paper-with-me

Papers

Generating Paraphrases with Lean Vocabulary

2019-10-01 · WS 2019 10 · Tadashi Nomoto

In this work, we examine whether it is possible to achieve the state of the art performance in paraphrase generation with reduced vocabulary. Our approach consists of building a convolution to sequence model (Conv2Seq) partially guided by the reinforcement learning, and training it on the subword representation of the input. The experiment on the Quora dataset, which contains over 140,000 pairs of sentences and corresponding paraphrases, found that with less than 1,000 token types, we were able to achieve performance which exceeded that of the current state of the art.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Paraphrase Generationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

2019-08-28 · IJCNLP 2019 11 · Wanyu Du, Yangfeng Ji

Generating paraphrases from given sentences involves decoding words step by step from a large vocabulary. To learn a decoder, supervised learning which maximizes the likelihood of tokens always suffers from the exposure …

DecoderImitation LearningParaphrase Generationreinforcement-learning+2

Towards Human Understanding of Paraphrase Types in ChatGPT

2024-07-02 · Dominik Meier, Jan Philip Wahle, Terry Ruas, Bela Gipp

Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpr…

Sentence

Generating Syntactic Paraphrases

2018-10-01 · EMNLP 2018 10 · Emilie Colin, Claire Gardent

We study the automatic generation of syntactic paraphrases using four different models for generation: data-to-text generation, text-to-text generation, text reduction and text expansion, We derive training data for each…

Data-to-Text GenerationMachine TranslationParaphrase GenerationQuestion Answering+3

Metaphoric Paraphrase Generation

2020-02-28 · Kevin Stowe, Leonardo Ribeiro, Iryna Gurevych

This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two different models for this task: a lexical…

Paraphrase GenerationSentence

Generating Paraphrases from DBPedia using Deep Learning

2016-09-01 · WS 2016 9 · Amin Sleimi, Claire Gardent
Deep LearningLanguage ModelingLanguage ModellingText Generation