In this paper, we adopt a relational view of analogies applied to Semantic Role Classification in FrameNet. We define analogies as formal relations over the Cartesian product of frame evoking lexical units (LUs) and frame element (FEs) pairs, which we use to construct a new dataset. Each element of this binary relation is labelled as a valid analogical instance if the frame elements share the same semantic role, or as invalid otherwise. This formulation allows us to transform Semantic Role Classification into binary classification and train a lightweight Artificial Neural Network (ANN) that exhibits rapid convergence with minimal parameters. Unconventionally, no Semantic Role information is introduced to the neural network during training. We recover semantic roles during inference by computing probability distributions over candidates of all semantic roles within a given frame through random sampling and analogical transfer. This approach allows us to surpass previous state-of-the-art results while maintaining computational efficiency and frugality.
Figures & tables
Figure 1: An example of an annotated sentence for the frame type triggered by decline.v .
Dataset
N. sents
N. frames
N. docs
All
27,228
796
101
train
18,772
754
70
dev
2,192
368
8
test
6,264
563
23
Table 1: The number of sentences, frames, and documents in the datasets
Dataset
all
positive
negative
train
7,638,128
3,036,470
4,601,658
train_balanced
6,072,940
3,036,470
3,036,470
dev
154,802
72,290
82,512
test
984,724
397,880
586,844
Table 2: Number of analogical instances
Figure 2: Architecture of our pipeline
Figure 3: Training statistics wrt checkpoints
Label
0 (negative)
1(positive)
Precision
91.80
86.03
Recall
90.18
88.23
F1 score
90.98
87.12
Accuracy
89.39
Table 3: Scores of the binary analogy model (in %)
Figure 4: Semantic parsing workflows with two distinct semantic role classifiers
Frame id.
Arg id.
SR cl.
Accuracy
Lin et al.
Lin et al.
Lin et al.
48.95
Lin et al.
Lin et al.
Ours
49.81
Table 4: Overall performance of state-of-the-art end-to-end parser vs ours on FrameNet 1.7
Frame id.
Arg id.
SR cl.
Accuracy
gold
Swayamdipta et al.
Swayamdipta et al.
58.46
gold
Swayamdipta et al.
Ours
59.35
Table 5: Overall performance of former state-of-the-art SRL approach vs ours on FrameNet 1.7
Precision
Recall
F1 score
Accuracy
Ours
80.77
79.26
79.17
79.30
Baseline 1 ( et )
-
-
-
9.14
Baseline 2 ( pt,et )
-
-
-
20.64
Table 6: Baseline evaluation results on FrameNet 1.7 test set with gold frame and spans, using the exact same architecture as our approach. Precision, recall, and F1 scores are weighted.
Analogical reasoning studies how systems transfer relations and solutions between situations with shared structure, enabling inference beyond direct examples.
Semantic Role Labeling (SRL) provides an explicit representation of predicate-argument structure, capturing linguistically grounded relations such as who did what to whom. While recent NLP progress has been dominated by large language models (LLMs), these systems often rely on implicit semantic representations, often lacking explicit structural constraints and systematic explanatory mechanisms. Traditionally, SRL systems have often relied on AllenNLP; however, the framework entered maintenance mode in December 2022, limiting compatibility with evolving encoder architectures and modern inference requirements. We revisit structured SRL modeling, introducing a modernized encoder-based framework that preserves explicit predicate-argument structure while enabling inference 10 times faster. Using BERT-base, the model attains comparable predictive performance, and RoBERTa and DeBERTa further improve F1 performance within the same framework. We adopt a dependency-informed diagnostic methodology to characterize span-level inconsistencies and conduct a representation-level analysis of LLM behavior under dependency-informed structural signals. Results indicate that dependency cues primarily improve structural stability. Finally, we illustrate how the framework's explicit predicate-argument structure can support multilingual SRL projection as a downstream application.
Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal analogy generation lack an interpretable measure of whether this structure is understood and maintained in the generated output. We address this gap with Pullback Refinement via Interpretable Structural Mapping (PRISM), a modality-agnostic framework for measuring and improving relational alignment in multimodal analogies, evaluated on visual metaphor generation. PRISM represents analogies as explicit relational mappings grounded in category theory and uses VLMs to instantiate these structures across modalities. Its first component, the pullback score, quantifies relational alignment from the resulting graph representation. On the AnaloBench benchmark, selecting the correct analogy purely by pullback score achieves 82.5% accuracy, demonstrating that the score captures meaningful relational information. PRISM's second component is an iterative refinement loop that uses the pullback score as an in-context feedback signal to iteratively revise the generated image towards greater relational depth. VLM-as-a-judge and human evaluations show that PRISM consistently improves metaphor consistency and analogy appropriateness over zero- shot generation, with human participants preferring the refined output in 57.65% of pairwise comparisons. However, a qualitative analysis reveals that refinement can favour visually crowded compositions rather than genuinely deeper relational correspondences.
Explicit representations of predicate-argument relations form the basis of interpretable semantic analysis, supporting reasoning, generation, and evaluation. However, attaining such semantic structures requires costly annotation efforts and has remained largely confined to English. We leverage the Question-Answer driven Semantic Role Labeling (QA-SRL) framework -- a natural-language formulation of predicate-argument relations -- as the foundation for extending semantic annotation to new languages. To this end, we introduce a cross-linguistic projection approach that reuses an English QA-SRL parser within a constrained translation and word-alignment pipeline to automatically generate question-answer annotations aligned with target-language predicates. Applied to Hebrew, Russian, and French -- spanning diverse language families -- the method yields high-quality training data and fine-tuned, language-specific parsers that outperform strong multilingual LLM baselines (GPT-4o, LLaMA-Maverick). By leveraging QA-SRL as a transferable natural-language interface for semantics, our approach enables efficient and broadly accessible predicate-argument parsing across languages.
Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein +3