Decoding a Neural Retriever’s Latent Space for Query Suggestion

Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, Thomas Hofmann


Abstract
Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to a change in the latent space that ultimately determines the retrieval results. To shed light on this embedding space, we learn a “query decoder” that, given a latent representation of a neural search engine, generates the corresponding query. We show that it is possible to decode a meaningful query from its latent representation and, when moving in the right direction in latent space, to decode a query that retrieves the relevant paragraph. In particular, the query decoder can be useful to understand “what should have been asked” to retrieve a particular paragraph from the collection. We employ the query decoder to generate a large synthetic dataset of query reformulations for MSMarco, leading to improved retrieval performance. On this data, we train a pseudo-relevance feedback (PRF) T5 model for the application of query suggestion that outperforms both query reformulation and PRF information retrieval baselines.
Anthology ID:
2022.emnlp-main.601
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8786–8804
Language:
URL:
https://aclanthology.org/2022.emnlp-main.601
DOI:
10.18653/v1/2022.emnlp-main.601
Bibkey:
Cite (ACL):
Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, and Thomas Hofmann. 2022. Decoding a Neural Retriever’s Latent Space for Query Suggestion. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8786–8804, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Decoding a Neural Retriever’s Latent Space for Query Suggestion (Adolphs et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.601.pdf