Search Results for author: Dongqi Pu

Found 5 papers, 0 papers with code

Passing Parser Uncertainty to the Transformer. Labeled Dependency Distributions for Neural Machine Translation.

no code implementations EAMT 2022 Dongqi Pu, Khalil Sima’an

Existing syntax-enriched neural machine translation (NMT) models work either with the single most-likely unlabeled parse or the set of n-best unlabeled parses coming out of an external parser.

Machine Translation NMT +1

SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation

no code implementations26 Mar 2024 Dongqi Pu, Yifan Wang, Jia Loy, Vera Demberg

Scientific news reports serve as a bridge, adeptly translating complex research articles into reports that resonate with the broader public.

Text Generation

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer

no code implementations13 Jun 2023 Dongqi Pu, Vera Demberg

Large-scale language models, like ChatGPT, have garnered significant media attention and stunned the public with their remarkable capacity for generating coherent text from short natural language prompts.

Sentence Style Transfer +1

Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization

no code implementations26 May 2023 Dongqi Pu, Yifan Wang, Vera Demberg

For text summarization, the role of discourse structure is pivotal in discerning the core content of a text.

Abstractive Text Summarization

Cannot find the paper you are looking for? You can Submit a new open access paper.