Mobile QR Code QR CODE

2025

Reject Ratio

81.5%


  1. (Hebei Mechanical and Electrical Polytechnic, Xingtai 054000, China)



Natural language processing, Multi-interactive feature fusion, Semantic accuracy, Processing of long and difficult sentences

1. Introduction

Automatic translation system, as an important application in the field of natural language processing, has made remarkable progress in recent years. However, with the acceleration of globalization and the increasing cross-cultural communication, the translation system faces more and more challenges. Especially when it comes to cultural nuances, idioms, and complex contexts, traditional translation methods (such as statistical machine translation and rule-based translation systems) are often difficult to achieve satisfactory translation results. English grammatical error correction (GEC) is a crucial aspect of natural language processing (NLP), focusing on identifying and rectifying grammatical errors by analyzing grammatical dependencies and logicality in input sentences. In second language learning, ESL learners must promptly spot spelling errors and ensure grammatical accuracy, as grammar underpins precise, clear, and effective communication [1]. Efficient GEC tools aid learners in revising their work, enhancing grammar perception and application, and overcoming grammar barriers in ESL learning. They also alleviate teachers' classroom workload and teaching pressure. Research on automatic GEC informs machine understanding of natural language, intelligent knowledge processing, and semantic search technology, providing insights for foreign and native language learning [2, 3]. This exploration helps students grasp English word meanings accurately, reduces misuse, improves grammatical proficiency, enhances learning initiative, and boosts English learning efficiency.

The traditional translation system refers to the process of using the artificial way to transform the content of one language into another language. It depends on the translator's language understanding, expression ability and the understanding of the culture, background and grammar of the two languages. It has existed for thousands of years and is one of the main translation methods. With NLP advancements, GEC methods have evolved from rule-based, classification-based, and language model-based to the current mainstream machine translation-based approaches. Each method has its strengths and limitations. For instance, rule-based methods target syntax errors precisely but require vast rule bases and may encounter rule conflicts. Classification-based GEC excels in correcting articles and prepositions but covers fewer error types. Neural machine translation handles long-distance dependencies well but poses high model training complexity. Currently, data-driven and machine translation-based methods dominate GEC tasks, with neural machine translation (NMT) models making significant progress [4, 5]. These models effectively handle long-distance semantic dependencies, enabling improved syntax error correction. Researchers utilize Encoder-Decoder structures to train multiple GEC models on artificially synthesized datasets, jointly correcting input sentences at the source to mitigate overfitting and boost generalization. They further refine the decoding results with external features like language models, edit distance, and edit operations.

When labeled corpora are scarce, synthesizing high-quality training data is crucial for improving the performance of GEC models [6, 7]. Data augmentation methods based on seed corpus error distributions, have been proposed. However, such data may not align with the natural distribution of grammatical errors, limiting their direct application to GEC tasks. Additionally, these methods often face challenges in ensuring data quality. The quality of the generated training data will also be uneven due to the pros and cons of the translation model. The data augmentation method based on revision history can collect manually corrected historical data, which is more authentic, but usually requires data cleaning, quality control and other operations to identify and delete irrelevant and inaccurate data. Nowadays, the GEC model widely uses data augmentation methods to solve the problem of training in the GEC field. The problem of lack of data; Using model integration and other methods to achieve model optimization; A multi-feature reordering strategy is used to sort the candidate corrective sentences to optimize the output results [8, 9]. Usually, the combination of the three can make the model output the best correction results.

2. Relevant Theories and Methods

This chapter discusses theories and methods in syntax error detection and correction, including corpora, evaluation methods, detection/correction models, and data augmentation techniques. Machine translation-based GEC methods, stemming from statistical and neural approaches, yield promising results. However, a lack of manually labeled data poses challenges. To enhance GEC system performance, techniques beyond traditional models have emerged. Multi-interaction feature fusion is an advanced algorithm that improves the accuracy of the translation system by dynamically integrating syntactic structure, semantic information and pragmatic elements. This fusion approach aims to capture those nuances and contextual cues that are difficult to capture by traditional translation methods, thus improving the naturalness and accuracy of translation. Fig. 1 illustrates the typical GEC system architecture for syntax error detection and correction tasks.

Fig. 1. Automatic English translation efficiency optimization process.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig1.png

2.1. Grammatical Error Detection and Correction Task-Related Corpus

Deep learning has achieved notable advances in NLP tasks, but detecting and correcting English grammatical errors remains challenging [10]. This stems from the diversity of syntax errors, semantic interdependencies, and the scarcity of manually labeled data. To enhance GEC model performance, the learner corpus size is continuously expanded. Corpora in the GEC field include monolingual corpora and learner corpora. Monolingual corpus has the advantages of rich text types, large amount of data, and easy collection; The learner corpus consists of “wrong-right” parallel sentence pairs, which contain high-quality tagged corpus, but the data scale is small.

