English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this paper, we report our methods and experiments for the TRECConversational Assistance Track (CAsT) 2022. In this work, we aim to reproducemulti-stage retrieval pipelines and explore one of the potential benefits ofinvolving mixed-initiative interaction in conversational passage retrievalscenarios: reformulating raw queries. Before the first ranking stage of amulti-stage retrieval pipeline, we propose a mixed-initiative query rewritingmodule, which achieves query rewriting based on the mixed-initiativeinteraction between the users and the system, as the replacement for the neuralrewriting method. Specifically, we design an algorithm to generate appropriatequestions related to the ambiguities in raw queries, and another algorithm toreformulate raw queries by parsing users' feedback and incorporating it intothe raw query. For the first ranking stage of our multi-stage pipelines, weadopt a sparse ranking function: BM25, and a dense retrieval method:TCT-ColBERT. For the second-ranking step, we adopt a pointwise reranker:MonoT5, and a pairwise reranker: DuoT5. Experiments on both TREC CAsT 2021 andTREC CAsT 2022 datasets show the effectiveness of our mixed-initiative-basedquery rewriting (or query reformulation) method on improving retrievalperformance compared with two popular reformulators: a neural reformulator:CANARD-T5 and a rule-based reformulator: historical query reformulator(HQE).

Mixed-initiative Query Rewriting in Conversational Passage Retrieval