Generating visually grounded image captions with specific linguistic sty...
Aspect Sentiment Triplet Extraction (ASTE) is widely used in various
app...
Multimodal speech emotion recognition aims to detect speakers' emotions ...
Neural-symbolic computing aims at integrating robust neural learning and...
As one of the challenging NLP tasks, designing math word problem (MWP)
s...
In recent years, vision and language pre-training (VLP) models have adva...
Multi-Label Few-Shot Aspect Category Detection (FS-ACD) is a new sub-tas...
Complaining is a speech act that expresses a negative inconsistency betw...
Recently, parallel text generation has received widespread attention due...
Unknown intent detection aims to identify the out-of-distribution (OOD)
...
Transformer architecture achieves great success in abundant natural lang...
Non-autoregressive Transformer is a promising text generation model. How...
Social recommendation is effective in improving the recommendation
perfo...
Aspect-based sentiment analysis (ABSA) aims at analyzing the sentiment o...
Aspect-level sentiment classification (ALSC) and aspect oriented opinion...
Aspect-level sentiment classification (ASC) aims to detect the sentiment...
Aspect-oriented Fine-grained Opinion Extraction (AFOE) aims at extractin...
Recent studies show that the attention heads in Transformer are not equa...
Cross-prompt automated essay scoring (AES) requires the system to use no...
Existing question answering systems can only predict answers without exp...
Neural machine translation systems tend to fail on less de-cent inputs
d...
In sequence labeling, previous domain adaptation methods focus on the
ad...
Scenario-based question answering (SQA) has attracted increasing researc...
Variational auto-encoders (VAEs) are widely used in natural language
gen...
Generative adversarial nets (GAN) has been successfully introduced for
g...
Existing neural machine translation systems do not explicitly model what...
In the encoder-decoder architecture for neural machine translation (NMT)...
Pairwise ranking methods are the basis of many widely used discriminativ...
Modern statistical machine translation (SMT) systems usually use a linea...