2.1.1 The One-Billion Word Benchmark corpus

The One-Billion Word Benchmark is a benchmark corpus of nearly 1 billion words. The data set was released by Cornell University in 2013 and is mainly derived from the web page. The base material library can be used to quickly evaluate language modeling techniques [11, 12]. Therefore, in order to improve the quality of the data, the data in the corpus have undergone preprocessing operations, including de-duplication, normalization, word segmentation and other operations. In addition, the dictionaries in the corpus are composed of 79347 words with word frequency higher than three markers, which represent the word markers outside the dictionary, the beginning markers of sentences and the end markers of sentences respectively. The publication of this corpus further improves language model performance.

2.1.2 Tatoeba corpus

The Tatoeba Corpus is a new benchmark corpus published for machine translation. The current version contains more than 500GB of compressed data and covers 555 languages [13, 14]. The data set provides some parallel corpus and monolingual corpus, which provide data source support for data augmentation methods.

2.1.3 Wikipedia corpus

Wikipedia is an online Encyclopaedia based on Wikipedia technology, written in multiple languages, with all-encompassing content, both arts and sciences. The Simple Wiki corpus uses only about 1500 common English words compared to the usual Wikipedia corpus, which makes the sentences more understandable grammatically [15], semantically, and structurally. The Wikipedia corpus contains modified editorial records (editorial histories) from different periods. The error statement is provided by an older Wikipedia page consisting of the manual correction, the time of correction, the name of the person who corrected it, and the revised summary. The correct statement is provided by the latest Wikipedia page.

2.2. GEC Evaluation Index

In recent years, English grammar error correction has made an important breakthrough in the field of natural language processing, and a variety of evaluation methods for GEC systems have been produced. Evaluation methods usually compare the output sequence with the gold standard sequence (manually labeled target sentences). During the comparison process, the output correction sentence and the target sentence need to be word aligned. Previously, the performance of the GEC model was only measured by accuracy [16]. Later, the GEC system can be measured by the recall rate of M2 and I indicators. Nowadays, the generation of GLEU and ERRANT error kits makes the evaluation results of the GEC system fairer and more reasonable. The system was evaluated by accuracy (P) and Fos values. The calculation formulas are as shown in Formulas (1)-(3).

(1)
$ P = \frac{\sum_{i=1}^n |e_i \cap g_i|}{\sum_{i=1}^n |e_i|}, $
(2)
$ U_i = \sum_{i=1}^n |k_i \cap p_i|, $
(3)
$ F_{0.5} = \frac{P \times R(1+0.5^2)}{(0.5^2 \times P) + R}. $

2.3. GELU Algorithm Principle

Jia et al. [17] introduced the GLEU metric for sentence fluency evaluation, a BLEU variant. Let S be the error sentence, R the manually labeled standard, and W the uniform weight. The GEC system's corrected output is C. GLEU calculates the weighted accuracy Pn of C compared to R. BP (Brevity Penalty) factors in the lengths of C and R. GLEU is used specifically for the JFLEG dataset. The formula was calculated as described in Eqs. (4) and (5).

(4)
$ GLEU(C,R,S) = BP \cdot \exp \left( \sum_{n=1}^4 W_n \log p'_n \right), $
(5)
$ BP = \begin{cases} 1, & \text{if } c > r, \\ e^{\left(1-\frac{r}{c}\right)}, & \text{if } c \le r. \end{cases} $

ERRANT Toolkit extracts the number of edits from the source sentence and the corrected sentence, realizes the classification of error types, and helps to evaluate the types of grammatical errors. The tool uses an alignment algorithm between source and correcting sentences proposed by Razia et al. and uses a rule-based error type framework to assign error types [18, 19]. The frame is independent of the dataset, relying only on information such as part-of-speech markers. For M2, I index, GLEU and other evaluation indicators, because the output of GEC system is not annotated, the performance of English error correction can only be measured by the recall rate. The ERRANT toolkit overcomes this shortcoming. Previous metrics tend to evaluate the overall performance of the system, but systems with poor overall performance may have an advantage in correcting specific error types. ERRANT Syntax Error Annotation Toolkit proposes the idea of error type analysis to evaluate the performance of the system more comprehensively. The calculation formula is described as Eq. (6).

(6)
$ I = \begin{cases} WACC_{sys}, & \text{if } WACC_{sys} = WACC_{base}, \\ \frac{WACC_{sys} - WACC_{base}}{1 - WACC_{base}}, & \text{if } WACC_{sys} > WACC_{base}. \end{cases} $

3. Syntax Error Generation Model

In this paper, the open-source FAIR Sequence-to-Sequence toolkit is used to implement the model structure. The dimension of the word vector and the target end of the GEG system is 512, the network layer contained in the encoder and decoder is 6 layers, the hidden layer (FFN) dimension of the forward neural network sublayer is set to 4096, the dropout rate is set to 0.2, the optimization algorithm uses Adam [20], 8 attention heads, the initialization learning rate is 0.002, the label smoothing rate is set to 0.2, the warmup step size is 16000, and the sampling decoding is used. The experiment used the CoNLL-2014 test set and M2 as evaluation indicators.

