SEINE: Segment-based Indexing For Neural Information Retrieval

Abstract

Many early neural Information Retrieval (NeurIR) methods are re-rankers that rely on a traditional first-stage retriever due to expensive query time computations. Recently, representation-based retrievers have gained much attention, which learns query representation and document representation separately, making it possible to pre-compute document representations offline and reduce the workload at query time. Both dense and sparse representation-based retrievers have been explored. However, these methods focus on finding the representation that best represents a text (aka metric learning) and the actual retrieval function that is responsible for similarity matching between query and document is kept at a minimum by using dot product. One drawback is that unlike traditional term-level inverted index, the index formed by these embeddings cannot be easily re-used by another retrieval method. Another drawback is that keeping the interaction at minimum hurts retrieval effectiveness. On the

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydong2023seine

Related papers

• Neural Models For Information Retrieval (2017)0.00
• Neural Information Retrieval: A Literature Review (2016)0.00
• Neural IR Meets Graph Embedding: A Ranking Model For Product Search (2019)11.85
• Incorporating Query Term Independence Assumption For Efficient Retrieval And Ranking Using Deep Neural Networks (2019)0.00
• A Deep Look Into Neural Ranking Models For Information Retrieval (2019)17.73
• Semi-parametric Retrieval Via Binary Bag-of-tokens Index (2024)0.00
• Beyond Precision: A Study On Recall Of Initial Retrieval With Neural Representations (2018)4.52
• Improving Neural Ranking Models With Traditional IR Methods (2023)0.00