Papers › All-but-the-Top: Simple and Effective Postprocessing for Word Representations

All-but-the-Top: Simple and Effective Postprocessing for Word Representations

5 Feb 2017ICLR 2018 1arXiv:1702.01417archive 2025-07-28

Jiaqi Mu, Suma Bhat, Pramod Viswanath

Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a few top dominating directions from the word vectors -- that renders off-the-shelf representations {\em even stronger}. The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1702.01417")

Code

Syntology Ran 2 of 26 code samples harvested from 2 repositories linked to this paper; 24 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: community (archive-listed): 26 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lgalke/vec4ir mentioned on GitHubtfMIT report
nlpAThits/WOMBAT mentioned on GitHub report
woctezuma/steam-descriptions mentioned on GitHubtfMIT 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

26 samples harvested; 2 ran; 0 honoured the contract we drafted; 24 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
24unverified

Licence: 0 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

mean_reciprocal_rank lgalke/vec4ir/vec4ir/rank_metrics.py community (archive-listed) ran MIT (permissive) · 65bd69884cbfbdc9 · report
r_precision lgalke/vec4ir/vec4ir/rank_metrics.py community (archive-listed) ran fingerprinted MIT (permissive) · 1c940d569262c1bb · report
aggregate_dicts lgalke/vec4ir/vec4ir/combination.py community (archive-listed) unverified MIT (permissive) · b283385e4542d942 · report
all_but_the_top lgalke/vec4ir/vec4ir/postprocessing.py community (archive-listed) unverified MIT (permissive) · 5d4fdb7bf9b69030 · report
compute_pc woctezuma/steam-descriptions/SIF_embedding.py community (archive-listed) unverified MIT (permissive) · da8430897fe9994d · report
compute_retrieval_score woctezuma/steam-descriptions/hard_coded_ground_truth.py community (archive-listed) unverified MIT (permissive) · c956460114b027c7 · report
compute_retrieval_score_based_on_sharing_meta_data woctezuma/steam-descriptions/steam_spy_based_ground_truth.py community (archive-listed) unverified MIT (permissive) · d8ff6aad1114d84f · report
delta lgalke/vec4ir/vec4ir/eqlm.py community (archive-listed) unverified MIT (permissive) · 9b9bf22b3f9692b7 · report
eqe1 lgalke/vec4ir/vec4ir/eqlm.py community (archive-listed) unverified MIT (permissive) · 3514fb2cdfab561d · report
expand lgalke/vec4ir/vec4ir/eqlm.py community (archive-listed) unverified MIT (permissive) · 3c032c9ef0a071ed · report
f1_score lgalke/vec4ir/vec4ir/base.py community (archive-listed) unverified MIT (permissive) · 4e503c5d0be1ac1c · report
filter_none lgalke/vec4ir/vec4ir/base.py community (archive-listed) unverified MIT (permissive) · f3932c5856a22a48 · report
filter_out_words_not_in_vocabulary woctezuma/steam-descriptions/sentence_models.py community (archive-listed) unverified MIT (permissive) · ff6ad3cdd392ee59 · report
fuzzy_or lgalke/vec4ir/vec4ir/combination.py community (archive-listed) unverified MIT (permissive) · 14985f458b636e07 · report
get_small_banner_url woctezuma/steam-descriptions/find_unique_games.py community (archive-listed) unverified MIT (permissive) · 89ab94b0acec1f01 · report
get_store_url woctezuma/steam-descriptions/benchmark_utils.py community (archive-listed) unverified MIT (permissive) · d8940449fdc20406 · report
get_store_url_as_bb_code woctezuma/steam-descriptions/sentence_models.py community (archive-listed) unverified MIT (permissive) · dd93a92c0ff9a838 · report
get_weighted_average woctezuma/steam-descriptions/SIF_embedding.py community (archive-listed) unverified MIT (permissive) · 026881372c1acba1 · report
get_word_model_vocabulary woctezuma/steam-descriptions/word_model.py community (archive-listed) unverified MIT (permissive) · 74ad04dddaa20e30 · report
harvest lgalke/vec4ir/vec4ir/base.py community (archive-listed) unverified MIT (permissive) · 007dc399b4466aa1 · report
harvest_docs lgalke/vec4ir/vec4ir/datasets.py community (archive-listed) unverified MIT (permissive) · 6affee200375e11e · report
mine_gold lgalke/vec4ir/vec4ir/datasets.py community (archive-listed) unverified MIT (permissive) · 8292abe95b52ea1c · report
precision_at_k lgalke/vec4ir/vec4ir/rank_metrics.py community (archive-listed) unverified MIT (permissive) · 0b5204fbf39cb428 · report
remove_pc woctezuma/steam-descriptions/SIF_embedding.py community (archive-listed) unverified MIT (permissive) · 84d9ddc54e992bf6 · report
synthesize_topics lgalke/vec4ir/vec4ir/datasets.py community (archive-listed) unverified MIT (permissive) · 0ee5810d2cce719e · report
test_word woctezuma/steam-descriptions/word_model.py community (archive-listed) unverified MIT (permissive) · d4b5206c822ba5a1 · report

Tasks

AllGeneral ClassificationSentenceSentiment AnalysisSubjectivity AnalysisText ClassificationWord Similarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis MR GRU-RNN-WORD2VEC Accuracy 78.26 #11 of 19 Archive leaderboard report
Sentiment Analysis SST-5 Fine-grained classification GRU-RNN-WORD2VEC Accuracy 45.02 #25 of 31 Archive leaderboard report
Subjectivity Analysis SUBJ GRU-RNN-GLOVE Accuracy 91.85 #15 of 19 Archive leaderboard report
Text Classification TREC-6 GRU-RNN-GLOVE Error 7.0 #13 of 19 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.

Methods

GloVe

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