Search Results for author:
Found 16 papers, 6 papers with code
More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge
Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage.
KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding
Knowledge-enhanced methods have bridged the gap between human beings and machines in generating dialogue responses.
Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model
However, a dialogue is always aligned to a lot of retrieved fact candidates; as a result, the linearized text is always lengthy and then significantly increases the burden of using PLMs.
Adaptive Pseudo-Siamese Policy Network for Temporal Knowledge Prediction
Specifically, we design the policy network in our model as a pseudo-siamese policy network that consists of two sub-policy networks.
MixKG: Mixing for harder negative samples in knowledge graph
The representations of entities and relations are learned via contrasting the positive and negative triplets.
Knowledge graph enhanced recommender system
This is attributed to the rich attribute information contained in KG to improve item and user representations as side information.
SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification
Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances.
Ranked #1 on
Speaker Verification
on VoxCeleb
Dynamic Multi-scale Convolution for Dialect Identification
To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling.
Multi-Level Graph Contrastive Learning
In this paper, we propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs.
Tucker decomposition-based Temporal Knowledge Graph Completion
Developing the model for temporal knowledge graphs completion is an increasingly important task.
Self-supervised Graph Representation Learning via Bootstrapping
In addition, we summarize three kinds of augmentation methods for graph-structured data and apply them to the DGB.
Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues
Given a query, our approach first retrieves a set of prototype dialogues that are relevant to the query.
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness
We collect and build a large-scale Chinese dataset aligned with the commonsense knowledge for dialogue generation.
Traffic Danger Recognition With Surveillance Cameras Without Training Data
Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories.
HL-EncDec: A Hybrid-Level Encoder-Decoder for Neural Response Generation
Recent years have witnessed a surge of interest on response generation for neural conversation systems.
MOBA-Slice: A Time Slice Based Evaluation Framework of Relative Advantage between Teams in MOBA Games
In this paper, we introduce MOBA-Slice, a time slice based evaluation framework of relative advantage between teams in MOBA games.
