Sentence Similarity

44 papers with code • 1 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?


Most implemented papers

SentEval: An Evaluation Toolkit for Universal Sentence Representations

facebookresearch/SentEval LREC 2018

We introduce SentEval, a toolkit for evaluating the quality of universal sentence representations.

Calculating the similarity between words and sentences using a lexical database and corpus statistics

nihitsaxena95/sentence-similarity-wordnet-sementic 15 Feb 2018

To calculate the semantic similarity between words and sentences, the proposed method follows an edge-based approach using a lexical database.

On the Effect of Dropping Layers of Pre-trained Transformer Models

hsajjad/transformers 8 Apr 2020

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments.

Generating Sentences by Editing Prototypes

kelvinguu/neural-editor TACL 2018

We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence.

Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

percyliang/sempre EMNLP 2017

To learn a semantic parser from denotations, a learning algorithm must search over a combinatorially large space of logical forms for ones consistent with the annotated denotations.

Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations

sidak/context-mover-distance-and-barycenters 29 Aug 2018

We present a framework for building unsupervised representations of entities and their compositions, where each entity is viewed as a probability distribution rather than a vector embedding.

NeuralWarp: Time-Series Similarity with Warping Networks

josifgrabocka/neuralwarp 20 Dec 2018

Research on time-series similarity measures has emphasized the need for elastic methods which align the indices of pairs of time series and a plethora of non-parametric have been proposed for the task.

Sentence Similarity Learning by Lexical Decomposition and Composition

Leputa/CIKM-AnalytiCup-2018 COLING 2016

Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences.

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus

imatge-upc/vqa-2016-cvprw ACL 2016

Over the past decade, large-scale supervised learning corpora have enabled machine learning researchers to make substantial advances.