Papers › Revealing the Importance of Semantic Retrieval for Machine Reading at Scale
Revealing the Importance of Semantic Retrieval for Machine Reading at Scale
Yixin Nie, Songhe Wang, Mohit Bansal
Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural combination of information retrieval (IR) and machine comprehension (MC). Advancements in representation learning have led to separated progress in both IR and MC; however, very few studies have examined the relationship and combined design of retrieval and comprehension at different levels of granularity, for development of MRS systems. In this work, we give general guidelines on system design for MRS by proposing a simple yet effective pipeline system with special consideration on hierarchical semantic retrieval at both paragraph and sentence level, and their potential effects on the downstream task. The system is evaluated on both fact verification and open-domain multihop QA, achieving state-of-the-art results on the leaderboard test sets of both FEVER and HOTPOTQA. To further demonstrate the importance of semantic retrieval, we present ablation and analysis studies to quantify the contribution of neural retrieval modules at both paragraph-level and sentence-level, and illustrate that intermediate semantic retrieval modules are vital for not only effectively filtering upstream information and thus saving downstream computation, but also for shaping upstream data distribution and providing better data for downstream modeling. Code/data made publicly available at: https://github.com/easonnie/semanticRetrievalMRS
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):
get_harvested_code_for_paper(arxiv_id="1909.08041")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1909.08041", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1909.08041")
Code
Syntology 17 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 4 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 11 ran (10 with no instrument failure; 1 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.
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
17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
5e7db7ffb7a92c64 · report
fixture: signature instance:dict/0/?, max_evidence:int/0/int · returned tuple · level recorded 2026-09-22 2781a9591cbfdb33 · report
fixture: signature predictions:list/1/dict, actual:list/1/dict, max_evidence:int/0/int · returned tuple · level recorded 2026-09-22 bacc307a6797cb32 · report
fixture: signature predictions:list/1/dict, actual:list/1/dict, max_evidence:int/0/int · returned tuple · level recorded 2026-09-22 ba1043dff5ce07b8 · report
fixture: signature dict_db:dict/0/?, file:str/0/str, with_int_type:bool/0/bool, memory_efficient:bool/0/bool, value_type:str/0/str · returned dict · level recorded 2026-09-22 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 src/bert_model_variances/bert_maxout_clf.py ran · our draft was wrong fingerprinted MIT (permissive) ·
0f786c407fb1ee4c · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded 292d77ea319f82b8 · report
fixture: signature dl:int/0/int, avdl:int/0/int · returned float · level recorded 2026-09-25 d8f74d3b75b19f79 · report
fixture: signature gram:list/1/str, mode:str/0/str · returned bool · level recorded 2026-09-24 019955faa9c53626 · report
fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24 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 src/bert_model_variances/bert_maxout_clf.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only ·
40e9fee2e0b7e278 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 7ba88a577b6a2d52 · report
fixture: signature terms:list/1/str, poss:list/1/str, n:int/0/int, included_tags:list/1/str, as_strings:bool/0/bool · returned list · level recorded 2026-09-24 6d9943f9b30c55eb · report
fixture: signature item:dict/0/? · returned list · level recorded 2026-09-24 1df66838eb1b9b17 · report
fixture: signature texts:list/1/str, charoffsets:list/1/list · returned tuple · level recorded 2026-09-24 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket src/build_rindex/build_wiki_rindex.py ran fingerprinted MIT (permissive) ·
b1c91c9e3a3b88e4 · report
fixture: signature text:str/0/str · returned str · level recorded 2026-09-25 0a343f931a447c8e · report
fixture: signature cursor:Cursor/0/?, article_title:str/0/str, p_num:int/0/int, table_name:str/0/str · returned list · level recorded 2026-09-24 e157daea0cea1f36 · report
fixture: signature input_str:str/0/str · returned str · level recorded 2026-09-24 Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | HotpotQA | SemanticRetrievalMRS | ANS-EM | 0.453 | #44 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | SemanticRetrievalMRS | ANS-F1 | 0.573 | #44 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | SemanticRetrievalMRS | JOINT-EM | 0.251 | #44 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | SemanticRetrievalMRS | JOINT-F1 | 0.476 | #44 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | SemanticRetrievalMRS | SUP-EM | 0.387 | #44 of 72 | Archive leaderboard | report |
| Question Answering | HotpotQA | SemanticRetrievalMRS | SUP-F1 | 0.708 | #44 of 72 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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