Related papers: Pre-trained Embeddings for Entity Resolution: An E…

Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Due to the complex layouts of documents, it is challenging to extract information for documents. Most previous studies develop multimodal pre-trained models in a self-supervised way. In this paper, we focus on the embedding learning of word…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been…

With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even…

Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further…

Word embeddings and language models have transformed natural language processing (NLP) by facilitating the representation of linguistic elements in continuous vector spaces. This review visits foundational concepts such as the…

Entity resolution (ER) is a fundamental task in data integration that enables insights from heterogeneous data sources. The primary challenge of ER lies in classifying record pairs as matches or nonmatches, which in multi-source ER (MS-ER)…

Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most…

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Entity resolution (ER) aims at matching records that refer to the same real-world entity. Although widely studied for the last 50 years, ER still represents a challenging data management problem, and several recent works have started to…

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…

Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key pitfalls of evaluation of sentence embeddings, a currently…

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have…

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint training of mention…

Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying…