Online recommender systems (RS) aim to match user needs with the vast am...
Current dense retrievers (DRs) are limited in their ability to effective...
Artificial Intelligence (AI) has made incredible progress recently. On t...
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
...
Recently multi-lingual pre-trained language models (PLM) such as mBERT a...
Retrieving evidences from tabular and textual resources is essential for...
The Differentiable Search Index (DSI) is a new, emerging paradigm for
in...
Recent research demonstrates the effectiveness of using pretrained langu...
The learn-to-compare paradigm of contrastive representation learning (CR...
Although spoken language understanding (SLU) has achieved great success ...
Knowledge graph (KG) based Collaborative Filtering is an effective appro...
Dense retrieval has achieved impressive advances in first-stage retrieva...
Lack of training data presents a grand challenge to scaling out spoken
l...
Spoken Language Understanding (SLU) is composed of two subtasks: intent
...
Named entity recognition (NER) is a fundamental component in many
applic...
Producing the embedding of a sentence in an unsupervised way is valuable...
Modern Automatic Speech Recognition (ASR) systems can achieve high
perfo...
Recently, universal neural machine translation (NMT) with shared
encoder...
We study the problem of leveraging the syntactic structure of text to en...
In natural language processing (NLP) tasks, slow inference speed and hug...
Lack of training data in low-resource languages presents huge challenges...
Cross-lingual Machine Reading Comprehension (CLMRC) remains a challengin...
The abundant semi-structured data on the Web, such as HTML-based tables ...
Quantum machine learning is expected to be one of the first practical
ap...
Span extraction is an essential problem in machine reading comprehension...
The Natural Questions (NQ) benchmark set brings new challenges to Machin...
Question Aware Open Information Extraction (Question aware Open IE) take...
Training and refreshing a web-scale Question Answering (QA) system for a...
Training and refreshing a web-scale Question Answering (QA) system for a...
Multilingual pre-trained models could leverage the training data from a ...
Verifying the correctness of a textual statement requires not only seman...
Pre-training text representations has recently been shown to significant...
Modern Automatic Speech Recognition (ASR) systems can achieve high
perfo...
We study the problem of generating inferential texts of events for a var...
In this paper, we introduce XGLUE, a new benchmark dataset to train
larg...
Line segment detection is an essential task in computer vision and image...
We present CodeBERT, a bimodal pre-trained model for programming languag...
Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) h...
Commonsense question answering aims to answer questions which require
ba...
We present Unicoder, a universal language encoder that is insensitive to...
Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have
de...
When building deep neural network models for natural language processing...
In this paper, we propose a novel pretraining-based encoder-decoder
fram...
We proposed a kind of naturally combined shape-color affine moment invar...