Papers › Auxiliary Objectives for Neural Error Detection Models

Auxiliary Objectives for Neural Error Detection Models

17 Jul 2017WS 2017 9arXiv:1707.05227archive 2025-07-28

Marek Rei, Helen Yannakoudakis

We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary costs provide the model with additional linguistic information, allowing it to learn general-purpose compositional features that can then be exploited for other objectives. Our experiments show that a joint learning approach trained with parallel labels on in-domain data improves performance over the previous best error detection system. While the resulting model has the same number of parameters, the additional objectives allow it to be optimised more efficiently and achieve better performance.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Grammatical Error Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Grammatical Error Detection CoNLL-2014 A1 Bi-LSTM + POS (unrestricted data) F0.5 36.1 #2 of 8 Archive leaderboard report
Grammatical Error Detection CoNLL-2014 A1 Bi-LSTM + POS (trained on FCE) F0.5 17.5 #7 of 8 Archive leaderboard report
Grammatical Error Detection CoNLL-2014 A2 Bi-LSTM + POS (unrestricted data) F0.5 45.1 #2 of 8 Archive leaderboard report
Grammatical Error Detection CoNLL-2014 A2 Bi-LSTM + POS (trained on FCE) F0.5 26.2 #6 of 8 Archive leaderboard report
Grammatical Error Detection FCE Bi-LSTM + err POS GR F0.5 47.7 #5 of 8 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