Papers › Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser

Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser

24 Sep 2016EMNLP 2016 11arXiv:1609.07561archive 2025-07-28

Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Noah A. Smith

We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy LSTM transition-based parsers with different random initializations. We cast this approach as minimum Bayes risk decoding (under the Hamming cost) and argue that weaker consensus within the ensemble is a useful signal of difficulty or ambiguity. The second parser is a "distillation" of the ensemble into a single model. We train the distillation parser using a structured hinge loss objective with a novel cost that incorporates ensemble uncertainty estimates for each possible attachment, thereby avoiding the intractable cross-entropy computations required by applying standard distillation objectives to problems with structured outputs. The first-order distillation parser matches or surpasses the state of the art on English, Chinese, and German.

PaperPDFConference PDFCode

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

Code

adhigunasurya/distillation_parser officialmentioned in papermentioned on GitHub 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

Dependency Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dependency Parsing Penn Treebank Distilled neural FOG LAS 92.06 #18 of 22 Archive leaderboard report
Dependency Parsing Penn Treebank Distilled neural FOG POS 97.44 #18 of 22 Archive leaderboard report
Dependency Parsing Penn Treebank Distilled neural FOG UAS 94.26 #18 of 22 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

LSTMSigmoid ActivationTanh Activation

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