pith. sign in

arxiv: 2104.07186 · v1 · pith:JWW2ARCJnew · submitted 2021-04-15 · 💻 cs.IR · cs.CL

COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List

classification 💻 cs.IR cs.CL
keywords exactmatchcoilcontextualizedlexicalinvertedretrievalarchitecture
0
0 comments X
read the original abstract

Classical information retrieval systems such as BM25 rely on exact lexical match and carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft semantic matching all query document terms, but they lose the computation efficiency of exact match systems. This paper presents COIL, a contextualized exact match retrieval architecture that brings semantic lexical matching. COIL scoring is based on overlapping query document tokens' contextualized representations. The new architecture stores contextualized token representations in inverted lists, bringing together the efficiency of exact match and the representation power of deep language models. Our experimental results show COIL outperforms classical lexical retrievers and state-of-the-art deep LM retrievers with similar or smaller latency.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

    cs.DS 2026-06 unverdicted novelty 8.0

    Proves that for bounded n, there exist MV embeddings with m vectors each whose Chamfer matrix requires single-vector dimension D = (ε² m)^Ω(1/ε) to approximate within ε, separating MV from SV expressiveness.

  2. Unified and Efficient Approach for Multi-Vector Similarity Search

    cs.DB 2026-04 unverdicted novelty 7.0

    MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.

  3. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

    cs.CL 2024-02 unverdicted novelty 7.0

    M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual,...

  4. Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps

    cs.IR 2026-04 conditional novelty 6.0

    Transferring modern encoders to normalized (lowercased) vocabularies via geometric embedding initialization and activation calibration closes the performance gap in learned sparse retrieval, achieving 52.4 nDCG on BEIR.

  5. Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead

    cs.IR 2026-04 accept novelty 6.0

    Empirical comparison across 14 retrievers on the BRIGHT benchmark shows reasoning-specialized models can match strong accuracy with competitive speed while many large LLM bi-encoders add latency for small gains and co...

  6. The Role of Vocabularies in Learning Sparse Representations for Ranking

    cs.IR 2025-09 unverdicted novelty 5.0

    Larger 100K vocabularies in SPLADE models, especially those initialized with ESPLADE pretraining, improve retrieval effectiveness after pruning compared to 32K baselines while keeping similar efficiency.

  7. RAGe: A Retrieval-Augmented Generation Evaluation Framework

    cs.IR 2026-05 unverdicted novelty 3.0

    RAGe is a modular evaluation framework that correlates retrieval and generation quality with hardware constraints to recommend optimal RAG components for specific datasets.