Related papers: Semi-Structured Query Grounding for Document-Orien…

As immersive technologies evolve, immersive computational notebooks offer new opportunities for interacting with code, data, and outputs. However, scaling these environments remains a challenge, particularly when analysts manually arrange…

Due to the usefulness in data enrichment for data analysis tasks, joinable table discovery has become an important operation in data lake management. Existing approaches target equi-joins, the most common way of combining tables for…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

A Natural Language Interface (NLI) facilitates users to pose queries to retrieve information from a database without using any artificial language such as the Structured Query Language (SQL). Several applications in various domains…

Large-scale visual search engines are expected to solve a dual problem at once: (i) locate every image that truly contains the object described by a sentence and (ii) identify the object's bounding box or exact pixels within each hit.…

This paper has proposed a Graph - semantic based conceptual model for semi-structured database system, called GOOSSDM, to conceptualize the different facets of such system in object oriented paradigm. The model defines a set of graph based…

Despite the great success of word embedding, sentence embedding remains a not-well-solved problem. In this paper, we present a supervised learning framework to exploit sentence embedding for the medical question answering task. The learning…

Embedding models trained separately on similar data often produce representations that encode stable information but are not directly interchangeable. This lack of interoperability raises challenges in several practical applications, such…

We present an empirical study of embedding-based retrieval under realistic conversational settings, where queries are short, dialogue-like, and weakly specified, and retrieval corpora contain structured conversational artifacts. Focusing on…

There are significant benefits to serve deep learning models from relational databases. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system…

Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…

We present a reality check on large language models and inspect the promise of retrieval augmented language models in comparison. Such language models are semi-parametric, where models integrate model parameters and knowledge from external…

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

Objective: Applying large language models (LLMs) to the clinical domain is challenging due to the context-heavy nature of processing medical records. Retrieval-augmented generation (RAG) offers a solution by facilitating reasoning over…

Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this work, we argue that these embeddings, while effective, are…

We describe a novel architecture for semantic image retrieval---in particular, retrieval of instances of visual situations. Visual situations are concepts such as "a boxing match," "walking the dog," "a crowd waiting for a bus," or "a game…

We propose an end-to-end approach for phrase grounding in images. Unlike prior methods that typically attempt to ground each phrase independently by building an image-text embedding, our architecture formulates grounding of multiple phrases…

In the era of dense retrieval, document indexing and retrieval is largely based on encoding models that transform text documents into embeddings. The efficiency of retrieval is directly proportional to the number of documents and the size…

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax…

Distributed algorithms for solving coupled semidefinite programs (SDPs) commonly require many iterations to converge. They also put high computational demand on the computational agents. In this paper we show that in case the coupled…