Fig. 2. Multi-interactive feature fusion NLP algorithm process.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig2.png

Fig. 2 shows multi-interactive feature fusion NLP algorithm process. Data augmentation can be regarded as a way to preprocess the data of training set. The core of the multi-interaction feature fusion algorithm is the dynamic integration of language features such as syntactic, semantic and pragmatic. Syntactic features focus on the structural information of sentences, such as word order, phrase and clauses; semantic features include the meaning of words, synonyms and antonyms, and context, politeness and implied meaning. By combining these features, the algorithm is able to more accurately capture the intention and context information of the original text and thus, improve the accuracy of translation. In order to improve the quality of the data, it is necessary to clean up the data before performing tasks such as data augmentation and model training. For example, before using Lang-8 data, the training data needs to be cleaned up [21]. The FPN class represents the case that FP and FN are satisfied at the same time, and the calculation formulas of P, R and F are described in Eqs. (7)-(9).

(7)
$ P = \frac{TP}{TP+FP}, $
(8)
$ R = \frac{TP}{TP+FN}, $
(9)
$ F_\beta = (1+\beta^2) \cdot \frac{P \cdot R}{(\beta^2 \cdot P) + R}. $

For the learner corpus containing special symbols, the operation of deleting special symbols is performed. Translation model loss function and optimization algorithm update formulas are shown in Eqs. (10) and (11).

(10)
$ U_l^A := \sum_{k=(l-1)T}^{(l-1)T+h-1} (az_k - bc(G_k^D)), $
(11)
$ z_k(\bar{\mathcal{E}}_k^A, \mathcal{E}_k^A, \mathcal{E}_k^D) := x^T[k+1] L_c x[k+1]. $

3.1. Syntax Error Generation Model and Experimental Process Design

To better understand the context, we explored lexical, syntactic, and semantic feature extraction techniques. At the lexical level, we employed word frequency statistics and word embedding techniques to capture the semantic information and distribution properties of words. In terms of syntactic features, we use analytic trees and dependency graphs to extract the structural information of sentences. Semantic features are acquired through semantic role annotation and named entity recognition technology. These feature extraction techniques work together on the original text and provide rich linguistic information for the subsequent translation process. Firstly, the validity of this experiment is verified on the existing three learner corpus NUCLE, FCE, W-IHLOCNESS and the monolingual corpus One Billion Word. In addition, in order to facilitate the comparison with the existing work, the Lang-8 corpus is used to fine-tune the GEC model at the end of this paper. Table 1 shows all the training corpus used in this paper and the corresponding data scales. By counting the sentence length distribution in the learner corpus, the sentence length in the monolingual corpus is constrained, and the training data length in the monolingual corpus is reduced to the token length of 5 to 100. Table 1 shows all the training corpus used in this paper and the corresponding data scales.

Table 1. All the training corpus used in this paper and the corresponding data scales.

Corpus name Number of sentences Marks (tokens)
Learner corpus NUCLE 57151 (approx. 57K) Approximately 1.2 M
FCE 28350 (approx. 28K) Approximately 455K;
Wi & locness 34308 (approx. 34K) Approximately 628K;
Social Media Volume data Lang-8 1.04 million (approximately 1.04 M) Approximately 11.86 M Lingua franca
Material storage One Billion word 1.7 million (about 1.7 M) Approximately 19M

The probabilities of introducing the four rules are 0.3, 0.25, 0.25, 0.217. Secondly, through the analysis of the distribution of error types in the learner corpus, it is found that verb (about 7%), noun (about 4.5%), article (about 10.86%), spelling (about 9.59%), preposition (about 11.2%) and punctuation errors (about 9.7%) account for a high proportion. In order to solve these error types, this paper proposes a strategy of substitution rule derivative mutation. By counting the words with a word frequency number higher than 3 in the monolingual corpus, the first 7000 words are reserved to form a dictionary. Feature fusion weights and multi-interaction feature extraction formulas are shown in Eqs. (12) and (13).

(12)
$ c(G') := \sum_{p=1}^{\bar{n}(G')} |V'_p|^2 - |V|^2 \quad (\le 0), $
(13)
$ \sum_{m=0}^k (\bar{\beta}^A |\bar{\mathcal{E}}_m^A| + \beta^A |\mathcal{E}_m^A|) \le \kappa^A + \rho^A k, $

In the process of synthesizing data, one of the four operations of insertion, deletion, replacement and exchange is randomly performed on the selected words to be operated on. The artificial rule is defined as follows:

(1) Insert error (insert type)

The original sentence S without semantic errors, its sequence S is w0w1...w’...wi-1wi, and the error statement T obtained by inserting a rule and adding a token (token), the sequence T is: w0w1...w’...wi-1wi.Weighted accuracy WAcc calculation formula is described as Eq. (14).

(14)
$ W_{ACC} = \frac{\omega \cdot TP + TN}{\omega \cdot (TP+FP) + TN + FN - (\omega+1) \cdot \frac{FPN}{2}}. $

(2) Delete error (delete type)

The original sentence S without semantic errors, its sequence S is w0w1...w’...wi-1wi, through the deletion rule, randomly delete a token (token) w, and the resulting error statement T, the sequence T is: w0w1... wi-1wi.

