Specifically, we first conduct domain-aware pre-training using large-scale multi-scenario multi-domain dialogue data to enhance the adaptability of our pre-trained model.
Therefore, we propose a novel Coarse-to-Fine contribution network for multimodal Summarization (CFSum) to consider different contributions of images for summarization.
To alleviate the CF, we investigate knowledge distillation based life-long learning methods.
Therefore, we propose a novel role interaction enhanced method for role-oriented dialogue summarization.
Therefore, in this paper, we introduce a novel Chinese dataset for Customer Service Dialogue Summarization (CSDS).
In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized.
Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence.
End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way.
Cross-lingual summarization aims at summarizing a document in one language (e. g., Chinese) into another language (e. g., English).
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.
In this paper, we propose a novel task, multimodal summarization with multimodal output (MSMO).
In this paper, we investigate the sentence summarization task that produces a summary from a source sentence.
Ranked #7 on Text Summarization on DUC 2004 Task 1
In this work, we propose an extractive Multi-modal Summarization (MMS) method which can automatically generate a textual summary given a set of documents, images, audios and videos related to a specific topic.