTA systems still employ a sequence-to …
highlighted subparts of a table. Previous SOTA systems still employ a sequence-to …
Crossing the conversational chasm: A primer on natural language processing for multilingual task-oriented dialogue systems
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent with the
aim of completing a concrete task. Although this technology represents one of the central …
aim of completing a concrete task. Although this technology represents one of the central …
Scigen: a dataset for reasoning-aware text generation from scientific tables
We introduce SciGen, a new challenge dataset consisting of tables from scientific articles
and their corresponding descriptions, for the task of reasoning-aware data-to-text …
and their corresponding descriptions, for the task of reasoning-aware data-to-text …
Stylized data-to-text generation: A case study in the e-commerce domain
Existing data-to-text generation efforts mainly focus on generating a coherent text from non-
linguistic input data, such as tables and attribute–value pairs, but overlook that different …
linguistic input data, such as tables and attribute–value pairs, but overlook that different …
[PDF][PDF] Knowledge-Aware Dialogue Generation via Hierarchical Infobox Accessing and Infobox-Dialogue Interaction Graph Network.
S Wu, M Wang, D Zhang, Y Zhou, Y Li, Z Wu - IJCAI, 2021 - ijcai.org
Due to limited knowledge carried by queries, traditional dialogue systems often face the
dilemma of generating boring responses, leading to poor user experience. To alleviate this …
dilemma of generating boring responses, leading to poor user experience. To alleviate this …
Improving encoder by auxiliary supervision tasks for table-to-text generation
Table-to-text generation aims at automatically generating natural text to help people
conveniently obtain salient information in tables. Although neural models for table-to-text …
conveniently obtain salient information in tables. Although neural models for table-to-text …
Enhancing neural data-to-text generation models with external background knowledge
Recent neural models for data-to-text generation rely on massive parallel pairs of data and
text to learn the writing knowledge. They often assume that writing knowledge can be …
text to learn the writing knowledge. They often assume that writing knowledge can be …
Table to text generation with accurate content copying
Y Yang, J Cao, Y Wen, P Zhang - Scientific reports, 2021 - nature.com
Generating fluent, coherent, and informative text from structured data is called table-to-text
generation. Copying words from the table is a common method to solve the “out-of …
generation. Copying words from the table is a common method to solve the “out-of …