{"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/towards-a-better-metric-for-evaluating","title":"Towards a Better Metric for Evaluating Question Generation Systems","arxiv_id":"1808.10192","date":"2018-08-30","proceeding":"EMNLP 2018 10","authors":["Preksha Nema","Mitesh M. Khapra"],"abstract":"There has always been criticism for using $n$-gram based similarity metrics,\nsuch as BLEU, NIST, etc, for evaluating the performance of NLG systems.\nHowever, these metrics continue to remain popular and are recently being used\nfor evaluating the performance of systems which automatically generate\nquestions from documents, knowledge graphs, images, etc. Given the rising\ninterest in such automatic question generation (AQG) systems, it is important\nto objectively examine whether these metrics are suitable for this task. In\nparticular, it is important to verify whether such metrics used for evaluating\nAQG systems focus on answerability of the generated question by preferring\nquestions which contain all relevant information such as question type\n(Wh-types), entities, relations, etc. In this work, we show that current\nautomatic evaluation metrics based on $n$-gram similarity do not always\ncorrelate well with human judgments about answerability of a question. To\nalleviate this problem and as a first step towards better evaluation metrics\nfor AQG, we introduce a scoring function to capture answerability and show that\nwhen this scoring function is integrated with existing metrics, they correlate\nsignificantly better with human judgments. The scripts and data developed as a\npart of this work are made publicly available at\nhttps://github.com/PrekshaNema25/Answerability-Metric","url_abs":"http://arxiv.org/abs/1808.10192v2","url_pdf":"http://arxiv.org/pdf/1808.10192v2.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":"towards-a-better-metric-for-evaluating","repo_url":"https://github.com/PrekshaNema25/Answerability-Metric","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10192"}},"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/PrekshaNema25/Answerability-Metric","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"bf8671cc374f7bce","entry":"NER_line","repo":"PrekshaNema25/Answerability-Metric","repo_kind":"official","path":"answerability_score.py","file_url":"https://github.com/PrekshaNema25/Answerability-Metric/blob/HEAD/answerability_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf8671cc374f7bce"}},{"code_sha256_prefix":"b1000ed9cb48b3b1","entry":"get_stopwords","repo":"PrekshaNema25/Answerability-Metric","repo_kind":"official","path":"answerability_score.py","file_url":"https://github.com/PrekshaNema25/Answerability-Metric/blob/HEAD/answerability_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1000ed9cb48b3b1"}},{"code_sha256_prefix":"1480e98be7b4f7bd","entry":"remove_stopwords_and_NER_line","repo":"PrekshaNema25/Answerability-Metric","repo_kind":"official","path":"answerability_score.py","file_url":"https://github.com/PrekshaNema25/Answerability-Metric/blob/HEAD/answerability_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1480e98be7b4f7bd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}