Automated Paraphrase Quality Assessment Using Recurrent Neural Networks and Language Models [Konferenzbericht] Paper presented at the International Conference on Intelligent Tutoring Systems (17th, Athens, Greece, Jul 9, 2021).

Autor/inn/en	Nicula, Bogdan; Dascalu, Mihai; Newton, Natalie; Orcutt, Ellen; McNamara, Danielle S.
Titel	Automated Paraphrase Quality Assessment Using Recurrent Neural Networks and Language Models [Konferenzbericht] Paper presented at the International Conference on Intelligent Tutoring Systems (17th, Athens, Greece, Jul 9, 2021).
Quelle	(2021), (9 Seiten) PDF als Volltext (1); PDF als Volltext kostenfreie Datei (2) Verfügbarkeit
Zusatzinformation	Weitere Informationen
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Phrase Structure; Networks; Semantics; Feedback (Response); Syntax; Computational Linguistics; Language Usage; Models; Teaching Methods; Classification; Artificial Intelligence; Linguistic Input; Intelligent Tutoring Systems; Natural Language Processing; Literacy Education; Elementary School Students + Suchen Sie Ihr Suchwort? Phrasenstruktur; Semantik; Linguistics; Computerlinguistik; Sprachgebrauch; Analogiemodell; Teaching method; Lehrmethode; Unterrichtsmethode; Classification system; Klassifikation; Klassifikationssystem; Künstliche Intelligenz; Sprachbildung; Intelligentes Tutorsystem; Natürliche Sprache
Abstract	The ability to automatically assess the quality of paraphrases can be very useful for facilitating literacy skills and providing timely feedback to learners. Our aim is twofold: a) to automatically evaluate the quality of paraphrases across four dimensions: lexical similarity, syntactic similarity, semantic similarity and paraphrase quality, and b) to assess how well models trained for this task generalize. The task is modeled as a classification problem and three different methods are explored: (a) manual feature extraction combined with an Extra Trees model, (b) GloVe embeddings and a Siamese neural network, and (c) using a pre-trained BERT model fine-tuned on our task. Starting from a dataset of 1998 paraphrases from the User Language Paraphrase Corpus (ULPC), we explore how the three models trained on the ULPC dataset generalize when applied on a separate, small paraphrase corpus based on children inputs. The best out-of-the-box generalization performance is obtained by the Extra Trees model with at least 75% average F1-scores for the three similarity dimensions. We also show that the Siamese neural network and BERT models can obtain an improvement of at least 5% after fine-tuning across all dimensions. (As Provided).
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01