paper-with-me

Papers

Analysis and Prediction of Unalignable Words in Parallel Text

2014-04-01 · EACL 2014 4 · Frances Yung, Kevin Duh, Yuji Matsumoto
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationPredictionWord Alignment

Similar Papers 제목 키워드 기반

Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming

2020-10-06 · Findings of the Association for Computational Linguistics 2020 · Kanishka Misra, Allyson Ettinger, Julia Taylor Rayz

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question,…

Sensitivity

Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation

2018-08-27 · EMNLP 2018 10 · Marzieh Fadaee, Christof Monz

Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly…

Machine TranslationTranslation

FastSpeech: Fast,Robustand Controllable Text-to-Speech

2019-05-22 · Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin 외

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesiz…

Decodertext-to-speechText to SpeechText-To-Speech Synthesis

Disentangled Representation Learning for Non-Parallel Text Style Transfer

2018-08-13 · ACL 2019 7 · Vineet John, Lili Mou, Hareesh Bahuleyan, Olga Vechtomova

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives…

PredictionRepresentation LearningStyle TransferText Style Transfer

Topic Modeling based on Keywords and Context

2017-10-07 · Johannes Schneider

Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model …

General ClassificationTopic Models