{"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/e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","arxiv_id":"2105.03761","date":"2021-05-08","proceeding":"ICCV 2021 10","authors":["Maxime Kayser","Oana-Maria Camburu","Leonard Salewski","Cornelius Emde","Virginie Do","Zeynep Akata","Thomas Lukasiewicz"],"abstract":"Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, there is a lack of comparison between existing methods, which is due to a lack of re-usable evaluation frameworks and a scarcity of datasets. In this work, we introduce e-ViL and e-SNLI-VE. e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs (over 430k instances). We also propose a new model that combines UNITER, which learns joint embeddings of images and text, and GPT-2, a pre-trained language model that is well-suited for text generation. It surpasses the previous state of the art by a large margin across all datasets. Code and data are available here: https://github.com/maximek3/e-ViL.","url_abs":"https://arxiv.org/abs/2105.03761v2","url_pdf":"https://arxiv.org/pdf/2105.03761v2.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":"e-vil-a-dataset-and-benchmark-for-natural","repo_url":"https://github.com/maximek3/e-ViL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"e-vil-a-dataset-and-benchmark-for-natural","repo_url":"https://github.com/virginie-do/e-SNLI-VE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"uniter","method_name":"UNITER"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"e-snli-ve","name":"e-SNLI-VE","full_name":""},{"slug":"e-vil","name":"e-ViL","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.03761","atlas_url":"https://app.syntology.ai/?focus=2105.03761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03761"}},"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":"deterministic:regex_extraction","url":"https://github.com/maximek3/e-ViL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/virginie-do/e-SNLI-VE","reach":null}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":10,"ran":5,"repositories":1},"listed":{"samples":5,"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":15,"samples":[{"code_sha256_prefix":"c7ae06c1dd45a529","entry":"BahdanauAttention","repo":"virginie-do/e-SNLI-VE","repo_kind":"listed","path":"code/models.py","file_url":"https://github.com/virginie-do/e-SNLI-VE/blob/HEAD/code/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7ae06c1dd45a529"}},{"code_sha256_prefix":"0521d08772217a27","entry":"BertConfig","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0521d08772217a27"}},{"code_sha256_prefix":"8c436a09d6111527","entry":"BertIntermediate","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c436a09d6111527"}},{"code_sha256_prefix":"d54118b1b40771d8","entry":"UniterImageEmbeddings","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d54118b1b40771d8"}},{"code_sha256_prefix":"5599fa55122e553e","entry":"UniterTextEmbeddings","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5599fa55122e553e"}},{"code_sha256_prefix":"3c06d11eadebd504","entry":"gelu","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c06d11eadebd504"}},{"code_sha256_prefix":"b547373c1b308a7f","entry":"glove_embeddings_initializer","repo":"virginie-do/e-SNLI-VE","repo_kind":"listed","path":"code/models.py","file_url":"https://github.com/virginie-do/e-SNLI-VE/blob/HEAD/code/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b547373c1b308a7f"}},{"code_sha256_prefix":"28583b97c6efcaf1","entry":"BertEncoder","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28583b97c6efcaf1"}},{"code_sha256_prefix":"5646c8ef704d0a44","entry":"BertLayer","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5646c8ef704d0a44"}},{"code_sha256_prefix":"fe3c40780a0269fa","entry":"BertPreTrainedModel","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe3c40780a0269fa"}},{"code_sha256_prefix":"bd3741138096cd02","entry":"RNN_Decoder","repo":"virginie-do/e-SNLI-VE","repo_kind":"listed","path":"code/models.py","file_url":"https://github.com/virginie-do/e-SNLI-VE/blob/HEAD/code/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd3741138096cd02"}},{"code_sha256_prefix":"05f0de5ed2b23318","entry":"UniterModel","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"05f0de5ed2b23318"}},{"code_sha256_prefix":"939b0f97860f009d","entry":"eVSNLI_net","repo":"virginie-do/e-SNLI-VE","repo_kind":"listed","path":"code/models.py","file_url":"https://github.com/virginie-do/e-SNLI-VE/blob/HEAD/code/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"939b0f97860f009d"}},{"code_sha256_prefix":"53d4ca353f363a76","entry":"gated_tanh","repo":"virginie-do/e-SNLI-VE","repo_kind":"listed","path":"code/models.py","file_url":"https://github.com/virginie-do/e-SNLI-VE/blob/HEAD/code/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53d4ca353f363a76"}},{"code_sha256_prefix":"f4e7ffb01089db78","entry":"load_tf_weights_in_bert","repo":"maximek3/e-ViL","repo_kind":"official","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f4e7ffb01089db78"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}