Decoding a Neural Retriever's Latent Space for Query Suggestion
This work addresses the lack of interpretability in neural retrieval systems for search applications, though it is incremental as it builds on existing methods for query reformulation.
The paper tackled the problem of interpretability in neural retrieval models by developing a query decoder that generates queries from latent representations, enabling the creation of a synthetic dataset for MSMarco that improved retrieval performance, with the trained T5 model outperforming baselines in query suggestion.
Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice.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.