Related papers: Scaling Multilingual Semantic Search in Uber Eats …
Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages. We consider multilingual entity linking, where a single model is trained to link references…
Large language models (LLMs) typically enhance their performance through either the retrieval of semantically similar information or the improvement of their reasoning capabilities. However, a significant challenge remains in effectively…
With the rapid advancement of multimodal information retrieval, increasingly complex retrieval tasks have emerged. Existing methods predominately rely on task-specific fine-tuning of vision-language models, often those trained with…
Experience management is an emerging business area where organizations focus on understanding the feedback of customers and employees in order to improve their end-to-end experiences. This results in a unique set of machine learning…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and RAG strategy. We introduce an iterative…
Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in the area of information retrieval and natural language…
This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality,…
Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…
Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning…
The rapid growth of e-commerce requires robust multimodal representations that capture diverse signals from user-generated listings. Existing vision-language models (VLMs) typically align titles with primary images, i.e., single-view, but…
In this paper, we present an architecture executing a complex machine learning model such as a neural network capturing semantic similarity between a query and a document; and deploy to a real-world production system serving 500M+users. We…
This paper studies the performances of BERT combined with tree structure in short sentence ranking task. In retrieval-based question answering system, we retrieve the most similar question of the query question by ranking all the questions…
Building real-world complex Named Entity Recognition (NER) systems is a challenging task. This is due to the complexity and ambiguity of named entities that appear in various contexts such as short input sentences, emerging entities, and…
We address the task of ranking objects (such as people, blogs, or verticals) that, unlike documents, do not have direct term-based representations. To be able to match them against keyword queries, evidence needs to be amassed from…
Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answering challenge…
Although Large Language Models (LLMs) demonstrate excellent capabilities and performance for general reasoning tasks within the general public domain, they may face challenges with culturally grounded knowledge within languages with limited…
Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on…
While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory has a number of benefits from accuracy improvements to data…
Recommendation systems are widely used in e-commerce websites and online platforms to address information overload. However, existing systems primarily rely on historical data and user feedback, making it difficult to capture user intent…