Online recommender systems (RS) aim to match user needs with the vast am...
Large language models (LLMs) have shown remarkable capacity for in-conte...
Code Large Language Models (Code LLMs), such as StarCoder, have demonstr...
Information retrieval (IR) plays a crucial role in locating relevant
res...
Large Language Models (LLMs) have significantly advanced natural languag...
Code execution is a fundamental aspect of programming language semantics...
In this work, we propose a simple method that applies a large language m...
Training large language models (LLM) with open-domain instruction follow...
Current dense retrievers (DRs) are limited in their ability to effective...
Text summarization has a wide range of applications in many scenarios. T...
In monolingual dense retrieval, lots of works focus on how to distill
kn...
Recent multilingual pre-trained models have shown better performance in
...
Image-text retrieval (ITR) is a task to retrieve the relevant images/tex...
Recently multi-lingual pre-trained language models (PLM) such as mBERT a...
Long document retrieval aims to fetch query-relevant documents from a
la...
To improve the performance of the dual-encoder retriever, one effective
...
Dense retrieval aims to map queries and passages into low-dimensional ve...
Knowledge distillation is often used to transfer knowledge from a strong...
Although speech is a simple and effective way for humans to communicate ...
Code contrastive pre-training has recently achieved significant progress...
Retrieving evidences from tabular and textual resources is essential for...
Knowledge distillation is an effective way to transfer knowledge from a
...
In large-scale retrieval, the lexicon-weighting paradigm, learning weigh...
Retrieval models based on dense representations in semantic space have b...
Gazetteer is widely used in Chinese named entity recognition (NER) to en...
This paper focuses on text data augmentation for few-shot NLP tasks. The...
The Differentiable Search Index (DSI) is a new, emerging paradigm for
in...
A ranker plays an indispensable role in the de facto 'retrieval rera...
Recent research demonstrates the effectiveness of using pretrained langu...
The sparse Mixture-of-Experts (MoE) model is powerful for large-scale
pr...
As more and more pre-trained language models adopt on-cloud deployment, ...
The learn-to-compare paradigm of contrastive representation learning (CR...
Large-scale retrieval is to recall relevant documents from a huge collec...
Although spoken language understanding (SLU) has achieved great success ...
Current Knowledge-Grounded Dialogue Generation (KDG) models specialize i...
Knowledge graph (KG) based Collaborative Filtering is an effective appro...
The conversational recommender systems (CRSs) have received extensive
at...
Generating natural and informative texts has been a long-standing proble...
Recently, various response generation models for two-party conversations...
Dense retrieval has achieved impressive advances in first-stage retrieva...
Generating new events given context with correlated ones plays a crucial...
This paper focuses on the Data Augmentation for low-resource Natural Lan...
Language guided image inpainting aims to fill in the defective regions o...
Learning sentence embeddings in an unsupervised manner is fundamental in...
In this paper, we propose the CodeRetriever model, which combines the
un...
This paper presents a unified multimodal pre-trained model called NÜWA t...
Retrieve-based dialogue response selection aims to find a proper respons...
Responsing with image has been recognized as an important capability for...
In this paper, we present a pre-trained language model (PLM) based frame...
Event correlation reasoning infers whether a natural language paragraph
...