(3) Exchange error (replace type)

The original sentence S without semantic errors, whose sequence S is w0w1...w’...wi-1wi, by exchanging any two tokens (tokens), the error statement T is obtained, and the sequence T is: w0w1...wi-1... wi.

(4) Substitution error (swap type)

The original sentence S without semantic errors, whose sequence S is w0w1...w’...wi-1wi, uses the confusion set created in this paper to replace the randomly selected token w: if w is in the list of words to be replaced in the confusion set, then randomly select an alternative word from the list of candidate sets corresponding to the token to replace it. If it does not appear in the list of confusion sets, then choose a word from the dictionary to replace it. The resulting error statement T, sequence T is: w0w1...w... wi-1wi. For the replacement rule, as far as possible, randomly select a word from the created candidate set to replace. Constructing a variety of polymorphic errors through artificial rules can provide more training data for GEG and GEC models. The specific experimental process of the rule-based data augmentation method is as follows:

Step 1: Use the three existing learner corpus to train the GEC model of this paper, and verify the results on the CoNLL-2014 test set.

Step 2: Use rule-based data augmentation method to generate training data with file sizes of 20M (the number of sentences is about 190K), 80M, 140M, and 200M, train GEC models, and compare the use of different scales The impact of data on training GEC. The BLEU score, feature importance assessment, and sequence-to-sequence model encoding-decoding formulas are shown in Eqs. (15)-(17).

(15)
$ P(s \mid t) = \prod_{T=1}^N P(s_T \mid t, s_{1:T-1}; \alpha_{backward}), $
(16)
$ \alpha_{backward} = \arg\max \sum \log P(s_T \mid t, s_{1:T-1}; \alpha_{backward}), $
(17)
$ Loss(\alpha_{backward}) = \sum -\log P(s_t \mid t, s_{kt-1}; \alpha_{backward}), $

Step 2: (GEG2→GEC) In order to further optimize the GEG2 model, this paper tries to combine the two data augmentation methods. First, the rule-based method is used to synthesize the training data, pre-train the error generation model, and then fine-tune it with the learner corpus to obtain the optimized error generation model GEG2. Using GEG, the model processes monolingual corpus, and generates synthetic data with file sizes of 20M, 80M, 140M, and 200M respectively. The synthetic data are used for the training of the GEC model to verify the fusion effect of different data augmentation methods.

3.2. Experimental Results and Analysis

Training data of different scales generated by rule-based data augmentation methods are used to train the GEC model together with the learner corpus. Its results on the CoNLL-2014 test set are shown in Fig. 3. With the increasing of the scale of synthetic data, the R value and F0.5 value of the GEC model trained using synthetic data can reach 23.7% and 37.9%, respectively, exceeding the 15.7% and 11.4% of the GEC model trained using only the learner corpus [22]. However, there is a large difference in accuracy, which is lower than the 18.4% of the GEC model trained using the learner corpus.

Fig. 3. Results on the CoNLL-2014 test set.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig3.png

Fig. 3 shows results on the CoNLL-2014 test set. Analyzing the reasons, using the rule-based data augmentation method, with the continuous increase of data scale, the performance of the trained syntax error correction model on the test set has been improved to a certain extent. It shows that the amplification of the data has a significant impact on the overall performance of the GEC model.

When the GEC model is trained with 200M synthetic data, its performance in recall rate exceeds that of the GEC model trained with only learner corpus. This is due to the data augmentation strategy used in this paper, that is, in the process of generating training data, part of speech errors, punctuation errors, and spelling errors of different words are incorporated. Compared with the simple random word selection from the vocabulary, the error types are richer and more targeted, and the recall rate is significantly improved.

Fig. 4. Translation efficiency versus the bar graph.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig4.png

Fig. 4 shows translation efficiency versus the bar graph. As for the accuracy of model recognition, with the increase of synthetic training data, the results continue to improve, but there is a certain gap between the accuracy of the model obtained by training only using the learner corpus. The learner corpus contains English grammatical errors in real situations, and the types of errors are abundant [23]. Compared with the learner corpus, the data augmentation method proposed in this paper still has a certain gap between the GEC model and the learner corpus in terms of the types and quantities of errors. However, the gap can be made up by the amount of data. Therefore, how to further improve the quality of data has important research significance.

Fig. 5. GEC model performance trained on data of different sizes.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig5.png

Fig. 5 shows GEC model performance trained on data of different sizes. The resulting GEC model is trained using different scale synthetic data generated by different GEG models, and the results are shown in Table 2. The F0.5 value of the best GEC model using the GEG model is 0.286. Compared with the GEG model, the performance of the GEC model using the GEG and synthesized 200M training data is about 5.2%, 3.9%, 4.9% higher than that using the GEG model, 3.9%, 4.9%, respectively.

Table 2. The resulting GEC models were trained using synthetic data of different sizes generated by different GEG models.

