Related papers: Features and Aggregators for Web-scale Entity Sear…
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…
Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based…
Efficiently ranking relevant items from large candidate pools is a cornerstone of modern information retrieval systems -- such as web search, recommendation, and retrieval-augmented generation. Listwise rerankers, which improve relevance by…
Many datasets exhibit a well-defined structure that can be exploited to design faster search tools, but it is not always clear when such acceleration is possible. Here, we introduce a framework for similarity search based on characterizing…
Traditional named entity recognition models use gazetteers (lists of entities) as features to improve performance. Although modern neural network models do not require such hand-crafted features for strong performance, recent work has…
With an ever growing number of extractive summarization techniques being proposed, there is less clarity then ever about how good each system is compared to the rest. Several studies highlight the variance in performance of these systems…
Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously…
Dictionary-based entity extraction involves finding mentions of dictionary entities in text. Text mentions are often noisy, containing spurious or missing words. Efficient algorithms for detecting approximate entity mentions follow one of…
End-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task…
Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive results for single-document summarization, yet their outputs are often…
Joint extraction of entities and relations aims to detect entity pairs along with their relations using a single model. Prior work typically solves this task in the extract-then-classify or unified labeling manner. However, these methods…
Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of…
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by…
Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries.…
Entity linking is a prominent thread of research focused on structured data creation by linking spans of text to an ontology or knowledge source. We revisit the use of structured prediction for entity linking which classifies each…
Entity Alignment (EA) aims to match equivalent entities in different Knowledge Graphs (KGs), which is essential for knowledge fusion and integration. Recently, embedding-based EA has attracted significant attention and many approaches have…
Text analytics has become an important part of business intelligence as enterprises increasingly seek to extract insights for decision making from text data sets. Processing large text data sets can be computationally expensive, however,…
With the development of Semantic Web, entity summarization has become an emerging task to generate concrete summaries for real world entities. To solve this problem, we propose an approach named MPSUM that extends a probabilistic topic…
A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture…
Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph. Traditional methods use a two-step process with separate models for entity recognition and disambiguation, which can be…