41 |
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
42 |
Svar: A Tiny C++ Header Brings Unified Interface for Multiple programming Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
43 |
A Short Introduction to Information-Theoretic Cost-Benefit Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
YACLC: A Chinese Learner Corpus with Multidimensional Annotation ...
|
|
|
|
BASE
|
|
Show details
|
|
45 |
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Modeling Bilingual Conversational Characteristics for Neural Chat Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
49 |
CPM-2: Large-scale Cost-effective Pre-trained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
50 |
Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding ...
|
|
|
|
BASE
|
|
Show details
|
|
51 |
Rethinking the Two-Stage Framework for Grounded Situation Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
52 |
Knowledge Graph Completion with Text-aided Regularization ...
|
|
|
|
Abstract:
Knowledge Graph Completion is a task of expanding the knowledge graph/base through estimating possible entities, or proper nouns, that can be connected using a set of predefined relations, or verb/predicates describing interconnections of two things. Generally, we describe this problem as adding new edges to a current network of vertices and edges. Traditional approaches mainly focus on using the existing graphical information that is intrinsic of the graph and train the corresponding embeddings to describe the information; however, we think that the corpus that are related to the entities should also contain information that can positively influence the embeddings to better make predictions. In our project, we try numerous ways of using extracted or raw textual information to help existing KG embedding frameworks reach better prediction results, in the means of adding a similarity function to the regularization part in the loss function. Results have shown that we have made decent improvements over baseline ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Information Retrieval cs.IR
|
|
URL: https://arxiv.org/abs/2101.08962 https://dx.doi.org/10.48550/arxiv.2101.08962
|
|
BASE
|
|
Hide details
|
|
54 |
Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms ...
|
|
|
|
BASE
|
|
Show details
|
|
55 |
Automatic Construction of Sememe Knowledge Bases via Dictionaries ...
|
|
|
|
BASE
|
|
Show details
|
|
56 |
An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
Personalized Transformer for Explainable Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|