System Combination for Grammatical Error Correction Based on Integer
Programming
- URL: http://arxiv.org/abs/2111.01465v1
- Date: Tue, 2 Nov 2021 10:08:46 GMT
- Title: System Combination for Grammatical Error Correction Based on Integer
Programming
- Authors: Ruixi Lin and Hwee Tou Ng
- Abstract summary: We propose a system combination method for grammatical error correction (GEC) based on nonlinear integer programming (IP)
Our method optimize a novel F score objective based on error types, and combines multiple end-to-end GEC systems.
Experiments of the IP approach on combining state-of-the-art standalone GEC systems show that the combined system outperforms all standalone systems.
- Score: 26.817392377302014
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we propose a system combination method for grammatical error
correction (GEC), based on nonlinear integer programming (IP). Our method
optimizes a novel F score objective based on error types, and combines multiple
end-to-end GEC systems. The proposed IP approach optimizes the selection of a
single best system for each grammatical error type present in the data.
Experiments of the IP approach on combining state-of-the-art standalone GEC
systems show that the combined system outperforms all standalone systems. It
improves F0.5 score by 3.61% when combining the two best participating systems
in the BEA 2019 shared task, and achieves F0.5 score of 73.08%. We also perform
experiments to compare our IP approach with another state-of-the-art system
combination method for GEC, demonstrating IP's competitive combination
capability.
Related papers
- Decoding-Time Language Model Alignment with Multiple Objectives [88.64776769490732]
Existing methods primarily focus on optimizing LMs for a single reward function, limiting their adaptability to varied objectives.
Here, we propose $textbfmulti-objective decoding (MOD)$, a decoding-time algorithm that outputs the next token from a linear combination of predictions.
We show why existing approaches can be sub-optimal even in natural settings and obtain optimality guarantees for our method.
arXiv Detail & Related papers (2024-06-27T02:46:30Z) - Ensemble Quadratic Assignment Network for Graph Matching [52.20001802006391]
Graph matching is a commonly used technique in computer vision and pattern recognition.
Recent data-driven approaches have improved the graph matching accuracy remarkably.
We propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
arXiv Detail & Related papers (2024-03-11T06:34:05Z) - System Combination via Quality Estimation for Grammatical Error
Correction [29.91720235173108]
We propose GRECO, a new state-of-the-art quality estimation model that gives a better estimate of the quality of a corrected sentence.
We also propose three methods for utilizing GEC quality estimation models for system combination with varying generality.
arXiv Detail & Related papers (2023-10-23T13:46:49Z) - Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic
Learning [53.73316523766183]
Coreference resolution systems need to tackle two main tasks.
One task is to detect all of the potential mentions, the other is to learn the linking of an antecedent for each possible mention.
We propose a hybrid rule-neural coreference resolution system based on actor-critic learning.
arXiv Detail & Related papers (2022-12-20T08:55:47Z) - Two-pass Decoding and Cross-adaptation Based System Combination of
End-to-end Conformer and Hybrid TDNN ASR Systems [61.90743116707422]
This paper investigates multi-pass rescoring and cross adaptation based system combination approaches for hybrid TDNN and Conformer E2E ASR systems.
The best combined system obtained using multi-pass rescoring produced statistically significant word error rate (WER) reductions of 2.5% to 3.9% absolute (22.5% to 28.9% relative) over the stand alone Conformer system on the NIST Hub5'00, Rt03 and Rt02 evaluation data.
arXiv Detail & Related papers (2022-06-23T10:17:13Z) - Matching Pursuit Based Scheduling for Over-the-Air Federated Learning [67.59503935237676]
This paper develops a class of low-complexity device scheduling algorithms for over-the-air learning via the method of federated learning.
Compared to the state-of-the-art proposed scheme, the proposed scheme poses a drastically lower efficiency system.
The efficiency of the proposed scheme is confirmed via experiments on the CIFAR dataset.
arXiv Detail & Related papers (2022-06-14T08:14:14Z) - A Study of Different Ways to Use The Conformer Model For Spoken Language
Understanding [25.41993752756759]
We compare different ways to combine ASR and NLU, in particular using a single Conformer model.
We find that it is not necessarily a choice between two-stage decoding and end-to-end systems which determines the best system for research or application.
arXiv Detail & Related papers (2022-04-08T07:12:11Z) - Selecting the Best Optimizing System [16.16839471915128]
We formulate selecting the best optimizing system (SBOS) problems and provide solutions for those problems.
An SBOS problem compares different systems based on their expected performances under their own optimally chosen decision to select the best.
We design easy-to-implement algorithms that adaptively chooses a system and a choice of decision to evaluate the noisy system performance.
arXiv Detail & Related papers (2022-01-09T18:26:40Z) - Model Selection in Batch Policy Optimization [88.52887493684078]
We study the problem of model selection in batch policy optimization.
We identify three sources of error that any model selection algorithm should optimally trade-off in order to be competitive.
arXiv Detail & Related papers (2021-12-23T02:31:50Z) - Diversity-Driven Combination for Grammatical Error Correction [30.63256303821261]
Grammatical error correction (GEC) is the task of detecting and correcting errors in a written text.
To achieve successful system combination, multiple component systems need to produce corrected sentences that are both diverse and of comparable quality.
We present Diversity-Driven Combination (DDC) for GEC, a system combination strategy that encourages diversity among component systems.
arXiv Detail & Related papers (2021-10-28T14:20:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.