Papers › Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

13 Jun 2019ACL 2019 7arXiv:1906.05807archive 2025-07-28

Minjoon Seo, Jinhyuk Lee, Tom Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi

Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query. In this paper, we introduce the query-agnostic indexable representation of document phrases that can drastically speed up open-domain QA and also allows us to reach long-tail targets. In particular, our dense-sparse phrase encoding effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents. Leveraging optimization strategies, our model can be trained in a single 4-GPU server and serve entire Wikipedia (up to 60 billion phrases) under 2TB with CPUs only. Our experiments on SQuAD-Open show that our model is more accurate than DrQA (Chen et al., 2017) with 6000x reduced computational cost, which translates into at least 58x faster end-to-end inference benchmark on CPUs.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 16 ran (13 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

uwnlp/denspi officialmentioned on GitHubpytorchApache-2.0Syntology: 19 samples, 16 ran (3 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
8ran
3unverified

Licence: 4 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from uwnlp/denspi. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

uwnlp/denspi official repository 19 samples, 16 ran (3 instrument-failed) · 3 unverified
adjust open/mips.py ran Apache-2.0 (permissive) · 805c7cf81b34cfb8 · report fixture: signature each:dict/0/? · returned dict · level recorded 2026-09-25
convert_to_unicode in 40 papers tokenization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 1923fc05163d207d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
encode_phrase phrase.py ran Apache-2.0 (permissive) · b29057ff0bdfab27 · report fixture: signature layer:Tensor/3/float, phrase_size:int/0/int, span_kq_size:int/0/int, get_first_only:bool/0/bool · returned tuple · level recorded 2026-09-25
exact_match_score in 82 papers evaluate-v1.1.py ran · violated contract fingerprinted Apache-2.0 (permissive) · f6c275d6a18330a9 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-22
f1_score in 121 papers evaluate-v1.1.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2112c433b9c6d343 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-22
filter_metadata post.py ran Apache-2.0 (permissive) · 2ce75402d89eabd7 · report fixture: signature metadata:dict/0/?, threshold:float/0/float · returned dict · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
bert.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 40e9fee2e0b7e278 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_logits in 19 papers phrase.py ran Apache-2.0 (permissive) · c3c09581ddf6a885 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, metric:str/0/str · returned Tensor · level recorded 2026-09-25
int8_to_float open/mips.py ran Apache-2.0 (permissive) · 892f4e6b7e006e15 · report fixture: signature num:ndarray/1/int, offset:float/0/float, factor:float/0/float · returned ndarray · level recorded 2026-09-25
load_backward run_piqa.py ran Apache-2.0 (permissive) · cba1d07a90a46468 · report fixture: signature state:dict/0/? · returned OrderedDict · level recorded 2026-09-25
load_vocab in 107 papers tokenization.py ran Apache-2.0 (permissive) · c8956ce86812a6c2 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-25
normalize_answer in 304 papers evaluate-v1.1.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c6a80c065d2e4851 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
overlap in 7 papers open/mips.py ran Apache-2.0 (permissive) · df3944b07a180cef · report fixture: signature t1:Tensor/1/float, t2:Tensor/1/float, a1:int/0/int, a2:int/0/int, b1:int/0/int, b2:int/0/int · returned bool · level recorded 2026-09-25
printable_text in 36 papers tokenization.py ran · our draft was wrong Apache-2.0 (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
warmup_constant in 30 papers optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · e7d542062316094a · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22
warmup_linear in 45 papers optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c58d57224530d17e · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22
compress_metadata post.py unverified Apache-2.0 (permissive) · 13b8c556b20f1352 · report
get_sparse_logits phrase.py unverified Apache-2.0 (permissive) · ad8fbb8cb7f3dc0a · report
warmup_cosine in 30 papers optimization.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 35f7cddf90dd05d4 · report

Tasks

Open-Domain Question AnsweringQuestion Answering

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections