{"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/hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","arxiv_id":"1707.07847","date":"2017-07-25","proceeding":null,"authors":["Yi Tay","Luu Anh Tuan","Siu Cheung Hui"],"abstract":"The dominant neural architectures in question answer retrieval are based on\nrecurrent or convolutional encoders configured with complex word matching\nlayers. Given that recent architectural innovations are mostly new word\ninteraction layers or attention-based matching mechanisms, it seems to be a\nwell-established fact that these components are mandatory for good performance.\nUnfortunately, the memory and computation cost incurred by these complex\nmechanisms are undesirable for practical applications. As such, this paper\ntackles the question of whether it is possible to achieve competitive\nperformance with simple neural architectures. We propose a simple but novel\ndeep learning architecture for fast and efficient question-answer ranking and\nretrieval. More specifically, our proposed model, \\textsc{HyperQA}, is a\nparameter efficient neural network that outperforms other parameter intensive\nmodels such as Attentive Pooling BiLSTMs and Multi-Perspective CNNs on multiple\nQA benchmarks. The novelty behind \\textsc{HyperQA} is a pairwise ranking\nobjective that models the relationship between question and answer embeddings\nin Hyperbolic space instead of Euclidean space. This empowers our model with a\nself-organizing ability and enables automatic discovery of latent hierarchies\nwhile learning embeddings of questions and answers. Our model requires no\nfeature engineering, no similarity matrix matching, no complicated attention\nmechanisms nor over-parameterized layers and yet outperforms and remains\ncompetitive to many models that have these functionalities on multiple\nbenchmarks.","url_abs":"http://arxiv.org/abs/1707.07847v3","url_pdf":"http://arxiv.org/pdf/1707.07847v3.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":"hyperbolic-representation-learning-for-fast","repo_url":"https://github.com/vanzytay/WSDM2018_HyperQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"efficient-neural-network","task_name":"Efficient Neural Network"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-semevalcqa","task":"Question Answering","dataset":"SemEvalCQA","model":"HyperQA","rank_in_archive_order":1,"of":5,"metrics":{"MAP":"0.795","P@1":"0.809"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-trecqa","task":"Question Answering","dataset":"TrecQA","model":"HyperQA","rank_in_archive_order":10,"of":13,"metrics":{"MAP":"0.770","MRR":"0.825"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"HyperQA","rank_in_archive_order":10,"of":25,"metrics":{"MAP":"0.712","MRR":"0.727"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-yahoocqa","task":"Question Answering","dataset":"YahooCQA","model":"HyperQA","rank_in_archive_order":3,"of":7,"metrics":{"MRR":"0.801","P@1":"0.683"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-yahoocqa","task":"Question Answering","dataset":"YahooCQA","model":"LSTM","rank_in_archive_order":6,"of":7,"metrics":{"MRR":"0.669","P@1":"0.465"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-yahoocqa","task":"Question Answering","dataset":"YahooCQA","model":"CNN","rank_in_archive_order":7,"of":7,"metrics":{"MRR":"0.632","P@1":"0.413"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.07847","atlas_url":"https://app.syntology.ai/?focus=1707.07847","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":"1707.07847"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.07847\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.07847"},"call":"get_concepts_for_paper(arxiv_id=\"1707.07847\")"}],"by_repo":[{"repo":"vanzytay/WSDM2018_HyperQA","kind":"listed","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":"9cab41447db76333de5da7a0c9bc55b14192897b16a544b30691768bd90c5730","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}