{"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/challenging-neural-dialogue-models-with","title":"Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena","arxiv_id":"1709.07840","date":"2017-09-22","proceeding":null,"authors":["Igor Shalyminov","Arash Eshghi","Oliver Lemon"],"abstract":"Natural, spontaneous dialogue proceeds incrementally on a word-by-word basis;\nand it contains many sorts of disfluency such as mid-utterance/sentence\nhesitations, interruptions, and self-corrections. But training data for machine\nlearning approaches to dialogue processing is often either cleaned-up or wholly\nsynthetic in order to avoid such phenomena. The question then arises of how\nwell systems trained on such clean data generalise to real spontaneous\ndialogue, or indeed whether they are trainable at all on naturally occurring\ndialogue data. To answer this question, we created a new corpus called bAbI+ by\nsystematically adding natural spontaneous incremental dialogue phenomena such\nas restarts and self-corrections to the Facebook AI Research's bAbI dialogues\ndataset. We then explore the performance of a state-of-the-art retrieval model,\nMemN2N, on this more natural dataset. Results show that the semantic accuracy\nof the MemN2N model drops drastically; and that although it is in principle\nable to learn to process the constructions in bAbI+, it needs an impractical\namount of training data to do so. Finally, we go on to show that an\nincremental, semantic parser -- DyLan -- shows 100% semantic accuracy on both\nbAbI and bAbI+, highlighting the generalisation properties of linguistically\ninformed dialogue models.","url_abs":"http://arxiv.org/abs/1709.07840v1","url_pdf":"http://arxiv.org/pdf/1709.07840v1.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":"challenging-neural-dialogue-models-with","repo_url":"https://github.com/ishalyminov/babi_tools","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.07840","atlas_url":"https://app.syntology.ai/?focus=1709.07840","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":"1709.07840"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.07840\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.07840"},"call":"get_concepts_for_paper(arxiv_id=\"1709.07840\")"}],"by_repo":[{"repo":"ishalyminov/babi_tools","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"938550a8cf1efd674c2e80a10153a6d3bd751a7444ea22b0862ccd6963f77a7f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}