230 citations · 559 across the 22 of their papers we have counts for
23 papers
ArK: Augmented Reality with Knowledge Interactive Emergent Ability
Qiuyuan Huang, Jae Sung Park, Abhinav Gupta +8
Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2D/3D scenes in unseen environments. The…
Understanding Causality with Large Language Models: Feasibility and Opportunities
Cheng Zhang, Stefan Bauer, Paul Bennett +8
We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question. We believe that…
Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories
Suyu Ge, Chenyan Xiong, Corby Rosset +3
In this paper we improve the zero-shot generalization ability of language models via Mixture-Of-Memory Augmentation (MoMA), a mechanism that retrieves augmentation documents from m…
Imagining Future Digital Assistants at Work: A Study of Task Management Needs
Yonchanok Khaokaew, Indigo Holcombe-James, Mohammad Saiedur Rahaman +11
Digital Assistants (DAs) can support workers in the workplace and beyond. However, target user needs are not fully understood, and the functions that workers would ideally want a D…
METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals
Payal Bajaj, Chenyan Xiong, Guolin Ke +7
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…
Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
Yu Meng, Chenyan Xiong, Payal Bajaj +4
We present a new framework AMOS that pretrains text encoders with an Adversarial learning curriculum via a Mixture Of Signals from multiple auxiliary generators. Following ELECTRA-…
Neural Approaches to Conversational Information Retrieval
Jianfeng Gao, Chenyan Xiong, Paul Bennett +1
A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface which allows users to interact with the system to seek i…
SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization
Philippe Laban, Tobias Schnabel, Paul N. Bennett +1
In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural language inference (NLI) mo…
Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
Ji Xin, Chenyan Xiong, Ashwin Srinivasan +3
Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding space and then matching them by nearest neighbor search. This requires strong locality…
Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul Bennett +1
This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplici…
Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature
Yu Wang, Jinchao Li, Tristan Naumann +12
Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hund…
Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder
Shuqi Lu, Di He, Chenyan Xiong +6
Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense ret…
COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Yu Meng, Chenyan Xiong, Payal Bajaj +4
We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining…
Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision
Si Sun, Yingzhuo Qian, Zhenghao Liu +5
The effectiveness of Neural Information Retrieval (Neu-IR) often depends on a large scale of in-domain relevance training signals, which are not always available in real-world rank…
CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
Chenyan Xiong, Zhenghao Liu, Si Sun +7
Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the cor…
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Lee Xiong, Chenyan Xiong, Ye Li +5
Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires…
Knowledge-Aware Language Model Pretraining
Corby Rosset, Chenyan Xiong, Minh Phan +3
How much knowledge do pretrained language models hold? Recent research observed that pretrained transformers are adept at modeling semantics but it is unclear to what degree they g…
Few-Shot Generative Conversational Query Rewriting
Shi Yu, Jiahua Liu, Jingqin Yang +4
Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing inform…
Analyzing and Learning from User Interactions for Search Clarification
Hamed Zamani, Bhaskar Mitra, Everest Chen +5
Asking clarifying questions in response to search queries has been recognized as a useful technique for revealing the underlying intent of the query. Clarification has applications…
Generic Intent Representation in Web Search
Hongfei Zhang, Xia Song, Chenyan Xiong +4
This paper presents GEneric iNtent Encoder (GEN Encoder) which learns a distributed representation space for user intent in search. Leveraging large scale user clicks from Bing sea…
Improving Recommender Systems Beyond the Algorithm
Tobias Schnabel, Paul N. Bennett, Thorsten Joachims
Recommender systems rely heavily on the predictive accuracy of the learning algorithm. Most work on improving accuracy has focused on the learning algorithm itself. We argue that t…
Using Shortlists to Support Decision Making and Improve Recommender System Performance
Tobias Schnabel, Paul N. Bennett, Susan T. Dumais +1
In this paper, we study shortlists as an interface component for recommender systems with the dual goal of supporting the user's decision process, as well as improving implicit fee…
Events and Controversies: Influences of a Shocking News Event on Information Seeking
Danai Koutra, Paul Bennett, Eric Horvitz
It has been suggested that online search and retrieval contributes to the intellectual isolation of users within their preexisting ideologies, where people's prior views are streng…