Language models that utilize extensive self-supervised pre-training from
unlabeled text, have recently shown to significantly advance the
state-of-the-art performance in a variety of language understanding tasks.
However, it is yet unclear if and how these recent models can be harnessed for
conducting text-based recommendations. In this work, we introduce RecoBERT, a
BERT-based approach for learning catalog-specialized language models for
text-based item recommendations. We suggest novel training and inference
procedures for scoring similarities between pairs of items, that don't require
item similarity labels. Both the training and the inference techniques were
designed to utilize the unlabeled structure of textual catalogs, and minimize
the discrepancy between them. By incorporating four scores during inference,
RecoBERT can infer text-based item-to-item similarities more accurately than
other techniques. In addition, we introduce a new language understanding task
for wine recommendations using similarities based on professional wine reviews.
As an additional contribution, we publish annotated recommendations dataset
crafted by human wine experts. Finally, we evaluate RecoBERT and compare it to
various state-of-the-art NLP models on wine and fashion recommendations tasks.

本研究提出了 RecoBERT，一种基于 BERT 的方法，用于学习目录专用的语言模型以实现基于文本的商品推荐，并通过独创的训练和推理过程，在不需要商品相似性标签的情况下评分，以更准确地推断商品之间的文本相似性，并将其应用到葡萄酒和时尚商品推荐任务中。

RecoBERT：用于基于文本推荐的目录语言模型

RecoBERT: A Catalog Language Model for Text-Based Recommendations

Collaborative filtering (CF) aims to build a model from users' past behaviors
and/or similar decisions made by other users, and use the model to recommend
items for users. Despite of the success of previous collaborative filtering
approaches, they are all based on the assumption that there are sufficient
rating scores available for building high-quality recommendation models. In
real world applications, however, it is often difficult to collect sufficient
rating scores, especially when new items are introduced into the system, which
makes the recommendation task challenging. We find that there are often "short"
texts describing features of items, based on which we can approximate the
similarity of items and make recommendation together with rating scores. In
this paper we "borrow" the idea of vector representation of words to capture
the information of short texts and embed it into a matrix factorization
framework. We empirically show that our approach is effective by comparing it
with state-of-the-art approaches.

本文提出了一种基于文本向量表示的协作过滤算法，用于在获取商品评分困难的情况下进行推荐，并与现有的算法进行了对比验证其有效性。

基于分布式表示的混合推荐系统与短物品描述

Distributed-Representation Based Hybrid Recommender System with Short  Item Descriptions

We propose Meta-Prod2vec, a novel method to compute item similarities for
recommendation that leverages existing item metadata. Such scenarios are
frequently encountered in applications such as content recommendation, ad
targeting and web search. Our method leverages past user interactions with
items and their attributes to compute low-dimensional embeddings of items.
Specifically, the item metadata is in- jected into the model as side
information to regularize the item embeddings. We show that the new item
representa- tions lead to better performance on recommendation tasks on an open
music dataset.

Meta-Prod2vec 提出了一种新方法来计算物品之间的相似度，该方法利用现有的物品元数据，通过注入元数据以正则化物品嵌入来计算物品的低维嵌入，从而提高推荐任务的性能。