Model Synthetic data scale for training GECs
20M 80M 140M
P R F0.5 P R F0.5 P R F0.5
GEG1→GEC 0.275 0.135 0.228 0.291 0.184 0.261 0.304 0.193 0.273
GEG2→GEC 0.359 0.153 0.282 0.36 0.232 0.343 0.372 0.243 0.335

To verify the effectiveness of the algorithm, we designed two sets of experiments. The first set of experiments compared the effect of single feature fusion and multiple feature fusion, and the translation results were quantified by manual evaluation and automatic evaluation tools (e. g., BLEU, NIST, etc.). The results show that the multi-feature fusion algorithm outperforms the single feature fusion algorithm in both translation speed and semantic accuracy.

Fig. 6. Plot ISON of translation quality before and after feature fusion.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig6.png

This paper utilizes rule-synthesized data and a learner corpus to train an error generation model. Training the GEC model with this synthesized data leads to better results than directly using rule data. This demonstrates the effectiveness of fusing different data augmentation methods. As seen in Table 2, expanding the training data synthesized by the GEG1 model improves the GEC model's performance. However, the performance gains diminish as data size increases from 20M to 80M compared to 80M to 140M and 140M to 200M [24]. This suggests the model may reach saturation in identifying certain error types. The side model, focused on rule-based errors, has limitations in identifying errors. The findings indicate the importance of further optimizing GEG and GEC models to improve performance. To further improve the quality of translation, we performed a detailed error analysis. We classify errors into categories such as mistranslation, omission, and grammatical problems, and provide specific examples. By analyzing these errors, we found that they mainly result from problems such as inaccurate feature extraction, insufficient training data, or model limitations. For these problems, we propose corresponding improvement measures to optimize the algorithm performance.

Fig. 6 shows plot ison of translation quality before and after feature fusion. The GEC model trained with GEG1 data outperforms that of GEG2 when using the same dataset. Using GEG2's synthetic data enhances the recall and F-score of the GEC model [25]. Rule-based augmentation ultimately improve error correction performance due to the enhanced dataset quality.

4. Syntax Error Correction Model

This paper focuses on training the correction model of grammatical errors while giving consideration to spelling errors and semantic errors. Since the rich monolingual corpus can provide training data of different written styles for the model, this study provides rich prior knowledge for the model through operations such as pre-training of the model. Written text can have different types of errors at the same time, such as spelling errors, grammatical errors, semantic errors, etc. Spelling errors are often corrected using separate components such as spell checkers, human-defined specific rule templates, etc. The spell checker simply compares words in the text to a large number of known words. If the word is not in the list, it is considered incorrect and corrected. Grammatical errors refer to errors that cause sentences to fail to conform to English grammatical rules. Unlike spell checking errors, grammatical checking requires the use of contextual information. Syntax errors can be divided into structural errors and non-structural errors. A structural error is an error that can only be corrected by inserting, deleting, or moving one or more words [26]. A non-structural error is an error that can be corrected by replacing an existing word with something else. A semantic error refers to the existence of an incorrect meaning in the text, and this type of error is neither a grammatical error nor a spelling error. Semantic errors require extensive knowledge to identify, and it is difficult to correct them. Correct sentence: The telephone is a kind of conventional communication tool There is no grammatical error in this sentence, but it violates a semantic error. The telephone is a kind of conventional communication tool. Correct sentence: The telephone is a kind of conventional communication tool. There is no grammatical error in this sentence. Therefore, if the model does not have extensive prior knowledge, it cannot better correct semantic errors.

4.1. Experimental Data Setting and Evaluation Indexes

To comprehensively assess the quality of translation, we employed multiple assessment criteria. In addition to the commonly used BLEU scores, we considered other indicators such as METEOR and TER. Meanwhile, we also performed a manual evaluation focusing on fluency, adequacy and fidelity of translation. To ensure the impartiality of the assessment results, we developed a detailed assessment protocol and took steps to mitigate the assessment bias. For the GEC system, the dimension of the word vector and the dimension of the target end is 512, the network layer contained in the encoder and decoder is 6 layers, the hidden layer (FFN) dimension of the forward neural network sublayer is set to 4096, the dropout rate is set to 0.2, using the NAG (Nesterovs Accelerated Gradient, NAG) optimization algorithm, 8 attention heads, the initialization learning rate is 0.02, the weight decay is 0.5, the number of cycles when training stops is 0, and the momentum is set to 0.99, etc. The experiment will use the commonly used CoNLL-2014 test set and M2 as evaluation indicators. In addition, the JFLEG test set and GLEU values will also be used to analyze the fluency of the correction results of GEC. The attention mechanism and the regularization term addition formula are shown in Eqs. (18) and (19).

(18)
$ s(t) = w_c s_c(t) \sqrt{\alpha_c p} + \sum_k w_k s_k(t) \sqrt{\alpha_k p}, $
(19)
$ y_k(t) = h_k^H s(t) + \sqrt{\eta \delta} h_0^H s(t) g_k c_b(t) + u_k(t). $

First, the rule-based data augmentation strategy proposed in this paper is used to synthesize training data, and together with the learner corpus, the GEG model is trained. Then the GEC model is trained with the training data synthesized by the GEG model and the learner corpus. Inspired by the work of Maria et al. [27] to alternately train the English-Czech translation model, this paper uses the GEC model to correct the source sentences in the learner's corpus, and reconstructs the corrected results with the standard reference sentences in the learner's corpus. Parallel corpus is added to the training data of the GEG model, and the GEG model is trained again.

