{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/generating-informative-and-diverse","title":"Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization","arxiv_id":"1809.05972","date":"2018-09-16","proceeding":"NeurIPS 2018 12","authors":["Yizhe Zhang","Michel Galley","Jianfeng Gao","Zhe Gan","Xiujun Li","Chris Brockett","Bill Dolan"],"abstract":"Responses generated by neural conversational models tend to lack\ninformativeness and diversity. We present Adversarial Information Maximization\n(AIM), an adversarial learning strategy that addresses these two related but\ndistinct problems. To foster response diversity, we leverage adversarial\ntraining that allows distributional matching of synthetic and real responses.\nTo improve informativeness, our framework explicitly optimizes a variational\nlower bound on pairwise mutual information between query and response.\nEmpirical results from automatic and human evaluations demonstrate that our\nmethods significantly boost informativeness and diversity.","url_abs":"http://arxiv.org/abs/1809.05972v5","url_pdf":"http://arxiv.org/pdf/1809.05972v5.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":"generating-informative-and-diverse","repo_url":"https://github.com/GraphGrailAi/DialoGPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generating-informative-and-diverse","repo_url":"https://github.com/dreasysnail/converse_GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generating-informative-and-diverse","repo_url":"https://github.com/souvikdgp16/dialo_gpt_daily_dialog","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generating-informative-and-diverse","repo_url":"https://github.com/sseol11/DialoGPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"conversational-response-generation","task_name":"Conversational Response Generation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"informativeness","task_name":"Informativeness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.05972","atlas_url":"https://app.syntology.ai/?focus=1809.05972","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1809.05972"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.05972\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.05972"},"call":"get_concepts_for_paper(arxiv_id=\"1809.05972\")"}],"by_repo":[{"repo":"GraphGrailAi/DialoGPT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.00536"],"harvested_for_calls":[{"arxiv_id":"1911.00536","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.00536"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.00536\")"}]},{"repo":"dreasysnail/converse_GAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"souvikdgp16/dialo_gpt_daily_dialog","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sseol11/DialoGPT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.00536"],"harvested_for_calls":[{"arxiv_id":"1911.00536","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.00536"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.00536\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"68fb353f86b0a87bb67304161a7f3f334128fa77367663bffb01fe59e7be9403","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}