Titlebook: Chinese Computational Linguistics; 22nd China National Maosong Sun,Bing Qin,Yubo Chen Conference proceedings 2023 The Editor(s) (if applic

sphincter

難取悅

Unsupervised Style Transfer in?News Headlines via?Discrete Style Spaceg data is one of the main problems in this field. In this work, we design a .iscrete style space for unsupervised .eadline .tyle .ransfer, short for .. This model decomposes the style-dependent text generation into content-feature extraction and style modelling. Then, generation decoder receives inp

碎石頭

locus-ceruleus

Improving Zero-Shot Cross-Lingual Dialogue State Tracking via?Contrastive Learnings is expensive. Existing models address this issue by code-switched data augmentation or intermediate fine-tuning of multilingual pre-trained models. However, these models can only perform implicit alignment across languages. In this paper, we propose a novel model named .ontrastive .earning for .ro

CHANT

擁護(hù)

A Distantly-Supervised Relation Extraction Method Based on?Selective Gate and?Noise Correctionh results are applied to various fields. To address the problem that current distantly supervised relation extraction (DSRE) methods based on large-scale corpus annotation generate a large amount of noisy data, a DSRE method that incorporates selective gate and noise correction framework is proposed

Crepitus

Improving Cascade Decoding with?Syntax-Aware Aggregator and?Contrastive Learning for?Event Extractiontial benefits of the syntactic structure of sentences. In this paper, we improve cascade decoding with a novel module and a self-supervised task. Specifically, we propose a syntax-aware aggregator module to model the syntax of a sentence based on cascade decoding framework such that it captures eve

Entirety

金哥占卜者

incontinence

Self Question-Answering: Aspect Sentiment Triplet Extraction via?a?Multi-MRC Framework Based on?Rethed opinion terms that explain the underlying cause of the sentiment. Some recent studies fail to capture the strong interdependence between ATE and OTE, while others fail to effectively introduce the relationship between aspects and opinions into sentiment classification tasks. To solve these proble