Представления предложений
Related Papers
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features
AbstractThe recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of …...
Unsupervised Domain Clusters in Pretrained Language Models
AbstractThe notion of “in-domain data” in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality. In …...
Toward Unifying Text Segmentation and Long Document Summarization
AbstractText segmentation is important for signaling a document’s structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find …...
SentBench: Comprehensive Evaluation of Self-Supervised Sentence Representation with Benchmark Construction
Abstract“Self-supervised learning has been widely used to learn effective sentence representations. Previ-ous evaluation of sentence representations mainly focuses on the limited combination of tasks andparadigms while failing to evaluate their …...