Search Results for author: Shengjie Li

Found 10 papers, 1 papers with code

End-to-End Neural Discourse Deixis Resolution in Dialogue

1 code implementation29 Nov 2022 Shengjie Li, Vincent Ng

We adapt Lee et al.'s (2018) span-based entity coreference model to the task of end-to-end discourse deixis resolution in dialogue, specifically by proposing extensions to their model that exploit task-specific characteristics.

Clue: Cross-modal Coherence Modeling for Caption Generation

no code implementations2 May 2020 Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, Matthew Stone

We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning.

controllable image captioning Relation

Cross-modal Coherence Modeling for Caption Generation

no code implementations ACL 2020 Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, Matthew Stone

We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning.

controllable image captioning Relation

Segmenting Epipolar Line

no code implementations11 Oct 2020 Shengjie Li, Qi Cai, Yuanxin Wu

Identifying feature correspondence between two images is a fundamental procedure in three-dimensional computer vision.

Neural Anaphora Resolution in Dialogue

no code implementations ACL (CODI, CRAC) 2021 Hideo Kobayashi, Shengjie Li, Vincent Ng

We describe the systems that we developed for the three tracks of the CODI-CRAC 2021 shared task, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.

coreference-resolution

The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis

no code implementations ACL (CODI, CRAC) 2021 Shengjie Li, Hideo Kobayashi, Vincent Ng

The CODI-CRAC 2021 shared task is the first shared task that focuses exclusively on anaphora resolution in dialogue and provides three tracks, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.

coreference-resolution

Summarizing Dialogues with Negative Cues

no code implementations COLING 2022 Junpeng Liu, Yanyan Zou, Yuxuan Xi, Shengjie Li, Mian Ma, Zhuoye Ding

In this work, rather than directly forcing a summarization system to merely pay more attention to the salient pieces, we propose to explicitly have the model perceive the redundant parts of an input dialogue history during the training phase.

Abstractive Dialogue Summarization

Neural Anaphora Resolution in Dialogue Revisited

no code implementations COLING (CODI, CRAC) 2022 Shengjie Li, Hideo Kobayashi, Vincent Ng

We present the systems that we developed for all three tracks of the CODI-CRAC 2022 shared task, namely the anaphora resolution track, the bridging resolution track, and the discourse deixis resolution track.

Multimodal Propaganda Processing

no code implementations17 Feb 2023 Vincent Ng, Shengjie Li

Propaganda campaigns have long been used to influence public opinion via disseminating biased and/or misleading information.

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