Similar to the monolingual corpus used by Tamara et al. [28] in training the reverse translation model, the monolingual data used in this paper are all from the written texts produced by native English-speaking learners in real situations, and the sentences are all authentic. The model performance evaluation index and feature fusion weight calculation formula is shown in Eq. (20).

(20)
$ \gamma_{k,b} = \frac{p \eta \delta v_{0,k} |g_k|^2}{p v_j + \sigma^2}. $

In order to improve the performance of grammatical error correction, the GEC model is used to correct the training data in the learner corpus, and the corrected results and the standard reference sentences in the training set form a parallel corpus, which is used as the extended data of the repeated training GEC model. The experimental process of alternating training model is as follows:

Step 1: For the translation-based GEC model, the excellent model will output the target sentence without syntax errors, and the low-performance model will produce erroneous output that is not in the actual situation. Because the performance of the GEC model trained with synthetic data is relatively low, this paper chooses the GEC model to process the source sentences in three learner corpora, so as to avoid the errors that some corrected sentences do not conform to grammatical rules due to the low GEC performance. Then the candidate sentences output from the model are combined with the standard reference sentences in the learner corpus to form a training set, and the error generation model is trained again after mixing with the training data synthesized by the rule-based data augmentation method, and the error generation model GEG is fine-tuned using three learner corpus;

Step 2 (GEG3→GEC): Using GEG, the model processes the monolingual corpus, and generates 20M, 80M, 140M, and 200M synthetic data with different scales again, and pre-trains the GEC model respectively.

Step 3: On the basis of the existing synthetic data, in order to further improve the performance of the GEC model, this paper tries to expand the scale of the pre-training data.

4.2. Experimental Results of Syntactic Error Correction Based on Alternating Training

Three grammatical error correction models were trained using 200M training data synthesized by GEG, and three learner corpus. Corrective sentences of the corresponding grammatical error correction models were defined as Corrective Sentence 1, Corrective Sentence 2, and Corrective Sentence 3 [29]. The source sentence is a grammatical error sentence, and the reference sentence is a standard corrective sentence. Correction results for some instances in the CoNLL-2014 test set are shown in Fig. 7.

Fig. 7. Corrected results for some instances in the CoNLL-2014 test set.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig7.png

Fig. 7 shows corrected results for some instances in the CoNLL-2014 test set. As shown in Fig. 7 (GEG1→GEC), the syntax error generation model GEG obtained through alternate training; Using GEG, the Fos value of the grammar correction model obtained from the synthesized training data can reach 0.384, which is about 4 percentage points higher than the F0.5 value obtained by using GEG and the model.

As shown in Fig. 8, if the learner corpus is added to the GEC model training process for fine-tuning, for the pre-training of the GEC model using 200M data synthesized at the same scale, the P, R, and F0.5 values of the GEC model are trained using GEG and the synthesized data Reach 0.659, 0.32, and 0.543 respectively. In order to further scale up the pre-training data, the GEC model is pre-trained after mixing the synthesized 200M training data with the synthesized 200M data synthesized by the rule-based data augmentation method, and then fine-tuned using three learner corpus. As can be seen from the experimental results in Fig. 8, after the data scale is expanded, the values of P, R, and F reach 0.677, 0.338, and 0.564, respectively, which are about 20%, 2%, and 13% higher than the GEC model without using learner corpus.

Fig. 8. Effect of different features on the translation accuracy.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig8.png

In order to better compare with the existing work, the Lang-8 corpus is added on the basis of the three-learner corpus, which is only used for fine-tuning the GEC model, and the model performance is further improved. Without the use of multi-model integration and reordering, the value of F0.5 reaches 0.62, and the accuracy of GEC model reaches 0.73, which has a clear advantage in the accuracy of correcting English grammatical errors. As shown in Fig. 9.

Fig. 9. Experimental results without using multi-model integration and reordering.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig9.png

In order to reasonably evaluate the performance of the GEC system on different indicators, this paper adds GLEU values to measure the performance of the system at the sentence level, and makes a comprehensive comparison with some existing research results. The results are shown in Fig. 10. The GLEU value on the JFLEG test set reached 0.61, which exceeded the GLEU result of Choaib et al. [30] on the JFLEG test set by about 5%.

Fig. 10. Comprehensive comparison with the results of some existing studies.

