Chenyan Xiong

Leading Conversational Search by Suggesting Useful Questions

2020

This paper studies a new scenario in conversational search, conversational question suggestion, which leads search engine users to more engaging experiences by suggesting interesting, informative, and useful follow-up questions. We first establish a novel evaluation …

METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

2022 · arXiv (Cornell University)

We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. Originated in ELECTRA, this training strategy has demonstrated sample-efficiency to pretrain models at the scale of …

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

2025 · arXiv (Cornell University)

Recent large language models such as Gemini-1.5, DeepSeek-V3, and Llama-4 increasingly adopt Mixture-of-Experts (MoE) architectures, which offer strong efficiency-performance trade-offs by activating only a fraction of the model per token. Yet academic researchers still lack …

Bag-of-Entities Representation for Ranking

2016

This paper presents a new bag-of-entities representation for document ranking, with the help of modern knowledge bases and automatic entity linking. Our system represents query and documents by bag-of-entities vectors constructed from their entity annotations, …

Query-Biased Partitioning for Selective Search

2016

Selective search is a cluster-based distributed retrieval architecture that reduces computational costs by partitioning a corpus into topical shards, and selectively searching them. Prior research formed topical shards by clustering the corpus based on the …

Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding

2017

This paper introduces Explicit Semantic Ranking (ESR), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, SemanticScholar.org, reveals that a major error source is its …

End-to-End Neural Ad-hoc Ranking with Kernel Pooling

2017

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling …

Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search

2018

This paper presents \textttConv-KNRM, a Convolutional Kernel-based Neural Ranking Model that models n-gram soft matches for ad-hoc search. Instead of exact matching query and document n-grams, \textttConv-KNRM uses Convolutional Neural Networks to represent n-grams of …