Add causal span model (mDeBERTa-v3 BIO tagger)

README.md

@@ -7,8 +7,18 @@ tags:
 - cause-effect
 - span-extraction
 - causal-news-corpus
+- multilingual
 language:
 - en
+- es
+- fr
+- de
+- pt
+- tr
+- ru
+- ar
+- zh
+- ja
 ---
 
 # causal-span-pointer-mdeberta
@@ -59,12 +69,29 @@ print(predict_sentence(model, tokenizer, "Heavy rainfall caused severe flooding.
 `<ARG0>` = cause, `<ARG1>` = effect, `<SIG0>` = signal. The prediction is a list of
 tagged relation strings (up to two per sentence).
 
+### Multilingual
+
+Trained on English spans, but multilingual at inference (mDeBERTa encoder +
+script-aware segmentation). Use `predict_relations`, which returns character-exact
+spans in any script:
+
+```python
+from causal_span_model.pointer.infer import predict_relations
+
+predict_relations(model, tokenizer, "暴雨导致该地区发生严重洪灾。")
+# [{'cause': '暴雨', 'effect': '该地区发生严重洪灾', 'signal': '导致'}]
+predict_relations(model, tokenizer, "Las fuertes lluvias provocaron inundaciones.")
+# [{'cause': 'Las fuertes lluvias', 'effect': 'inundaciones', 'signal': 'provocaron'}]
+```
+
+Verified on es/fr/de/pt/tr/ru/ar and CJK (zh/ja).
+
 ## Notes
 
-- Trained on English CNC; not tuned for multilingual span extraction (for robust
-  multilingual zero-shot, see the BIO sibling model).
 - It is NOT compatible with a generic token-classification ONNX consumer -- it
   needs its own start/end + beam-search decoder (provided by the package).
+- It is a span EXTRACTOR that assumes the input is causal (no causal/non-causal
+  gate), so gate it before feeding arbitrary text.
 
 ## License