Small fixes in README

README.md

@@ -13,7 +13,7 @@ widget:
 - text: "He ate a sweet apple. What is the definition of apple?"
   example_title: "Definition generation"
 - text: "The paper contains a number of original ideas about color perception. What is the definition of original?"
-  example_title: "Definiton generation"
+  example_title: "Definition generation"
 license: cc-by-sa-4.0
 datasets:
 - marksverdhei/wordnet-definitions-en-2021
@@ -34,7 +34,7 @@ See details in the paper `Interpretable Word Sense Representations via Definitio
 
 The model is intended for research purposes, as a source of contextualized dictionary-like lexical definitions.
 
-The fine-tuning datasets were limited to English
+The fine-tuning datasets were limited to English.
 Although the original FLAN-T5 is a multilingual model, we did not thoroughly evaluate its ability to generate definitions in languages other than English. 
 
 Generated definitions can contain all sorts of biases and stereotypes, stemming from the underlying language model.
@@ -47,12 +47,12 @@ Three datasets were used to fine-tune the model:
 - *Oxford dictionary or CHA* ([Gadetsky et al., ACL 2018](https://aclanthology.org/P18-2043/))
 - English subset of *CodWoE* ([Mickus et al., SemEval 2022](https://aclanthology.org/2022.semeval-1.1/))
 
-FLAN-T5-Definition XL achieves the following results on the WordNet test set ([Ishiwatari et al., NAACL 2019](https://aclanthology.org/N19-1350/)):
+FLAN-T5-Definition XL achieves the following results on the WordNet test set:
 - ROUGE-L: 52.21
 - BLEU: 32.81
 - BERT-F1: 92.16
 
-FLAN-T5-Definition XL achieves the following results on the Oxford dictionary test set ([Gadetsky et al., ACL 2018](https://aclanthology.org/P18-2043/)):
+FLAN-T5-Definition XL achieves the following results on the Oxford dictionary test set:
 - ROUGE-L: 38.72
 - BLEU: 18.69
 - BERT-F1: 89.75