Alert button
Picture for David Wan

David Wan

Alert button

HistAlign: Improving Context Dependency in Language Generation by Aligning with History

May 08, 2023
David Wan, Shiyue Zhang, Mohit Bansal

Figure 1 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 2 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 3 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Figure 4 for HistAlign: Improving Context Dependency in Language Generation by Aligning with History
Viaarxiv icon

Faithfulness-Aware Decoding Strategies for Abstractive Summarization

Mar 06, 2023
David Wan, Mengwen Liu, Kathleen McKeown, Markus Dreyer, Mohit Bansal

Figure 1 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 2 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 3 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Figure 4 for Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Viaarxiv icon

Evaluating and Improving Factuality in Multimodal Abstractive Summarization

Nov 04, 2022
David Wan, Mohit Bansal

Figure 1 for Evaluating and Improving Factuality in Multimodal Abstractive Summarization
Figure 2 for Evaluating and Improving Factuality in Multimodal Abstractive Summarization
Figure 3 for Evaluating and Improving Factuality in Multimodal Abstractive Summarization
Figure 4 for Evaluating and Improving Factuality in Multimodal Abstractive Summarization
Viaarxiv icon

Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization

Sep 08, 2022
Shiyue Zhang, David Wan, Mohit Bansal

Figure 1 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 2 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 3 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Figure 4 for Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization
Viaarxiv icon

FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization

May 16, 2022
David Wan, Mohit Bansal

Figure 1 for FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
Figure 2 for FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
Figure 3 for FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
Figure 4 for FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
Viaarxiv icon

Segmenting Subtitles for Correcting ASR Segmentation Errors

Apr 16, 2021
David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan, Petra Galuščáková, Elena Zotkina, Zhengping Jiang, Peter Bell, Kathleen McKeown

Figure 1 for Segmenting Subtitles for Correcting ASR Segmentation Errors
Figure 2 for Segmenting Subtitles for Correcting ASR Segmentation Errors
Figure 3 for Segmenting Subtitles for Correcting ASR Segmentation Errors
Figure 4 for Segmenting Subtitles for Correcting ASR Segmentation Errors
Viaarxiv icon

Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines

Oct 19, 2020
David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathleen McKeown

Figure 1 for Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
Figure 2 for Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
Figure 3 for Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
Figure 4 for Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines
Viaarxiv icon

Incorporating Terminology Constraints in Automatic Post-Editing

Oct 19, 2020
David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, Kathleen McKeown

Figure 1 for Incorporating Terminology Constraints in Automatic Post-Editing
Figure 2 for Incorporating Terminology Constraints in Automatic Post-Editing
Figure 3 for Incorporating Terminology Constraints in Automatic Post-Editing
Figure 4 for Incorporating Terminology Constraints in Automatic Post-Editing
Viaarxiv icon