198 citations · 949 across the 29 of their papers we have counts for
29 papers
Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
Shicheng Xu, Liang Pang, Huawei Shen +1
Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship…
Uncertainty Calibration for Ensemble-Based Debiasing Methods
Ruibin Xiong, Yimeng Chen, Liang Pang +2
Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adju…
Transductive Learning for Unsupervised Text Style Transfer
Fei Xiao, Liang Pang, Yanyan Lan +3
Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and…
Adaptive Information Seeking for Open-Domain Question Answering
Yunchang Zhu, Liang Pang, Yanyan Lan +2
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to b…
Toward the Understanding of Deep Text Matching Models for Information Retrieval
Lijuan Chen, Yanyan Lan, Liang Pang +2
Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance im…
Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm
Lin Bo, Liang Pang, Gang Wang +3
Recently, pre-trained language models such as BERT have been applied to document ranking for information retrieval, which first pre-train a general language model on an unlabeled l…
Sketch and Customize: A Counterfactual Story Generator
Changying Hao, Liang Pang, Yanyan Lan +3
Recent text generation models are easy to generate relevant and fluent text for the given text, while lack of causal reasoning ability when we change some parts of the given text.…
Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
Liang Pang, Yanyan Lan, Xueqi Cheng
Neural text matching models have been widely used in community question answering, information retrieval, and dialogue. However, these models designed for short texts cannot well a…
Transformation Driven Visual Reasoning
Xin Hong, Yanyan Lan, Liang Pang +2
This paper defines a new visual reasoning paradigm by introducing an important factor, i.e.~transformation. The motivation comes from the fact that most existing visual reasoning t…
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
Weijie Yu, Chen Xu, Jun Xu +4
One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be r…
Beyond Language: Learning Commonsense from Images for Reasoning
Wanqing Cui, Yanyan Lan, Liang Pang +2
This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in…
Ranking Enhanced Dialogue Generation
Changying Hao, Liang Pang, Yanyan Lan +3
How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., re…
Robust Reinforcement Learning with Wasserstein Constraint
Linfang Hou, Liang Pang, Xin Hong +3
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness t…
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
Liang Pang, Jun Xu, Qingyao Ai +3
In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents. Therefore, an ideal…
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
Hainan Zhang, Yanyan Lan, Liang Pang +2
In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a su…
A Deep Look into Neural Ranking Models for Information Retrieval
Jiafeng Guo, Yixing Fan, Liang Pang +6
Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from tr…
HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
Liang Pang, Yanyan Lan, Jiafeng Guo +3
This paper is concerned with open-domain question answering (i.e., OpenQA). Recently, some works have viewed this problem as a reading comprehension (RC) task, and directly applied…
Continual Match Based Training in Pommerman: Technical Report
Peng Peng, Liang Pang, Yufeng Yuan +1
Continual learning is the ability of agents to improve their capacities throughout multiple tasks continually. While recent works in the literature of continual learning mostly foc…
Locally Smoothed Neural Networks
Liang Pang, Yanyan Lan, Jun Xu +2
Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often cruci…
Learning Visual Features from Snapshots for Web Search
Yixing Fan, Jiafeng Guo, Yanyan Lan +3
When applying learning to rank algorithms to Web search, a large number of features are usually designed to capture the relevance signals. Most of these features are computed based…
DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
Liang Pang, Yanyan Lan, Jiafeng Guo +3
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR). Existing deep IR models such as DSSM and CDSSM directly apply neural networks to ge…
A Deep Investigation of Deep IR Models
Liang Pang, Yanyan Lan, Jiafeng Guo +2
The effective of information retrieval (IR) systems have become more important than ever. Deep IR models have gained increasing attention for its ability to automatically learning…
MatchZoo: A Toolkit for Deep Text Matching
Yixing Fan, Liang Pang, JianPeng Hou +3
In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared…
A Study of MatchPyramid Models on Ad-hoc Retrieval
Liang Pang, Yanyan Lan, Jiafeng Guo +2
Deep neural networks have been successfully applied to many text matching tasks, such as paraphrase identification, question answering, and machine translation. Although ad-hoc ret…