57 citations · 263 across the 45 of their papers we have counts for
7 papers · 2 filters
AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents
Bevan Koopman, Ahmed Mourad, Hang Li +6
Decisions in agriculture are increasingly data-driven; however, valuable agricultural knowledge is often locked away in free-text reports, manuals and journal articles. Specialised…
Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation
Shengyao Zhuang, Houxing Ren, Linjun Shou +4
The Differentiable Search Index (DSI) is an emerging paradigm for information retrieval. Unlike traditional retrieval architectures where index and retrieval are two different and…
To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers
Hang Li, Shuai Wang, Shengyao Zhuang +4
Current pre-trained language model approaches to information retrieval can be broadly divided into two categories: sparse retrievers (to which belong also non-neural approaches suc…
Implicit Feedback for Dense Passage Retrieval: A Counterfactual Approach
Shengyao Zhuang, Hang Li, Guido Zuccon
In this paper we study how to effectively exploit implicit feedback in Dense Retrievers (DRs). We consider the specific case in which click data from a historic click log is availa…
CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos
Shengyao Zhuang, Guido Zuccon
Current dense retrievers are not robust to out-of-domain and outlier queries, i.e. their effectiveness on these queries is much poorer than what one would expect. In this paper, we…
Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training
Shengyao Zhuang, Guido Zuccon
The process of model checkpoint validation refers to the evaluation of the performance of a model checkpoint executed on a held-out portion of the training data while learning the…
Reinforcement Online Learning to Rank with Unbiased Reward Shaping
Shengyao Zhuang, Zhihao Qiao, Guido Zuccon
Online learning to rank (OLTR) aims to learn a ranker directly from implicit feedback derived from users' interactions, such as clicks. Clicks however are a biased signal: specific…