../../Resources/ieie/IEIESPC.2026.15.4.518/fig10.png

5. Conclusions

In the future, we will continue to deepen the research on this algorithm and explore more application scenarios and optimization methods to promote the continuous development and progress of automatic translation technology. At the same time, we also look forward to working with colleagues in the industry to jointly promote the innovation and application of natural language processing technology. In this study, NLP algorithm based on multi-interactive feature fusion is used to optimize the efficiency of automatic English translation system, and a series of remarkable results have been achieved. Through the introduction of multi-interactive feature fusion technology, we successfully fuse multi-level features such as lexical syntactic and semantic features and provide a richer and more accurate source of information for automatic English translation systems. Experimental results show that the proposed algorithm performs well in improving translation efficiency. Compared with traditional translation systems, the NLP algorithm based on multi-interactive feature fusion can process a large amount of text data more quickly, and significantly improve the translation speed while ensuring the translation quality. This advantage makes the algorithm have a wide range of application prospects in real-time translation, large-scale text translation and other scenarios. In terms of translation quality, the multi-interactive feature fusion algorithm also shows excellent performance. Through in-depth fusion and processing of multi-level features, the algorithm can more accurately grasp the semantic information and context relationship in the text, thereby generating more natural and smooth translation results. Especially when dealing with complex situations such as long and difficult sentences and technical terms, the algorithm can more accurately capture key information in the text, and avoid semantic ambiguity and misunderstanding that are common in traditional translation systems. In addition, this study also explores the application potential of multi-interactive feature fusion algorithms in different fields. Through experimental verification, we find that the algorithm has good translation effects in many fields such as technology, finance, and medicine, and provides strong support for cross-language communication. In summary, the NLP algorithm based on multi-interactive feature fusion has shown significant advantages and potential in the efficiency optimization research of automatic English translation systems.

