ChatGPT has gained significant interest due to its impressive performanc...
In this paper, we systematically study the potential of pre-training wit...
Dialogue response selection aims to select an appropriate response from
...
Extracting generalized and robust representations is a major challenge i...
This paper describes our system designed for SemEval-2023 Task 12: Senti...
News recommendation aims to predict click behaviors based on user behavi...
Passage retrieval aims to retrieve relevant passages from large collecti...
Growing techniques have been emerging to improve the performance of pass...
This paper presents a pre-training technique called query-as-context tha...
Capturing emotions within a conversation plays an essential role in mode...
Video language pre-training methods have mainly adopted sparse sampling
...
Contrastive learning has been extensively studied in sentence embedding
...
Dense passage retrieval aims to retrieve the relevant passages of a quer...
The emotion recognition in conversation (ERC) task aims to predict the
e...
The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions a...
Abstract syntax trees (ASTs) play a crucial role in source code
represen...
Before entering the neural network, a token is generally converted to th...
Contrastive learning has been proven suitable for learning sentence
embe...
Contrastive learning has been attracting much attention for learning
uns...
Contrastive learning has been gradually applied to learn high-quality
un...
Detecting rumors on social media is a very critical task with significan...
Session-based recommendation aims to predict user the next action based ...
The rapid development of social media changes the lifestyle of people an...
The problem of code generation from textual program descriptions has lon...
The dissemination of fake news significantly affects personal reputation...
Document-level Sentiment Analysis (DSA) is more challenging due to vague...
Information diffusion prediction is a fundamental task for understanding...
Withthegrowthofknowledgegraphs, entity descriptions are becoming extreme...
Pre-training text representations has recently been shown to significant...
While several state-of-the-art approaches to dialogue state tracking (DS...
Automatically labeling multiple styles for every song is a comprehensive...
The development of social media has revolutionized the way people
commun...
Opinion spam has become a widespread problem in social media, where hire...
Commonsense question answering aims to answer questions which require
ba...
This paper focuses on the task of generating long structured sentences w...
This paper focuses on the task of sentiment transfer on non-parallel tex...
Imbalanced data commonly exists in real world, espacially in
sentiment-r...
Typically, Ultra-deep neural network(UDNN) tends to yield high-quality m...
We propose a novel data augmentation method for labeled sentences called...