Related papers: Structure and Semantics Preserving Document Repres…
Applying machine learning algorithms to large-scale, text-based corpora (embeddings) presents a unique opportunity to investigate at scale how human semantic knowledge is organized and how people use it to judge fundamental relationships,…
In e-commerce search, relevance between query and documents is an essential requirement for satisfying user experience. Different from traditional e-commerce platforms that offer products, users search on life service platforms such as…
Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to…
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…
Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces…
Deep learning currently dominates the benchmarks for various NLP tasks and, at the basis of such systems, words are frequently represented as embeddings --vectors in a low dimensional space-- learned from large text corpora and various…
Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity…
The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike previous approaches that rely on either the structures or…
Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…
Scholarly documents have a great degree of variation, both in terms of content (semantics) and structure (pragmatics). Prior work in scholarly document understanding emphasizes semantics through document summarization and corpus topic…
In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural…
Deep learning is currently the subject of intensive study. However, fundamental concepts such as representations are not formally defined -- researchers "know them when they see them" -- and there is no common language for describing and…
A topic model is often formulated as a generative model that explains how each word of a document is generated given a set of topics and document-specific topic proportions. It is focused on capturing the word co-occurrences in a document…
Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among…
Page-level analysis of documents has been a topic of interest in digitization efforts, and multimodal approaches have been applied to both classification and page stream segmentation. In this work, we focus on capturing finer semantic…
Topic relevance between query and document is a very important part of social search, which can evaluate the degree of matching between document and user's requirement. In most social search scenarios such as Dianping, modeling search…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured…
Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook…
Representation learning is the first step in automating tasks such as research paper recommendation, classification, and retrieval. Due to the accelerating rate of research publication, together with the recognised benefits of…