{"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/effect-of-vision-and-language-extensions-on","title":"Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models","arxiv_id":"2104.08066","date":"2021-04-16","proceeding":"EMNLP 2021 11","authors":["Taichi Iki","Akiko Aizawa"],"abstract":"A method for creating a vision-and-language (V&L) model is to extend a language model through structural modifications and V&L pre-training. Such an extension aims to make a V&L model inherit the capability of natural language understanding (NLU) from the original language model. To see how well this is achieved, we propose to evaluate V&L models using an NLU benchmark (GLUE). We compare five V&L models, including single-stream and dual-stream models, trained with the same pre-training. Dual-stream models, with their higher modality independence achieved by approximately doubling the number of parameters, are expected to preserve the NLU capability better. Our main finding is that the dual-stream scores are not much different than the single-stream scores, contrary to expectation. Further analysis shows that pre-training causes the performance drop in NLU tasks with few exceptions. These results suggest that adopting a single-stream structure and devising the pre-training could be an effective method for improving the maintenance of language knowledge in V&L extensions.","url_abs":"https://arxiv.org/abs/2104.08066v2","url_pdf":"https://arxiv.org/pdf/2104.08066v2.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":"effect-of-vision-and-language-extensions-on","repo_url":"https://github.com/alab-nii/eval_vl_glue","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.08066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08066"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/alab-nii/eval_vl_glue","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"6d254a1b39c650ff","entry":"find_pruneable_heads_and_indices","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/modeling_utils.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6d254a1b39c650ff"}},{"code_sha256_prefix":"a4475703ff58ecf9","entry":"gelu_fast","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/activations.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/activations.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4475703ff58ecf9"}},{"code_sha256_prefix":"45bb87451230d5e8","entry":"gelu_new","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/activations.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/activations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"45bb87451230d5e8"}},{"code_sha256_prefix":"899d1e2736236351","entry":"is_remote_url","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/file_utils.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"899d1e2736236351"}},{"code_sha256_prefix":"f889d53c68539013","entry":"mish","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/activations.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/activations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f889d53c68539013"}},{"code_sha256_prefix":"56ffa4b32330ceab","entry":"torch_only_method","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/file_utils.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56ffa4b32330ceab"}},{"code_sha256_prefix":"598a2bf62b8c0a24","entry":"load_tsv","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/volta_image_feature.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/volta_image_feature.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"598a2bf62b8c0a24"}},{"code_sha256_prefix":"2cd9135e83a62a04","entry":"replace_return_docstrings","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/file_utils.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2cd9135e83a62a04"}},{"code_sha256_prefix":"9c750e2920328942","entry":"top_k_top_p_filtering","repo":"alab-nii/eval_vl_glue","repo_kind":"official","path":"eval_vl_glue/transformers_volta/generation_utils.py","file_url":"https://github.com/alab-nii/eval_vl_glue/blob/HEAD/eval_vl_glue/transformers_volta/generation_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9c750e2920328942"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}