Create README.md

README.md

@@ -0,0 +1,148 @@
+# Denotational Type Classifier
+
+This model classifies the denotational relation between two word senses, represented as a pair of definitions. It is based on `roberta-large` with a sequence-classification head and is trained for lexical-semantic relation classification.
+
+The model predicts one of the following relation types:
+
+* `generalization`
+* `specialization`
+* `metaphor`
+* `metonymy`
+* `homonymy`
+* `antonymy`
+
+The first five labels correspond to the denotational relation types evaluated in SenseRel. `antonymy` is included because it is present in the fine-tuning data, although it is not part of the expert-annotated SenseRel denotational test set.
+
+## Model Details
+
+* **Model type:** RoBERTa-large sequence classifier
+* **Base model:** `roberta-large`
+* **Task:** Denotational relation classification between word-sense definitions
+* **Input:** Two sense definitions for the same lexical item
+* **Output:** A denotational relation label
+* **Language:** English
+
+## Intended Use
+
+This model is intended for research on lexical semantics, semantic change, polysemy, and sense-level semantic relations. It can be used to classify the relation between two definitions of a word sense, for example whether a newer meaning is a generalization, specialization, metaphorical extension, metonymic extension, homonym, or antonymic development of another meaning.
+
+Example use cases include:
+
+* studying semantic change in dictionaries or lexical resources;
+* analyzing polysemous word senses;
+* supporting sense-level semantic annotation;
+* scaling exploratory studies of denotational change.
+
+The model is not intended for high-stakes decision-making or for general-purpose natural language understanding outside lexical-semantic relation classification.
+
+## Input Format
+
+The model expects a pair of definitions. In the experiments, definitions were concatenated and passed to the classifier.
+
+Example:
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+
+model_id = "YOUR_ORG/YOUR_MODEL_NAME"
+
+classifier = pipeline(
+    "text-classification",
+    model=model_id,
+    tokenizer=model_id
+)
+
+definition_1 = "the young of the domestic cow"
+definition_2 = "the young of various large mammals"
+
+text = definition_1 + " </s></s> " + definition_2
+classifier(text)
+```
+
+Expected output:
+
+```python
+[{"label": "generalization", "score": 0.XX}]
+```
+
+## Training Data
+
+The model was fine-tuned on a combined denotational-relation dataset referred to as `WN+CN+UM`, constructed from existing lexical-semantic resources:
+
+* ChainNet for metaphor, metonymy, and homonymy relations;
+* UniMet for additional metonymy examples;
+* WordNet-based hypernym/hyponym pairs for generalization and specialization;
+* auto-antonymy examples where available in the fine-tuning data.
+
+These resources use definition or synset-pair information as proxies for relations between word senses.
+
+## Training Procedure
+
+Definitions were concatenated and passed through `roberta-large`. A linear classification layer followed by a softmax activation was added on top to predict the relation label.
+
+Training setup:
+
+* maximum epochs: 10
+* batch size: 8
+* learning-rate schedule: linear
+* warm-up: 10% of total training steps
+* learning-rate search: `{1e-4, 2e-4, 1e-5, 2e-5, 1e-6}`
+* model selection: best weighted F1 on the development set
+* selected learning rate: `1e-6`
+
+## Evaluation
+
+The model was evaluated on:
+
+1. the `WN+CN+UM` test set;
+2. the SenseRel expert-annotated denotational dataset.
+
+| Dataset                       | Weighted F1 |
+| ----------------------------- | ----------: |
+| WN+CN+UM test set             |       0.734 |
+| SenseRel denotational dataset |       0.684 |
+
+On the SenseRel denotational dataset, this model achieved the best reported score among the evaluated systems.
+
+## Limitations
+
+The model should be used with the following limitations in mind:
+
+* It operates on definition pairs, not full diachronic corpus evidence.
+* Training data uses lexical-resource relations as proxies for sense-level semantic change.
+* The distinction between `generalization` and `specialization` is direction-sensitive and depends on the order of the input senses.
+* Taxonomical relations such as `generalization` and `specialization` may be confused with one another.
+* Figurative relations such as `metaphor` and `metonymy` can be difficult to separate, especially when senses are abstract or weakly related.
+* `homonymy` is challenging because the model must distinguish true unrelatedness from distant semantic extension.
+* The model was developed and evaluated for English noun sense definitions; performance may degrade on other parts of speech, languages, domains, or informal text.
+
+## Bias, Risks, and Ethical Considerations
+
+This model reflects the structure and assumptions of the lexical resources and annotation schemes used for training and evaluation. It may encode biases present in dictionary definitions, lexical databases, and historical semantic descriptions. Its predictions should be treated as linguistic classifications, not as definitive etymological or historical claims.
+
+For scholarly use, model outputs should be validated by domain experts, especially when used to support claims about semantic change.
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@inproceedings{cassotti-etal-2026-senserel,
+    title = "{S}ense{R}el: A Sense-Level Benchmark for Denotational and Connotational Meaning Relations",
+    author = "Cassotti, Pierluigi and
+      Baes, Naomi and
+      De Pascale, Stefano and
+      de S{\'a}, J{\'a}der Martins Camboim and
+      Periti, Francesco and
+      Haslam, Nick and
+      Geeraerts, Dirk and
+      Tahmasebi, Nina",
+    booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
+    month = jul,
+    year = "2026",
+    address = "San Diego, California, United States",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2026.acl-long.20/",
+    pages = "499--515"
+}
+```