{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/alleviating-exposure-bias-via-contrastive","title":"Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization","arxiv_id":"2108.11846","date":"2021-08-26","proceeding":null,"authors":["Shichao Sun","Wenjie Li"],"abstract":"Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, these models mostly suffer a discrepancy between training and inference, i.e., the exposure bias problem. During the training stage, with teacher forcing these models are optimized to maximize the likelihood of the gold summary given the gold summary tokens as input to the decoder, while at inference the given tokens are replaced by the generated tokens. Consequently, low-quality summaries are very likely to be generated. To remedy this problem, we propose to leverage contrastive learning to decrease the likelihood of these low-quality summaries, and meanwhile increase the likelihood of the gold summary. Since our solution expands the states that the model perceives during training, we expect that the exposure bias problem can be alleviated. We experimentally demonstrate that our method effectively improves the performance of the state-of-the-art model on different datasets.","url_abs":"https://arxiv.org/abs/2108.11846v1","url_pdf":"https://arxiv.org/pdf/2108.11846v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"alleviating-exposure-bias-via-contrastive","repo_url":"https://github.com/shichaosun/conabssum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.11846","atlas_url":"https://app.syntology.ai/?focus=2108.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11846"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shichaosun/conabssum","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a3826392847cbef3","entry":"count_trainable_parameters","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/callbacks.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/callbacks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3826392847cbef3"}},{"code_sha256_prefix":"295d9fdc5ce0b054","entry":"get_early_stopping_callback","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/callbacks.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/callbacks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"295d9fdc5ce0b054"}},{"code_sha256_prefix":"8609dcbe6167c497","entry":"add_newline_to_end_of_each_sentence","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/sentence_splitter.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/sentence_splitter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8609dcbe6167c497"}},{"code_sha256_prefix":"952f6fff9428619b","entry":"get_checkpoint_callback","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/callbacks.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/callbacks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"952f6fff9428619b"}},{"code_sha256_prefix":"e386d3a24af4d168","entry":"label_smoothed_nll_loss","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e386d3a24af4d168"}},{"code_sha256_prefix":"7c43af131a6f39a6","entry":"lmap","repo":"shichaosun/conabssum","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/shichaosun/conabssum/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c43af131a6f39a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}