Update README.md

README.md

@@ -5,7 +5,7 @@ license: apache-2.0
 ---
 
 # mFLAG
-mFLAG is a sequence-to-sequence model for multi-figurative language generation. It was introduced in the paper [Multi-Figurative Language Generation]() paper by Huiyuan Lai and Malvina Nissim.
+mFLAG is a sequence-to-sequence model for multi-figurative language generation. It was introduced in the paper [Multi-Figurative Language Generation](laihuiyuan/mFLAG) paper by [Huiyuan Lai](https://laihuiyuan.github.io/) and [Malvina Nissim](https://scholar.google.nl/citations?user=hnTpEOAAAAAJ&hl=en).
 
 # Model description
 mFLAG is a sequence-to-sequence model for multi-figurative language generation. It is trained by employing a scheme for multi-figurative language pre-training on top of BART, and a mechanism for injecting the target figurative information into the encoder; this enables the generation of text with the target figurative form from another figurative form without parallel figurative-figurative sentence pairs.
@@ -20,16 +20,14 @@ cd mFLAG
 ```python
 from model import MultiFigurativeGeneration
 from tokenization_mflag import MFlagTokenizerFast
-
-tokenizer = MFlagTokenizerFast.from_pretrained('checkpoints/mFLAG')
-model = MultiFigurativeGeneration.from_pretrained('checkpoints/mFLAG')
+tokenizer = MFlagTokenizerFast.from_pretrained('laihuiyuan/mFLAG')
+model = MultiFigurativeGeneration.from_pretrained('laihuiyuan/mFLAG')
 
 # hyperbole to sarcasm
-inp_id = tokenizer.encode("<hyperbole> I am not happy that he urged me to finish all the hardest tasks in the world", return_tensors="pt")
-fig_id = tokenizer.encode("<sarcasm>", add_special_tokens=False, return_tensors="pt")
-
-outs = model.generate(input_ids=inp_id[:, 1:], fig_ids=fig_id, forced_bos_token_id=fig_id.item())
-text = tokenizer.decode(outs[0].tolist(), skip_special_tokens=True, clean_up_tokenization_spaces=False)
+inp_ids = tokenizer.encode("<hyperbole> I am not happy that he urged me to finish all the hardest tasks in the world", return_tensors="pt")
+fig_ids = tokenizer.encode("<sarcasm>", add_special_tokens=False, return_tensors="pt")
+outs = model.generate(input_ids=inp_ids[:, 1:], fig_ids=fig_ids, forced_bos_token_id=fig_ids.item(), num_beams=5, max_length=60,)
+text = tokenizer.decode(outs[0, 2:].tolist(), skip_special_tokens=True, clean_up_tokenization_spaces=False)
 ```
 
 # Citation Info