Methods › Natural Language Processing › Autoencoding Transformers › SMITH

Siamese Multi-depth Transformer-based Hierarchical Encoder

SMITH

1 paper tagged archive 2025-07-28

Introduced by Liu Yang et al. in Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SMITH, or Siamese Multi-depth Transformer-based Hierarchical Encoder, is a Transformer-based model for document representation learning and matching. It contains several design choices to adapt self-attention models for long text inputs. For the model pre-training, a masked sentence block language modeling task is used in addition to the original masked word language model task used in BERT, to capture sentence block relations within a document. Given a sequence of sentence block representation, the document level Transformers learn the contextual representation for each sentence block and the final document representation.

PaperSource

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Clustering1
Form1
Information Retrieval1
Language Modeling1
Language Modelling1
Natural Language Understanding1
News Recommendation1
Playing the Game of 20481
Question Answering1
Representation Learning1
Retrieval1
Sentence1
Text Matching1

Usage over time archive 2025-07-28

Papers per year tagged with SMITH: 2020 to 2020, peak 1 1 0 2020: 1 paper 2020
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Autoencoding TransformersTransformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections