With the advancement of generative language models, the generated text h...
Multi-aspect controllable text generation aims to generate fluent senten...
Language models trained on large-scale corpora can generate remarkably f...
Dense retrieval has shown promise in the first-stage retrieval process w...
In this paper, we propose a new visual reasoning task, called Visual
Tra...
Most existing visual reasoning tasks, such as CLEVR in VQA, ignore an
im...
With the wide application of Large Language Models (LLMs) such as ChatGP...
Video corpus moment retrieval (VCMR) is the task of retrieving a relevan...
Current natural language understanding (NLU) models have been continuous...
Information retrieval aims to find information that meets users' needs f...
Pseudo-relevance feedback (PRF) has proven to be an effective query
refo...
Text matching is a fundamental technique in both information retrieval a...
Ensemble-based debiasing methods have been shown effective in mitigating...
Unsupervised style transfer models are mainly based on an inductive lear...
Information seeking is an essential step for open-domain question answer...
Semantic text matching is a critical problem in information retrieval.
R...
Recent text generation models are easy to generate relevant and fluent t...
Semantic text matching models have been widely used in community questio...
This paper defines a new visual reasoning paradigm by introducing an
imp...
One approach to matching texts from asymmetrical domains is projecting t...
This paper proposes a novel approach to learn commonsense from images,
i...
Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an...
How to effectively utilize the dialogue history is a crucial problem in
...
Robust Reinforcement Learning aims to find the optimal policy with some
...
The abductive natural language inference task (αNLI) is proposed to
eval...
In learning-to-rank for information retrieval, a ranking model is
automa...
In multi-turn dialogue generation, response is usually related with only...
Ranking models lie at the heart of research on information retrieval (IR...
This paper is concerned with open-domain question answering (i.e., OpenQ...
Continual learning is the ability of agents to improve their capacities
...
Convolutional Neural Networks (CNN) and the locally connected layer are
...
When applying learning to rank algorithms to Web search, a large number ...
This paper concerns a deep learning approach to relevance ranking in
inf...
In recent years, deep neural models have been widely adopted for text
ma...
Semantic matching, which aims to determine the matching degree between t...
Matching two texts is a fundamental problem in many natural language
pro...
Matching natural language sentences is central for many applications suc...