شماره ركورد كنفرانس :
3297
عنوان مقاله :
Eigenvalue Based Features For Semantic Sentence Similarity
عنوان به زبان ديگر :
Eigenvalue Based Features For Semantic Sentence Similarity
پديدآورندگان :
Vardasbi Ali School of Electrical and Computer Engineering - College of Engineering University of Tehran Tehran , Faili Heshaam School of Electrical and Computer Engineering - College of Engineering University of Tehran Tehran , Asadpour Masoud School of Electrical and Computer Engineering - College of Engineering University of Tehran Tehran
كليدواژه :
Word Embedding , Eigenvalue Decomposition , Semantic Similarity , Sentence Similarity
عنوان كنفرانس :
نوزدهمين سمپوزيوم بين المللي هوش مصنوعي و پردازش سيگنال
چكيده لاتين :
Due to its increasing importance, the semantic sentence
similarity is getting more attention among natural language
processing researchers during recent years. To the best of our
knowledge, previous studies on the task have not exploited the
eigenvalue analysis on their systems. In this paper we approach
the sentence similarity task through eigenvalue analysis. We will
propose a simple but efficient new aligner and introduce three new
features for the task. Two of our proposed features are based on
the eigenvalue analysis. Finally, we will show the significance of
our proposed aligner and features through experiments.
Specifically, we will show that our features outperform the
STS2015 benchmarks for semantic sentence similarity.
