UMBC_EBIQUITY-CORE: Semantic Textual Similarity Systems

By Lushan Han, Abhay Lokesh Kashyap, Timothy W. Finin, J. Mayfield, Jonathan Weese. 2013

406 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

An efficient framework for learning sentence representations (2018, methodology): “Models were trained on the 7000novelsof the BookCorpusdataset (Kiros et al., 2015). The dataset consists of about 45M ordered sentences. We also consider a larger corpus for training: the UMBC corpus(Han et al., 2013), a dataset of 100Mweb pages crawledfrom the internet, preprocessedand tokenizedint”
Measuring Data (2022, background): “, 2009), semantic similarity (Han et al., 2013), and semantic coherence (Bommasani and Cardie, 2020b).”
Why We Need New Evaluation Metrics for NLG (2017, methodology): “• Semantic Similarity (SIM): We calculate the Semantic Text Similarity measure designed by Han et al. (2013).”
Advances in Pre-Training Distributed Word Representations (2017, methodology): “Further, we used all news datasets from statmt.org from years 2007 - 2016, the UMBC corpus (Han et al., 2013), the English Gigaword, and Common Crawl from May 2017 4 .”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “• Compared to textual MRs, pictorial MRs elicit texts that are significantly less similar to the underlying MR in terms of semantic text similarity (Han et al. 2013).”
Discovering states and transformations in image collections (2015, methodology): “As in Figure 9(b), we again use semantic similarity scores obtained from [12].”
Crowd-sourcing NLG Data: Pictures Elicit Better Data. (2016, methodology): “In particular, we calculated a similarity score between the provided MR and the collected utterance, using the UMBC Semantic Text Similarity measure provided by (Han et al., 2013), which ranked top in the *SEM 2013 Semantic Textual Sim- ilarity shared task.”
PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification (2015, methodology): “It has been used for recognizing textual entailment (Beltagy et al., 2014; Bjerva et al., 2014), measuring the semantic similarity of texts (Han et al., 2013; Ji and Eisenstein, 2013; Sultan et al., 2014b), mono-lingual alignment (Yao et al., 2013; Sultan et al., 2014a), natural language generation…”
RUSE: Regressor Using Sentence Embeddings for Automatic Machine Translation Evaluation (2018, methodology): “Quick-Thought is a collection of 4800-dimensional sentence embeddings trained on both 45 million sentences of the BookCorpus dataset (Zhu et al., 2015) and 129 million sentences of the UMBC corpus (Han et al., 2013).”
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training (2016, methodology): “We use a 300M-words corpus from the UMBC project (Han et al., 2013), which contains English paragraphs extracted from the web.”
Towards Robust Toxic Content Classification (2019, methodology): “We train our denoising autoencoder on a random subset of the UMBC webbase corpus (Han et We note that this approach does require knowledge of what character-level perturbations will be applied.”
DLS@CU: Sentence Similarity from Word Alignment and Semantic Vector Composition (2015, background): “Interestingly, the best systems at these two events were unsupervised (Han et al., 2013; Sultan et al., 2014b); some super-”
BIT at SemEval-2017 Task 1: Using Semantic Information Space to Evaluate Semantic Textual Similarity (2017, methodology): “For a long time, IC related methods were usually used as word similarity (Resnik, 1995; Jiang and Conrath, 1997; Lin, 1997) or word weight (Li et al., 2006; Han et al., 2013) rather than the core evaluation modules of sentence similarity methods (Wu and Huang, 2016).”
LIPN-IIMAS at SemEval-2017 Task 1: Subword Embeddings, Attention Recurrent Neural Networks and Cross Word Alignment for Semantic Textual Similarity (2017, methodology): “In an attempt to follow these statements and also inspired by success obtained by authors like Han et al. (2013) and Rychalska et al. (2016), we implemented a word alignment system.”
Samsung Poland NLP Team at SemEval-2016 Task 1: Necessity for diversity; combining recursive autoencoders, WordNet and ensemble methods to measure semantic similarity. (2016, background): “The concept of semantic similarity reﬂects the work of (Han et al., 2013), while out-of-context words and disjoint similar concepts reﬂect the ideas presented in (Han et al., 2015), but there are differences in both implementation and usage.”
Using Summarization to Discover Argument Facets in Online Idealogical Dialog (2017, methodology): “Our scale and MT task for AFS was inspired by the STS task and definition.”
FCICU at SemEval-2017 Task 1: Sense-Based Language Independent Semantic Textual Similarity Approach (2017, methodology): “Many of those methods were very successful and were among the top performing methods during the last years of SemEval 2013-2016 (Han et al., 2013; Han et al., 2015; Hänig et al., 2015; Sultan et al., 2014a; Sultan et al., 2014b; Sultan et al., 2015).”
Domain-specific Knowledge Extraction from the Web of Data (2018, methodology): “The similarity between domain term and the topics extracted is calculated using two most prominent state-of-the-art techniques; 1) word2vec similarity [Mikolov et al. 2013]: embedding-based semantic similarity measure and 2) UMBC similarity [Han et al. 2013]: hybrid semantic similarity measure.”