Xueqi Cheng

B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval

2021 · arXiv (Cornell University)

Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method …

Locate Who You Are: Matching Geo-location to Text for Anchor Link Prediction.

2021 · arXiv (Cornell University)

Nowadays, users are encouraged to activate across multiple online social networks simultaneously. Anchor link prediction, which aims to reveal the correspondence among different accounts of the same user across networks, has been regarded as a …

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

2022 · arXiv (Cornell University)

Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents. Existing PRF …

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate documents. This vulnerability raises …

RLKD: Distilling LLMs' Reasoning via Reinforcement Learning

2025 · arXiv (Cornell University)

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher models often …

Learning Hierarchical Representation Model for NextBasket Recommendation

2015

Next basket recommendation is a crucial task in market basket analysis. Given a user's purchase history, usually a sequence of transaction data, one attempts to build a recommender that can predict the next few items …

A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot …

Modeling Document Novelty with Neural Tensor Network for Search Result Diversification

2016

Search result diversification has attracted considerable attention as a means to tackle the ambiguous or multi-faceted information needs of users. One of the key problems in search result diversification is novelty, that is, how to …

Reinforcement Learning to Rank with Markov Decision Process

2017

One of the central issues in learning to rank for information retrieval is to develop algorithms that construct ranking models by directly optimizing evaluation measures such as normalized discounted cumulative gain~(ND CG). Existing methods usually …

Cross-Domain Recommendation: An Embedding and Mapping Approach

2017

Data sparsity is one of the most challenging problems for recommender systems. One promising solution to this problem is cross-domain recommendation, i.e., leveraging feedbacks or ratings from multiple domains to improve recommendation performance in a …

Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation

2018

Point-of-interest (POI) recommendation, i.e., recommending unvisited POIs for users, is a fundamental problem for location-based social networks. POI recommendation distinguishes itself from traditional item recommendation, e.g., movie recommendation, via geographical influence among POIs. Existing methods …

A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

2015 · arXiv (Cornell University)

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot …