Related papers: Embedding-based search in JetBrains IDEs
Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to…
Deep learning has become the most popular direction in machine learning and artificial intelligence. However, the preparation of training data, as well as model training, are often time-consuming and become the bottleneck of the end-to-end…
Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic…
Many problems can be viewed as forms of geospatial search aided by aerial imagery, with examples ranging from detecting poaching activity to human trafficking. We model this class of problems in a visual active search (VAS) framework, which…
Since data is often stored in different sources, it needs to be integrated to gather a global view that is required in order to create value and derive knowledge from it. A critical step in data integration is schema matching which aims to…
Recognizing toponyms and resolving them to their real-world referents is required for providing advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the…
We provide a reproducible, end-to-end demonstration of vector search with OpenAI embeddings using Lucene on the popular MS MARCO passage ranking test collection. The main goal of our work is to challenge the prevailing narrative that a…
Code search engine is an essential tool in software development. Many code search methods have sprung up, focusing on the overall ranking performance of code search. In this paper, we study code search from another perspective by analyzing…
Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding…
The process of engineering and deploying applications in the edge/embedded space is massively complicated by the non-homogeneous nature of the software stack and the complexity of diagnostics & debugging. Often different languages and…
This paper reviews machine learning applications and approaches to detection, classification and control of intelligent materials and structures with embedded distributed computation elements. The purpose of this survey is to identify…
Identifying similar documents within extensive volumes of data poses a significant challenge. To tackle this issue, researchers have developed a variety of effective distributed computing techniques. With the advancement of computing power…
State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word…
Planning problems are among the most important and well-studied problems in artificial intelligence. They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those…
Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters while ignoring the…
Understanding the meaning of words is crucial for many tasks that involve human-machine interaction. This has been tackled by research in Word Sense Disambiguation (WSD) in the Natural Language Processing (NLP) field. Recently, WSD and many…
Searching for information about a specific person is an online activity frequently performed by many users. In most cases, users are aided by queries containing a name and sending back to the web search engines for finding their will.…
Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…
In this work, we developed, integrated, and tested a feature that automatically highlights potentially important frames in stack traces. The feature was implemented in the internal bug-processing tool at JetBrains that processes tens of…
Software visualization can be of great use for understanding and exploring a software system in an intuitive manner. Spatial representation of software is a promising approach of increasing interest. However, little is known about how…