Titlebook: Natural Language Processing and Chinese Computing; 8th CCF Internationa Jie Tang,Min-Yen Kan,Hongying Zan Conference proceedings 2019 Sprin

小畫像

rheumatology

Bi-directional Capsule Network Model for Chinese Biomedical Community Question Answeringularly in the biomedical field. On biomedical CQA platforms, patients share information about diseases, drugs and symptoms by communicating with each other. Therefore, the biomedical CQA platforms become particularly valuable resources for information and knowledge acquisition of patients. To accura

AWL

Neural Response Generation with Relevant Emotions for Short Text Conversationy relevant to the post, but should also carry an appropriate emotion. In this paper, we conduct analysis based on social media data to investigate how emotions influence conversation generation. Based on observation, we propose methods to determine the appropriate emotions to be included in a respon

愛哭

Using Bidirectional Transformer-CRF for Spoken Language Understandingnd slot filling (SF). Currently, most effective models carry out these two tasks jointly and often result in better performance than separate models. However, these models usually fail to model the interaction between intent and slots and ties these two tasks only by a joint loss function. In this p

insurgent

Evaluating and Enhancing the Robustness of Retrieval-Based Dialogue Systems with Adversarial Examplebustness towards malicious attacks remains largely untested. In this paper, we generate adversarial examples in black-box settings to evaluate the robustness of retrieval-based dialogue systems. On three representative retrieval-based dialogue models, our attacks reduce R. by 38.3., 45.0. and 31.5.

同時發(fā)生

Many vs. Many Query Matching with Hierarchical BERT and Transformer consist of multiple sentences, namely query matching with informal text. On the basis, we first construct two datasets towards different domains. Then, we propose a novel query matching approach for informal text, namely Many vs. Many Matching with hierarchical BERT and transformer. First, we emplo

atopic

A Knowledge Selective Adversarial Network for Link Prediction in Knowledge GraphKGs, KG completion task, which is also called link prediction, is a newly emerging hot research topic. During KG embedding model training, negative sampling is a fundamental method for obtaining negative samples. Inspired by an adversarial learning framework KBGAN, this paper proposes a new knowledg

evasive

Feature-Level Attention Based Sentence Encoding for Neural Relation Extractionall the features as neural network model input, ignoring the different contribution of the features to the semantic representation of entities relations. In this paper, we propose a feature-level attention model to encode sentences, which tries to reveal the different effects of features for relatio

進(jìn)取心

遷移

Evidence Distilling for Fact Extraction and Verificationm is supposed to extract information from given Wikipedia documents and verify the given claim. In this paper, we present a four-stage model for this task including document retrieval, sentence selection, evidence sufficiency judgement and claim verification. Different from most existing models, we