Papers › To be Continuous, or to be Discrete, Those are Bits of Questions

To be Continuous, or to be Discrete, Those are Bits of Questions

12 Jun 2024arXiv:2406.07812archive 2025-07-28

Yiran Wang, Masao Utiyama

Recently, binary representation has been proposed as a novel representation that lies between continuous and discrete representations. It exhibits considerable information-preserving capability when being used to replace continuous input vectors. In this paper, we investigate the feasibility of further introducing it to the output side, aiming to allow models to output binary labels instead. To preserve the structural information on the output side along with label information, we extend the previous contrastive hashing method as structured contrastive hashing. More specifically, we upgrade CKY from label-level to bit-level, define a new similarity function with span marginal probabilities, and introduce a novel contrastive loss function with a carefully designed instance selection strategy. Our model achieves competitive performance on various structured prediction tasks, and demonstrates that binary representation can be considered a novel representation that further bridges the gap between the continuous nature of deep learning and the discrete intrinsic property of natural languages.

PaperPDFCode

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

Code

speedcell4/parserker officialmentioned in paper 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Constituency ParsingNested Named Entity RecognitionStructured Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Parsing CTB5 Hashing + Bert F1 score 92.33 #4 of 9 Archive leaderboard report
Constituency Parsing Penn Treebank Hashing + XLNet F1 score 96.43 #1 of 27 Archive leaderboard report
Constituency Parsing Penn Treebank Hashing + Bert F1 score 96.03 #7 of 27 Archive leaderboard report
Nested Named Entity Recognition ACE 2004 Hashing F1 87.93 #9 of 24 Archive leaderboard report
Nested Named Entity Recognition ACE 2005 Hashing F1 85.90 #10 of 25 Archive leaderboard report
Nested Named Entity Recognition GENIA Hashing F1 80.54 #7 of 26 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