paper-with-me

홈 › Papers

Multilingual Paraphrase Generation For Bootstrapping New Features in Task-Oriented Dialog Systems

2021-11-01 · EMNLP (NLP4ConvAI) 2021 11 · Subhadarshi Panda, Caglar Tirkaz, Tobias Falke, Patrick Lehnen

The lack of labeled training data for new features is a common problem in rapidly changing real-world dialog systems. As a solution, we propose a multilingual paraphrase generation model that can be used to generate novel utterances for a target feature and target language. The generated utterances can be used to augment existing training data to improve intent classification and slot labeling models. We evaluate the quality of generated utterances using intrinsic evaluation metrics and by conducting downstream evaluation experiments with English as the source language and nine different target languages. Our method shows promise across languages, even in a zero-shot setting where no seed data is available.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

intent-classificationIntent ClassificationMultilingual Paraphrase GenerationParaphrase Generation

Similar Papers 제목 키워드 기반

Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity

2020-08-11 · WMT (EMNLP) 2020 11 · Brian Thompson, Matt Post

Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting t…

DiversityMachine TranslationNMTParaphrase Generation+4

Unsupervised Text Generation by Learning from Search

2020-07-09 · NeurIPS 2020 12 · Jingjing Li, Zichao Li, Lili Mou, Xin Jiang 외

In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search. We start by applying a strong search algorithm (in particular, simulated annealing) towards a heuristically define…

Paraphrase GenerationText Generation

Multilingual Lexical Simplification via Paraphrase Generation

2023-07-28 · Kang Liu, Jipeng Qiang, Yun Li, Yunhao Yuan 외

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these m…

DiversityLexical SimplificationMachine TranslationParaphrase Generation+2

Measuring Semantic Abstraction of Multilingual NMT with Paraphrase Recognition and Generation Tasks

2018-08-21 · WS 2019 6 · Jörg Tiedemann, Yves Scherrer

In this paper, we investigate whether multilingual neural translation models learn stronger semantic abstractions of sentences than bilingual ones. We test this hypotheses by measuring the perplexity of such models when …

DecoderNMTParaphrase GenerationTranslation

Russian Paraphrasers: Paraphrase with Transformers

2021-04-01 · BSNLP 2021 4 · Alena Fenogenova

This paper studies the generation methods for paraphrasing in the Russian language. There are several transformer-based models (Russian and multilingual) trained on a collected corpus of paraphrases. We compare different…