Titlebook: Natural Language Processing and Chinese Computing; 9th CCF Internationa Xiaodan Zhu,Min Zhang,Ruifang He Conference proceedings 2020 Spring

Anguish

Adversarial BiLSTM-CRF Architectures for Extra-Propositional Scope Resolutionions in information extraction. Following this trend, recent studies go deeper into learning fine-grained extra-propositional structures, such as negation and speculation. However, most of elaborately-designed experiments reveal that existing extra-proposition models either fail to learn from the co

新娘

現(xiàn)代

Efficient Lifelong Relation Extraction with Dynamic Regularizationthods are designed for a fixed set of relations. They are unable to handle the lifelong learning scenario, i.e. adapting a well-trained model to newly added relations without catastrophically forgetting the previously learned knowledge. In this work, we present a memory-efficient dynamic regularizat

窗簾等

Collective Entity Disambiguation Based on Deep Semantic Neighbors and?Heterogeneous Entity Correlati. A large number of models were proposed based on the topical coherence assumption. Recently, several works have proposed a new assumption: topical coherence only needs to hold among neighboring mentions, which proved to be effective. However, due to the complexity of the text, there are still some

murmur

袋鼠

我的巨大

DCA: Diversified Co-attention Towards Informative Live Video Commentingives via metric learning, to collect a . and . context for comment generation. We also propose an effective parameter orthogonalization technique to avoid excessive overlap of information learned from different perspectives. Results show that our approach outperforms existing methods in the ALVC task, achieving new state-of-the-art results.

熱心助人

Obsessed

ABASH

Macro Discourse Relation Recognition via Discourse Argument Pair Graphd global information and argument-related keyword information. Then, we use a graph learning method to encode argument semantics and recognize the relationship between arguments. The experimental results on the Chinese MCDTB corpus show that our proposed model can effectively recognize the discourse relations and outperforms the SOTA model.