{"url":"/method/smith","slug":"smith","name":"SMITH","full_name":"Siamese Multi-depth Transformer-based Hierarchical Encoder","full_name_withheld":false,"description_markdown":"**SMITH**, or **Siamese Multi-depth Transformer-based Hierarchical Encoder**, is a [Transformer](https://paperswithcode.com/methods/category/transformers)-based model for document representation learning and matching. It contains several design choices to adapt [self-attention models](https://paperswithcode.com/methods/category/attention-modules) 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](https://paperswithcode.com/method/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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","paper":"/paper/beyond-512-tokens-siamese-multi-depth","first_author":"Liu Yang","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/beyond-512-tokens-siamese-multi-depth"},"source":{"url":"https://arxiv.org/abs/2004.12297v2","title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Autoencoding Transformers","url":"/methods/category/autoencoding-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/beyond-512-tokens-siamese-multi-depth","title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","date":"2020-04-26","arxiv_id":"2004.12297","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/clustering","name":"Clustering","papers":1},{"task":"/task/form","name":"Form","papers":1},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/news-recommendation","name":"News Recommendation","papers":1},{"task":"/task/2048","name":"Playing the Game of 2048","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/text-matching","name":"Text Matching","papers":1}],"tasks_shown":13,"n_tasks":13,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/smith"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}