Browse › Natural Language Processing › Word Sense Disambiguation › Words in Context

Word Sense Disambiguation archive 2025-07-28

Words in Context Benchmark (Word Sense Disambiguation)

37 rows 26 with code listed 1 metric Dataset page

The task of Word Sense Disambiguation (WSD) consists of associating words in context with their most suitable entry in a pre-defined sense inventory. The de-facto sense inventory for English in WSD is WordNet.. For example, given the word “mouse” and the following sentence:

“A mouse consists of an object held in one's hand, with one or more buttons.”

we would assign “mouse” with its electronic device sense (the 4th sense in the WordNet sense inventory).

The archive carries no text for this table; the description above is the archive's text for the task Word Sense Disambiguation. archive 2025-07-28

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: Accuracy (higher is better). Points are placed at the row's paper date; 37 of 37 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 COSINE + Transductive Learning 85.3 – Paper Code 2020 0 of 5 ran · 5 unverified report
2 PaLM 540B (finetuned) 78.8 – Paper Code 2022 30 of 37 ran · 7 unverified report
3 ST-MoE-32B 269B (fine-tuned) 77.7 – Paper Code 2022 5 of 5 ran · 0 unverified report
4 DeBERTa-Ensemble 77.5 – Paper Code 2020 4 of 13 ran · 9 unverified report
5 Vega v2 6B (fine-tuned) 77.4 – Paper – 2022 no code linked report
6 UL2 20B (fine-tuned) 77.3 – Paper Code 2022 0 of 16 ran · 16 unverified report
7 Turing NLR v5 XXL 5.4B (fine-tuned) 77.1 – Paper – 2022 no code linked report
8 T5-XXL 11B 76.9 – Paper Code 2019 2 of 31 ran · 29 unverified report
9 DeBERTa-1.5B 76.4 – Paper Code 2020 4 of 13 ran · 9 unverified report
10 ST-MoE-L 4.1B (fine-tuned) 74 – Paper Code 2022 5 of 5 ran · 0 unverified report
11 SenseBERT-large 340M 72.1 – Paper – 2019 no code linked report
12 SenseBERT-base 110M 70.3 – Paper – 2019 no code linked report
13 PaLM 2-L (one-shot) 66.8 – Paper Code 2023 linked, not harvested report
14 BERT-large 340M 65.5 – Paper – 2018 no code linked report
15 FLAN-T5-Large 783M 64.7 – Paper Code 2023 linked, not harvested report
16 LaMini-F-T5 783M 63.8 – Paper Code 2023 linked, not harvested report
17 Context2vec 59.3 – Paper – 2018 no code linked report
18 DeConf 58.7 – Paper – 2018 no code linked report
19 SW2V 58.1 – Paper – 2018 no code linked report
20 ElMo 57.7 – Paper – 2018 no code linked report
21 T0-3B (CoT fine-tuned) 56.7 – Paper Code 2023 linked, not harvested report
22 N-Grammer 343M 56.1 – Paper Code 2022 0 of 6 ran · 6 unverified report
23 AlexaTM 20B 53.3 – Paper Code 2022 1 of 1 ran · 0 unverified report
24 Sentence LSTM 53.1 – Paper – 2018 no code linked report
25 RoE-3B 52.97 – Paper Code 2023 3 of 3 ran · 0 unverified report
26 LaMini-GPT 1.5B 52.4 – Paper Code 2023 linked, not harvested report
27 KiC-770M 52.40 – Paper – 2022 no code linked report
28 PaLM 2-M (one-shot) 52.0 – Paper Code 2023 linked, not harvested report
29 Hybrid H3 125M (0-shot, logit scoring) 51.4 – Paper Code 2022 7 of 15 ran · 8 unverified report
30 Hybrid H3 125M (0-shot, rank classification) 51.4 – Paper Code 2022 7 of 15 ran · 8 unverified report
31 PaLM 2-S (one-shot) 50.6 – Paper Code 2023 linked, not harvested report
32 LaMini-T5 738M 50.5 – Paper Code 2023 linked, not harvested report
33 Flipped-3B 50.42 – Paper Code 2022 linked, not harvested report
34 GPT-2-XL 1.5B 49.8 – Paper Code 2023 linked, not harvested report
35 UL2 20B (0-shot) 49.8 – Paper Code 2022 0 of 16 ran · 16 unverified report
36 GPT-3 175B (few-shot, k=32) 49.4 – Paper Code 2020 15 of 65 ran · 50 unverified report
37 Hybrid H3 125M (3-shot, logit scoring) 49.1 – Paper Code 2022 7 of 15 ran · 8 unverified report

All 37 rows shown. 37 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 16 rows have a graph line, from 11 distinct papers; 12 rows (8 papers) have at least one sample that ran. Counting each paper once: Syntology ran 67 of 197 samples; 130 unverified. Separately, 15 of those 197 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

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