Papers with neural generation models

6 papers
Injecting Entity Types into Entity-Guided Text Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances in deep generative modeling have led to significant advances in natural language generation (NLG).
Approach: They propose to model the entity type carefully in the decoding phase to generate contextual words accurately.
Outcome: The proposed model produces a target sequence based on a given list of entities.
Posterior Control of Blackbox Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for conditional natural language generation are limited in their ability to produce controlled output.
Approach: They propose to augment neural generation models with discrete control states learned through a structured latent-variable approach.
Outcome: The proposed approach improves over benchmarks while providing fine-grained control.
FRUIT: Faithfully Reflecting Updated Information in Text (2022.naacl-main)

Copied to clipboard

Challenge: Existing work on generating edits grounded in external knowledge has focused on correcting grammar and reducing repetitive typing.
Approach: They propose a novel task where the goal is to update an existing article given new evidence by using a dataset of 170K distantly supervised data produced from Wikipedia snapshots.
Outcome: The proposed model can update Wikipedia articles faithfully with new capabilities and opens doors to many new applications.
Barch: an English Dataset of Bar Chart Summaries (2022.lrec-1)

Copied to clipboard

Challenge: a new dataset of human-written summaries of bar charts is available in english . a chart summary is a textual description of a data point, which is often analytical .
Approach: They propose a dataset of human-written summaries describing bar charts in english . a total of 47 charts are presented in the dataset, which includes 47 charts .
Outcome: a new dataset of human-written summaries describing bar charts is presented in english . the dataset shows that human speakers often include such statements into chart summary .
DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation (2021.acl-long)

Copied to clipboard

Challenge: Existing neural generation models fall short of coherence, thus requiring efficient content planning.
Approach: They propose a generation framework that conducts dynamic planning of content while generating the output based on a novel design of mixed language models.
Outcome: The proposed model outperforms competing models on argument generation and writing articles using New York Times’ Opinion section.
Ontologically Faithful Generation of Non-Player Character Dialogues (2024.emnlp-main)

Copied to clipboard

Challenge: a key challenge in creating NPC dialogues is that they should serve coherent narratives.
Approach: They propose to use supervised and in-context learning techniques to generate trees of dialogue between video game characters that accurately reflect quest and entity specifications.
Outcome: The proposed model performs well but room for improvement.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations