Language Models As Semantic Indexers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Bowen, Zeng, Hansi, Wang, Guoyin, Chen, Xiusi, Wei, Tianxin, Li, Ruirui, Wang, Zhengyang, Li, Zheng, Li, Yang, Lu, Hanqing, Wang, Suhang, Han, Jiawei, Tang, Xianfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913389074186240
author Jin, Bowen
Zeng, Hansi
Wang, Guoyin
Chen, Xiusi
Wei, Tianxin
Li, Ruirui
Wang, Zhengyang
Li, Zheng
Li, Yang
Lu, Hanqing
Wang, Suhang
Han, Jiawei
Tang, Xianfeng
author_facet Jin, Bowen
Zeng, Hansi
Wang, Guoyin
Chen, Xiusi
Wei, Tianxin
Li, Ruirui
Wang, Zhengyang
Li, Zheng
Li, Yang
Lu, Hanqing
Wang, Suhang
Han, Jiawei
Tang, Xianfeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07815
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Language Models As Semantic Indexers
Jin, Bowen
Zeng, Hansi
Wang, Guoyin
Chen, Xiusi
Wei, Tianxin
Li, Ruirui
Wang, Zhengyang
Li, Zheng
Li, Yang
Lu, Hanqing
Wang, Suhang
Han, Jiawei
Tang, Xianfeng
Information Retrieval
Computation and Language
Machine Learning
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.
title Language Models As Semantic Indexers
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/2310.07815