416 citations · 1.6k across the 85 of their papers we have counts for
64 papers · 1 filter
Hypertext Entity Extraction in Webpage
Yifei Yang, Tianqiao Liu, Bo Shao +4
Webpage entity extraction is a fundamental natural language processing task in both research and applications. Nowadays, the majority of webpage entity extraction models are traine…
Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency
Zilin Xiao, Linjun Shou, Xingyao Zhang +4
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using…
Instructed Language Models with Retrievers Are Powerful Entity Linkers
Zilin Xiao, Ming Gong, Jie Wu +4
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature stil…
Alleviating Over-smoothing for Unsupervised Sentence Representation
Nuo Chen, Linjun Shou, Ming Gong +5
Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language mo…
Large Language Models are Diverse Role-Players for Summarization Evaluation
Ning Wu, Ming Gong, Linjun Shou +2
Text summarization has a wide range of applications in many scenarios. The evaluation of the quality of the generated text is a complex problem. A big challenge to language evaluat…
Bridge the Gap between Language models and Tabular Understanding
Nuo Chen, Linjun Shou, Ming Gong +5
Table pretrain-then-finetune paradigm has been proposed and employed at a rapid pace after the success of pre-training in the natural language domain. Despite the promising finding…
Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval
Shunyu Zhang, Yaobo Liang, Ming Gong +2
Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are…
MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
Kun Zhou, Xiao Liu, Yeyun Gong +4
Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-tr…
Soft-Labeled Contrastive Pre-training for Function-level Code Representation
Xiaonan Li, Daya Guo, Yeyun Gong +6
Code contrastive pre-training has recently achieved significant progress on code-related tasks. In this paper, we present \textbf{SCodeR}, a \textbf{S}oft-labeled contrastive pre-t…
Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA
Junjie Huang, Wanjun Zhong, Qian Liu +3
Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training a…
Rethinking the Value of Gazetteer in Chinese Named Entity Recognition
Qianglong Chen, Xiangji Zeng, Jiangang Zhu +4
Gazetteer is widely used in Chinese named entity recognition (NER) to enhance span boundary detection and type classification. However, to further understand the generalizability a…
Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding
Shining Liang, Linjun Shou, Jian Pei +4
Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled trai…
Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling
Nuo Chen, Linjun Shou, Ming Gong +2
Large-scale cross-lingual pre-trained language models (xPLMs) have shown effectiveness in cross-lingual sequence labeling tasks (xSL), such as cross-lingual machine reading compreh…
Multi-View Document Representation Learning for Open-Domain Dense Retrieval
Shunyu Zhang, Yaobo Liang, Ming Gong +2
Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector…
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
Qiyu Wu, Chongyang Tao, Tao Shen +3
Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervi…
CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search
Xiaonan Li, Yeyun Gong, Yelong Shen +7
In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt tw…
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
Yuntao Li, Can Xu, Huang Hu +3
Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yie…
EventBERT: A Pre-Trained Model for Event Correlation Reasoning
Yucheng Zhou, Xiubo Geng, Tao Shen +2
Event correlation reasoning infers whether a natural language paragraph containing multiple events conforms to human common sense. For example, "Andrew was very drowsy, so he took…
Multimodal Dialogue Response Generation
Qingfeng Sun, Yujing Wang, Can Xu +7
Responsing with image has been recognized as an important capability for an intelligent conversational agent. Yet existing works only focus on exploring the multimodal dialogue mod…
Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
Chongyang Tao, Jiazhan Feng, Chang Liu +3
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the ad…
Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding
Yingmei Guo, Linjun Shou, Jian Pei +4
Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have be…
Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
Wei Chen, Yeyun Gong, Can Xu +9
We study the problem of coarse-grained response selection in retrieval-based dialogue systems. The problem is equally important with fine-grained response selection, but is less ex…
Maria: A Visual Experience Powered Conversational Agent
Zujie Liang, Huang Hu, Can Xu +5
Arguably, the visual perception of conversational agents to the physical world is a key way for them to exhibit the human-like intelligence. Image-grounded conversation is thus pro…
Language Scaling for Universal Suggested Replies Model
Qianlan Ying, Payal Bajaj, Budhaditya Deb +7
We consider the problem of scaling automated suggested replies for Outlook email system to multiple languages. Faced with increased compute requirements and low resources for langu…