References

1 
G. Huang , Y. Li , S. Jameel , Y. Long , G. Papanastasiou , From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?, Computational and Structural Biotechnology Journal, Vol. 24, pp. 362-373, 2024DOI
2 
C. J. Salley , N. Mohammadi , J. E. Taylor , Protecting critical infrastructure for disasters: NLP-based automated information retrieval to generate hypothetical cyberattack scenarios, Journal of Infrastructure Systems, Vol. 30, No. 3, Art. no. 04024008, 2024DOI
3 
S. Vittorio , F. Lunghini , P. Morerio , D. Gadioli , S. Orlandini , P. Silva , J. Martinovic , A. Pedretti , D. Bonanni , A. Del Bue , G. Palermo , G. Vistoli , A. R. Beccari , Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities, Computational and Structural Biotechnology Journal, Vol. 23, pp. 2141-2151, 2024DOI
4 
J. Ohse , B. Hadžić , P. Mohammed , N. L. Peperkorn , M. Danner , A. Yorita , N. Kubota , M. Rätsch , Y. Shiban , Zero-shot strike: Testing the generalisation capabilities of out-of-the-box LLM models for depression detection, Computer Speech & Language, Vol. 88, Art. no. 101663, 2024DOI
5 
K. Kyle , M. Eguchi , Evaluating NLP models with written and spoken L2 samples, Research Methods in Applied Linguistics, Vol. 3, No. 2, Art. no. 100120, 2024DOI
6 
I. H. Sarker , LLM potentiality and awareness: A position paper from the perspective of trustworthy and responsible AI modeling, Discover Artificial Intelligence, Vol. 4, Art. no. 40, 2024DOI
7 
M. N. S. Sabet Jahromi , S. M. Muddamsetty , A. S. S. Jarlner , A. M. Høgenhaug , T. Gammeltoft-Hansen , T. B. Moeslund , SIDU-TXT: An XAI algorithm for NLP with a holistic assessment approach, Natural Language Processing Journal, Vol. 7, Art. no. 100078, 2024DOI
8 
S. Yang , M. N. Zhu , H. Yu , Are artificial intelligence and blockchain the key to unlocking the box of clean energy?, Energy Economics, Vol. 134, Art. no. 107616, 2024DOI
9 
S. Lu , A. Jayaraman , Machine learning for analyses and automation of structural characterization of polymer materials, Progress in Polymer Science, Vol. 153, Art. no. 101828, 2024DOI
10 
A. Zapata Rozo , A. Campo-Archbold , D. Díaz-López , I. Gray , J. Pastor-Galindo , P. Nespoli , F. Gómez Mármol , D. McCoy , Cyber democracy in the digital age: Characterizing hate networks in the 2022 US midterm elections, Information Fusion, Vol. 110, Art. no. 102459, 2024DOI
11 
A. Amyan , M. Abboush , C. Knieke , A. Rausch , Automating fault test cases generation and execution for automotive safety validation via NLP and HIL simulation, Sensors, Vol. 24, No. 10, Art. no. 3145, 2024DOI
12 
L. Torbarina , T. Ferkovic , L. Roguski , V. Mihelcic , B. Sarlija , Z. Kraljevic , Challenges and opportunities of using transformer-based multi-task learning in NLP through ML lifecycle: A position paper, Natural Language Processing Journal, Vol. 7, Art. no. 100076, 2024DOI
13 
K. Denecke , R. May , O. Rivera Romero , Potential of large language models in health care: Delphi study, Journal of Medical Internet Research, Vol. 26, Art. no. e52399, 2024DOI
14 
V. Digumarthi , T. Amin , S. Kanu , J. Mathew , B. Edwards , L. A. Peterson , M. E. Lundy , K. E. Hegarty , Preoperative prediction model for risk of readmission after total joint replacement surgery: A random forest approach leveraging NLP and unfairness mitigation for improved patient care and cost-effectiveness, Journal of Orthopaedic Surgery and Research, Vol. 19, Art. no. 287, 2024DOI
15 
C. Preiksaitis , N. Ashenburg , G. Bunney , A. L. Chu , R. Kabeer , F. Riley , R. Ribeira , C. Rose , The role of large language models in transforming emergency medicine: Scoping review, JMIR Medical Informatics, Vol. 12, Art. no. e53787, 2024DOI
16 
I. Aden , C. H. T. Child , C. C. Reyes-Aldasoro , International Classification of Diseases prediction from MIMIIC-III clinical text using pre-trained ClinicalBERT and NLP deep learning models achieving state of the art, Big Data and Cognitive Computing, Vol. 8, No. 5, Art. no. 47, 2024DOI
17 
J. Zhang , S. Yang , Recommendations for the model-based systems engineering modeling process based on the SysML model and domain knowledge, Applied Sciences, Vol. 14, No. 10, Art. no. 4010, 2024DOI
18 
S. Mehta , R. Karwa , R. Chavan , V. Khatavkar , A. Joshi , Keyphrase extraction using graph-based statistical approach with NLP patterns, Sādhanā, Vol. 49, No. 2, Art. no. 170, 2024DOI
19 
G. Gouy , L. Attali , P. Voillot , P. Fournet , A. Agostini , Experiences of women with medical abortion care reflected in social media (VEILLE study): Noninterventional retrospective exploratory infodemiology study, JMIR Infodemiology, Vol. 4, Art. no. e49335, 2024DOI
20 
R. S. Abdul Kareem , T. Tilford , S. Stoyanov , Fine-grained food image classification and recipe extraction using a customized deep neural network and NLP, Computers in Biology and Medicine, Vol. 175, Art. no. 108528, 2024DOI
21 
A. Presciuttini , A. Cantini , F. Costa , A. Portioli-Staudacher , Machine learning applications on IoT data in manufacturing operations and their interpretability implications: A systematic literature review, Journal of Manufacturing Systems, Vol. 74, pp. 477-486, 2024DOI
22 
A. O. Thunström , H. K. Carlsen , L. Ali , T. Larson , A. Hellström , S. Steingrimsson , Usability comparison among healthy participants of an anthropomorphic digital human and a text-based chatbot as a responder to questions on mental health: Randomized controlled trial, JMIR Human Factors, Vol. 11, Art. no. e54581, 2024DOI
23 
E. Zambetta , N. Razakamanana , A. Robert , F. Clanché , C. Rivera , D. Martin , Z. Hebbache , R. Flicoteaux , E. Coudin , Combining deep neural networks, a rule-based expert system and targeted manual coding for ICD-10 coding causes of death of French death certificates from 2018 to 2019, International Journal of Medical Informatics, Vol. 188, Art. no. 105462, 2024DOI
24 
B. J. Galatzan , E. Johnson , T. Judson , L. Shan , Linguistic dissection of nursing handoffs: Implications for patient safety in varied-acuity hospital settings, Journal of Clinical Nursing, Vol. 33, No. 8, pp. 3077-3088, 2024DOI
25 
V. Torri , M. Ercolanoni , F. Bortolan , O. Leoni , F. Ieva , A NLP-based semi-automatic identification system for delays in follow-up examinations: An Italian case study on clinical referrals, BMC Medical Informatics and Decision Making, Vol. 24, Art. no. 107, 2024DOI
26 
A. Bibal , N. M. Salem , R. Cardon , E. K. White , D. E. Acuna , R. Burke , L. E. Hunter , RecSOI: Recommending research directions using statements of ignorance, Journal of Biomedical Semantics, Vol. 15, Art. no. 2, 2024DOI
27 
M. Pop , A.-L. Klemke , L. Seidler , N. Wernet , P. L. Steudel , V. Baust , E. Wohlmann , R. Fischer , Caenorhabditis elegans neuropeptide NLP-27 enhances neurodegeneration and paralysis in an opioid-like manner during fungal infection, iScience, Vol. 27, No. 4, Art. no. 109484, 2024DOI
28 
T. Al Shloul , T. Mazhar , Q. Abbas , M. Iqbal , Y. Y. Ghadi , T. Shahzad , F. Mallek , H. Hamam , Role of activity-based learning and ChatGPT on students' performance in education, Computers and Education: Artificial Intelligence, Vol. 6, Art. no. 100219, 2024DOI
29 
S. Masoumi , H. Amirkhani , N. Sadeghian , S. Shahraz , Natural language processing (NLP) to facilitate abstract review in medical research: The application of BioBERT to exploring the 20-year use of NLP in medical research, Systematic Reviews, Vol. 13, Art. no. 107, 2024DOI
30 
M. Choaib , M. Garouani , M. Bouneffa , N. Waldhoff , Y. Mohanna , IoT-AID: An automated decision support framework for IoT, SN Computer Science, Vol. 5, Art. no. 429, 2024DOI