DeepAI AI Chat
Log In Sign Up

Generating Sentences by Editing Prototypes

09/26/2017
by   Kelvin Guu, et al.
Stanford University
0

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. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/19/2015

Generating Sentences from a Continuous Space

The standard recurrent neural network language model (RNNLM) generates s...
04/15/2021

Sentence-Permuted Paragraph Generation

Generating paragraphs of diverse contents is important in many applicati...
04/19/2018

Incorporating Pseudo-Parallel Data for Quantifiable Sequence Editing

In the task of quantifiable sequence editing (QuaSE), a model needs to e...
07/03/2020

Interpretable Sequence Classification Via Prototype Trajectory

We propose a novel interpretable recurrent neural network (RNN) model, c...
06/19/2018

Response Generation by Context-aware Prototype Editing

Open domain response generation has achieved remarkable progress in rece...
06/17/2020

Iterative Edit-Based Unsupervised Sentence Simplification

We present a novel iterative, edit-based approach to unsupervised senten...
05/17/2021

Sentence Similarity Based on Contexts

Existing methods to measure sentence similarity are faced with two chall...