{"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/perspective-taking-and-pragmatics-for","title":"Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes","arxiv_id":"2109.08828","date":"2021-09-18","proceeding":"EMNLP 2021 11","authors":["Hyunwoo Kim","Byeongchang Kim","Gunhee Kim"],"abstract":"Empathy is a complex cognitive ability based on the reasoning of others' affective states. In order to better understand others and express stronger empathy in dialogues, we argue that two issues must be tackled at the same time: (i) identifying which word is the cause for the other's emotion from his or her utterance and (ii) reflecting those specific words in the response generation. However, previous approaches for recognizing emotion cause words in text require sub-utterance level annotations, which can be demanding. Taking inspiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level label. Also, we introduce a novel method based on pragmatics to make dialogue models focus on targeted words in the input during generation. Our method is applicable to any dialogue models with no additional training on the fly. We show our approach improves multiple best-performing dialogue agents on generating more focused empathetic responses in terms of both automatic and human evaluation.","url_abs":"https://arxiv.org/abs/2109.08828v2","url_pdf":"https://arxiv.org/pdf/2109.08828v2.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":"perspective-taking-and-pragmatics-for","repo_url":"https://github.com/skywalker023/focused-empathy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"empathetic-response-generation","task_name":"Empathetic Response Generation"},{"task_slug":"recognizing-emotion-cause-in-conversations","task_name":"Recognizing Emotion Cause in Conversations"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[{"method_slug":"gee","method_name":"GEE"}],"datasets_introduced":[{"slug":"emocause","name":"EmoCause","full_name":""}],"methods_introduced":[{"slug":"gee","name":"GEE","full_name":"Generative Emotion Estimator"}],"results":[{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"Human","rank_in_archive_order":1,"of":6,"metrics":{"Top-1 Recall":"41.3","Top-3 Recall":"81.1","Top-5 Recall":"95.0"},"uses_additional_data":false},{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"GEE","rank_in_archive_order":2,"of":6,"metrics":{"Top-1 Recall":"17.3","Top-3 Recall":"48.1","Top-5 Recall":"68.4"},"uses_additional_data":false},{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"BERT-Attention","rank_in_archive_order":3,"of":6,"metrics":{"Top-1 Recall":"13.8","Top-3 Recall":"40.6","Top-5 Recall":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"EmpDG","rank_in_archive_order":4,"of":6,"metrics":{"Top-1 Recall":"13.4","Top-3 Recall":"36.2","Top-5 Recall":"49.3"},"uses_additional_data":false},{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"RAKE","rank_in_archive_order":5,"of":6,"metrics":{"Top-1 Recall":"12.7","Top-3 Recall":"35.8","Top-5 Recall":"55.0"},"uses_additional_data":false},{"leaderboard":"/sota/recognizing-emotion-cause-in-conversations-on-1","task":"Recognizing Emotion Cause in Conversations","dataset":"EmoCause","model":"Random","rank_in_archive_order":6,"of":6,"metrics":{"Top-1 Recall":"10.7","Top-3 Recall":"30.6","Top-5 Recall":"48.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.08828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08828"}},"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/skywalker023/focused-empathy","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"060527bb34794b59","entry":"mish","repo":"skywalker023/focused-empathy","repo_kind":"official","path":"from_epitome/modeling_bert.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"060527bb34794b59"}},{"code_sha256_prefix":"49656b24dd2f6b62","entry":"calc_banned_bad_words_ids","repo":"skywalker023/focused-empathy","repo_kind":"official","path":"from_epitome/modeling_utils.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_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":"49656b24dd2f6b62"}},{"code_sha256_prefix":"f1cff4633a737beb","entry":"calc_banned_ngram_tokens","repo":"skywalker023/focused-empathy","repo_kind":"official","path":"from_epitome/modeling_utils.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_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":"f1cff4633a737beb"}},{"code_sha256_prefix":"0766f48ad6e01b56","entry":"load_tf_weights_in_bert","repo":"skywalker023/focused-empathy","repo_kind":"official","path":"from_epitome/modeling_bert.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_bert.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":"0766f48ad6e01b56"}},{"code_sha256_prefix":"8e873fc150477bd1","entry":"top_k_top_p_filtering","repo":"skywalker023/focused-empathy","repo_kind":"official","path":"from_epitome/modeling_utils.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_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":"8e873fc150477bd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}