Language Models As Semantic Indexers
- URL: http://arxiv.org/abs/2310.07815v3
- Date: Wed, 12 Jun 2024 20:36:22 GMT
- Title: Language Models As Semantic Indexers
- Authors: Bowen Jin, Hansi Zeng, Guoyin Wang, Xiusi Chen, Tianxin Wei, Ruirui Li, Zhengyang Wang, Zheng Li, Yang Li, Hanqing Lu, Suhang Wang, Jiawei Han, Xianfeng Tang,
- Abstract summary: We introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model.
We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval.
- Score: 78.83425357657026
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic indexing. It is non-trivial to design a method that can learn the document's semantic representations and its hierarchical structure simultaneously, given that semantic IDs are discrete and sequentially structured, and the semantic supervision is deficient. In this paper, we introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We tackle the challenge of sequential discrete ID by introducing a semantic indexer capable of generating neural sequential discrete representations with progressive training and contrastive learning. In response to the semantic supervision deficiency, we propose to train the model with a self-supervised document reconstruction objective. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval on five datasets from various domains. Code is available at https://github.com/PeterGriffinJin/LMIndexer.
Related papers
- Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
We introduce a framework called GRaded Generative Retrieval (GR$2$)
GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training.
Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
arXiv Detail & Related papers (2024-09-27T02:55:53Z) - STORE: Streamlining Semantic Tokenization and Generative Recommendation with A Single LLM [59.08493154172207]
We propose a unified framework to streamline the semantic tokenization and generative recommendation process.
We formulate semantic tokenization as a text-to-token task and generative recommendation as a token-to-token task, supplemented by a token-to-text reconstruction task and a text-to-token auxiliary task.
All these tasks are framed in a generative manner and trained using a single large language model (LLM) backbone.
arXiv Detail & Related papers (2024-09-11T13:49:48Z) - Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval [108.9772640854136]
Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query.
Recent studies have highlighted the potential of a strong generative retrieval model, trained with carefully crafted pre-training tasks, to enhance downstream retrieval tasks via fine-tuning.
We introduce BootRet, a bootstrapped pre-training method for generative retrieval that dynamically adjusts document identifiers during pre-training to accommodate the continuing of the corpus.
arXiv Detail & Related papers (2024-07-16T08:42:36Z) - CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks [20.390672895839757]
Retrieval-augmented generation (RAG) has emerged as a popular solution to enhance factual accuracy.
Traditional retrieval modules often rely on large document index and disconnect with generative tasks.
We propose textbfCorpusLM, a unified language model that integrates generative retrieval, closed-book generation, and RAG.
arXiv Detail & Related papers (2024-02-02T06:44:22Z) - Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos [63.94040814459116]
Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence.
We propose a novel semantic-aware masked slot attention on top of the fused semantic features and correspondence maps.
We adopt semantic- and instance-level temporal consistency as self-supervision to encourage temporally coherent object-centric representations.
arXiv Detail & Related papers (2023-08-19T09:12:13Z) - Multiview Identifiers Enhanced Generative Retrieval [78.38443356800848]
generative retrieval generates identifier strings of passages as the retrieval target.
We propose a new type of identifier, synthetic identifiers, that are generated based on the content of a passage.
Our proposed approach performs the best in generative retrieval, demonstrating its effectiveness and robustness.
arXiv Detail & Related papers (2023-05-26T06:50:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.