Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

TSRCDF-SS structure diagram.

The TSRCDF-SS structure diagram includes a dual encoders, and the improved classifier combines sequential transfer and cross-domain transfer.

More »

Fig 1 Expand

Fig 2.

Encoder t-SNE dimensionality reduction projection.

Comparison of sentence embedding performance of different encoders and combined encoders using t-SNE dimensionality reduction projection. This visualization highlights the differences in encoding capabilities of different encoders. The dataset used is TRAINNLI.

More »

Fig 2 Expand

Fig 3.

Software requirement pair encoding model based on SBERT and SimCSE.

Use the SBERT model and SimCSE model to encode individual requirements to obtain their respective embeddings. Then these embeddings are fused to finally obtain the six-element concatenated embedding result.

More »

Fig 3 Expand

Fig 4.

The pseudocode of fusion algorithm of sequential transfer and cross-domain transfer.

More »

Fig 4 Expand

Table 1.

Operating parameters of the model used in the experiment.

More »

Table 1 Expand

Fig 5.

Comparison of encoder combination results.

Precision, recall and F1 of different encoder combination experiments on TRAINNLI (30000) dataset.

More »

Fig 5 Expand

Fig 6.

Comparison of results of fully connected layers with different numbers of layers.

Results of comparative experiments on different numbers of FFNN layers on the TRAINNLI (30000) dataset.

More »

Fig 6 Expand

Fig 7.

t-SNE visualization of feature embeddings on the CDN dataset at different stages of the FFNN classifier.

(a) input embeddings before the fully connected layers, (b) embeddings after one fully connected layer, and (c) embeddings after two fully connected layers.

More »

Fig 7 Expand

Fig 8.

Comparison of results of different loss functions.

The results of the experiment using a two-layer FFNN and different loss functions on the TRAINNLI (30000) dataset.

More »

Fig 8 Expand

Table 2.

The improvement effect of different datasets on the improved model is evaluated, and ablation comparison experiments are performed on the TRAINNLI (30000) dataset (Unit:%).

More »

Table 2 Expand

Table 3.

Performance evaluation results on the TRAINNLI (30000) dataset (Unit:%).

More »

Table 3 Expand

Table 4.

Evaluation of cross-domain models trained with different combinations of requirement pair datasets (Unit:%).

More »

Table 4 Expand

Fig 9.

Representative confusion matrices for cross-domain requirement conflict detection.

These two examples correspond to (a) the WorldVista case, where the target domain data distribution is moderately imbalanced, and (b) the OPENCOSS case, where it is extremely imbalanced. These confusion matrices are reported to illustrate typical patterns under cross-domain transfer rather than to exhaustively characterize all source–target configurations.

More »

Fig 9 Expand