UKP: Computing Semantic Textual Similarity by Combining Multiple Content Similarity Measures

By Daniel Bär, Chris Biemann, Iryna Gurevych, Torsten Zesch. 2012

232 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, methodology): “Early methods focused on lexical semantics, surface form matching and basic syntactic similarity (Bär et al., 2012; Šarić et al., 2012a; Jimenez et al., 2012a).”
Learning Semantic Textual Similarity from Conversations (2018, methodology): “Early methods focused on lexical semantics, surface form matching and basic syntactic similarity (Bär et al., 2012; Jimenez et al., 2012).”
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015, neutral): “8037 Beltagy et al. (2014) 0.”
Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016, background): “Systems in the competition are ranked by the weighted mean (the of-943 Model Pearson’s r Beltagy et al. (2014) 0.8300 B¨ar et al. (2012) 0.8730 ˇSari´c et al. (2012) 0.8803 He et al. (2015) 0.9090 This work 0.9112 (Kashyap et al., 2014), 3rd (Lynum et al., 2014) systems in the STS2014 competition,…”
ECNU: One Stone Two Birds: Ensemble of Heterogenous Measures for Semantic Relatedness and Textual Entailment (2014, methodology): “Existing work on STS can be divided into 4 categories according to the similarity measures used (Gomaa and Fahmy, 2013): (1) string-based method (Bär et al., 2012; Malakasiotis and Androutsopoulos, 2007) which calculates similarities using surface strings at either character level or word level;…”
In Defense of Word Embedding for Generic Text Representation (2015, background): “When taking log scale of the similarities, it seems to outperform [3] on the msr-par benchmark but not on the other two.”
SemEval-2013 Task 7: The Joint Student Response Analysis and 8th Recognizing Textual Entailment Challenge (2013, methodology): “The UKP-BIU system is a hybrid of two semantic relationship approaches, namely (i) computing semantic textual similarity by combining multiple content similarity measures (B¨ar et al., 2012), and (ii) recognizing textual entailment with BIUTEE (Stern and Dagan, 2011).”
Short Text Similarity with Word Embeddings (2015, methodology): “In [29] features are calculated from aggregated similarity measures based on named entity recognition with WordNet and Levenshtein distance, higher order word co-occurrence similarity, the RelEx system, dependency trees and reused features of SemEval 2012 participants.”
DKPro Similarity: An Open Source Framework for Text Similarity (2013, methodology): “Intrinsic Evaluation DKPro Similarity contains the setup (Bär et al., 2012a) which participated in the Semantic Textual Similarity (STS) Task at SemEval-2012 (Agirre et al.”
BIT at SemEval-2017 Task 1: Using Semantic Information Space to Evaluate Semantic Textual Similarity (2017, background): “, 2014b; Wu and Huang, 2016), some of which are appeared for a long time when there wasn’t enough training data; The other kind is supervised systems (Bär et al., 2012; Šarić et al., 2012; Sultan et al., 2015; Rychalska et al., 2016; Brychcı́n and Svoboda, 2016) applying machine learning algorithms,”
Referential Translation Machines for Predicting Translation Quality (2014, background): “• Character n-grams {5}: Calculates cosine between character n-grams (for n=2,3,4,5,6) obtained for S and T (Bär et al., 2012).”
Learning Semantic Textual Similarity with Structural Representations (2013, methodology): “We adopt similarity features from two best performing systems of STS-2012, which were publicly released 1 : namely, the Takelab 2 system (ˇSari´c et al., 2012) and the UKP Lab’s system 3 (Bar et al., 2012).”
DLS@CU: Sentence Similarity from Word Alignment and Semantic Vector Composition (2015, methodology): “, 2012) and consequently, supervised systems were the most successful (Bär et al., 2012; Šarić et al., 2012).”
*SEM 2013 shared task: Semantic Textual Similarity (2013, methodology): “Although not mentioned in the descriptions ﬁles, some systems used the publicly available DKPro and Takelab systems.”
UWB at SemEval-2016 Task 1: Semantic Textual Similarity using Lexical, Syntactic, and Semantic Information (2016, methodology): “This section describes various techniques for estimating the text similarity.”
The Eras and Trends of Automatic Short Answer Grading (2015, methodology): “Examples are the work by Bär et al. (2011) (2012a) (2013), Burrows et al. (2013) and Potthast (2011) on text similarity and paraphrasing, and evaluation competition work by Bär et al. (2012b) on computing text similarity.”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “The features below are largely inspired by the feature sets used by the top performing system [14] in Semantic Textual Similarity (STS) task [2].”