相关论文: CEQE: Contextualized Embeddings for Query Expansio…

We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines,…

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that leverage these…

Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context. This is intuitively useful for generalization, especially in Named-Entity Recognition where it is crucial to…

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophisticated techniques. In the last few years, in particular,…

State-of-the-art extractive question-answering models achieve superhuman performances on the SQuAD benchmark. Yet, they are unreasonably heavy and need expensive GPU computing to answer questions in a reasonable time. Thus, they cannot be…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats…

Transformer-based Large Language Models (LLMs) are pioneering advances in many natural language processing tasks, however, their exceptional capabilities are restricted within the preset context window of Transformer. Position Embedding…

Lexicon-based retrieval has gained siginificant popularity in text retrieval due to its efficient and robust performance. To further enhance performance of lexicon-based retrieval, researchers have been diligently incorporating…

Query expansion (QE) is a well-known technique used to enhance the effectiveness of information retrieval. QE reformulates the initial query by adding similar terms that help in retrieving more relevant results. Several approaches have been…

Nowadays, search engine users commonly rely on query suggestions to improve their initial inputs. Current systems are very good at recommending lexical adaptations or spelling corrections to users' queries. However, they often struggle to…

Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.…

Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…

Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents…

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…

We present a method to represent input texts by contextualizing them jointly with dynamically retrieved textual encyclopedic background knowledge from multiple documents. We apply our method to reading comprehension tasks by encoding…

Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT?…

Lexical semantics is concerned with both the multiple senses a word can adopt in different contexts, and the semantic relations that exist between meanings of different words. To investigate them, Contextualized Language Models are a…

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains…