paper-with-me

홈 › Papers

Coherence-Based Distributed Document Representation Learning for Scientific Documents

2022-01-08 · Shicheng Tan, Shu Zhao, Yanping Zhang

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take into account the coherence of the document as a whole, e.g., a relation between the paper title and abstract, headline and description, or adjacent bodies in the document. The coherence shows whether a document is meaningful, both logically and syntactically, especially in scientific documents (papers or patents, etc.). In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document. First, we divide the document into two parts (e.g., title and abstract, etc) which construct a coupled text pair. Then, we adopt negative sampling to construct uncoupled text pairs whose two parts are from different documents. Finally, we train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents. We perform experiments on three datasets for one information retrieval task and two recommendation tasks. The experimental results verify the effectiveness of the proposed CTPE model.

📄 PDF Abstract BibTeX arXiv:2201.02846

Code (1)

aitsc/text-representation 공식 구현 pytorch

Tasks

Information RetrievalRepresentation LearningRetrieval

Similar Papers 제목 키워드 기반

Document-as-Image Representations Fall Short for Scientific Retrieval

2026-04-20 · Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh, Bhuwan Dhingra arxiv

Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source. Meanwhile, existing benchmarks for scientific document retriev…

Neural Embedding Allocation: Distributed Representations of Topic Models

2019-09-10 · Kamrun Naher Keya, Yannis Papanikolaou, James R. Foulds

Word embedding models such as the skip-gram learn vector representations of words' semantic relationships, and document embedding models learn similar representations for documents. On the other hand, topic models provid…

Document EmbeddingTopic Models

MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents

2023-05-07 · Anastasia Razdaibiedina, Alexander Brechalov

Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn…

ArticlesRecommendation SystemsRepresentation LearningRetrieval+1

Evaluating topic coherence measures

2014-03-25 · Frank Rosner, Alexander Hinneburg, Michael Röder, Martin Nettling 외

Topic models extract representative word sets - called topics - from word counts in documents without requiring any semantic annotations. Topics are not guaranteed to be well interpretable, therefore, coherence measures …

PhilosophyTopic Models

Explaining Relationships Between Scientific Documents

2020-02-02 · ACL 2021 5 · Kelvin Luu, Xinyi Wu, Rik Koncel-Kedziorski, Kyle Lo 외

We address the task of explaining relationships between two scientific documents using natural language text. This task requires modeling the complex content of long technical documents, deducing a relationship between t…

Language ModelingLanguage ModellingLarge Language ModelText Generation