Papers by David Vandyke

5 papers
Non-Autoregressive Text Generation with Pre-trained Language Models (2021.eacl-main)

Copied to clipboard

Challenge: Autoregressive generation models generate tokens in a left-to-right, token-by-token fashion, resulting in lag in inference.
Approach: They propose to use BERT as the backbone of a non-autoregressive generation model for greatly improved performance.
Outcome: The proposed model outperforms existing non-autoregressive models and achieves competitive performance with many strong autoregressive model.
Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to generate paraphrases are decomposable, but some use a sequence-to-sequence model to generate each word in a uniform way.
Approach: They propose a framework for identification then aggregation of input tokens and a custom decoder to generate paraphrases.
Outcome: The proposed framework outperforms previous studies on two benchmark datasets and generates paraphrases in interpretable and controllable way.
TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles (2024.findings-acl)

Copied to clipboard

Challenge: Existing datasets for Task-Oriented Dialogs (TOD) lack consideration for adaptive response styles and neglect to simulate interactions with app contexts like calendars or alarms.
Approach: They propose to generate an annotated task-oriented dialog dataset and an automatic pipeline to generate it.
Outcome: The proposed dataset provides a variety of system response styles and provides verbose or non-verbal responses.
A Generative Model for Joint Natural Language Understanding and Generation (2020.acl-main)

Copied to clipboard

Challenge: Natural language understanding (NLU) and natural language generation (NLG) have opposite goals.
Approach: They propose a generative model which couples NLU and NLG through a shared latent variable.
Outcome: The proposed model achieves state-of-the-art performance on two dialogue datasets with flat and tree-structured formal representations.
Plan-then-Generate: Controlled Data-to-Text Generation via Planning (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on producing results that are close to the references, i.e. what to generate and in what order (the output structure) cannot be explicitly controlled by the users.
Approach: They propose a Plan-then-Generate framework to improve the controllability of neural data-to-text models.
Outcome: The proposed model can control both the intra-sentence and inter-sentent structure of the generated output.

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