paper-with-me

홈 › Papers

Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings

2017-04-30 · ACL 2017 7 · John Wieting, Kevin Gimpel

We consider the problem of learning general-purpose, paraphrastic sentence embeddings, revisiting the setting of Wieting et al. (2016b). While they found LSTM recurrent networks to underperform word averaging, we present several developments that together produce the opposite conclusion. These include training on sentence pairs rather than phrase pairs, averaging states to represent sequences, and regularizing aggressively. These improve LSTMs in both transfer learning and supervised settings. We also introduce a new recurrent architecture, the Gated Recurrent Averaging Network, that is inspired by averaging and LSTMs while outperforming them both. We analyze our learned models, finding evidence of preferences for particular parts of speech and dependency relations.

📄 PDF Abstract BibTeX arXiv:1705.00364

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingsTransfer Learning

Similar Papers 제목 키워드 기반

Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext

2017-06-06 · EMNLP 2017 9 · John Wieting, Jonathan Mallinson, Kevin Gimpel

We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of…

Machine TranslationSentenceSentence EmbeddingsTranslation

Towards Universal Paraphrastic Sentence Embeddings

2015-11-25 · John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu

We consider the problem of learning general-purpose, paraphrastic sentence embeddings based on supervision from the Paraphrase Database (Ganitkevitch et al., 2013). We compare six compositional architectures, evaluating …

General ClassificationSentenceSentence EmbeddingsSentence Similarity+2

Simple and Effective Paraphrastic Similarity from Parallel Translations

2019-09-30 · ACL 2019 7 · John Wieting, Kevin Gimpel, Graham Neubig, Taylor Berg-Kirkpatrick

We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating paraphrase corpora. Further, we show that the resulting mod…

SentenceSentence Embeddings

A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations

2019-04-02 · NAACL 2019 6 · Mingda Chen, Qingming Tang, Sam Wiseman, Kevin Gimpel

We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentangleme…

DisentanglementSemantic SimilaritySemantic Textual SimilaritySentence

ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations

2017-11-15 · ACL 2018 7 · John Wieting, Kevin Gimpel

We describe PARANMT-50M, a dataset of more than 50 million English-English sentential paraphrase pairs. We generated the pairs automatically by using neural machine translation to translate the non-English side of a larg…

Machine TranslationNatural Language UnderstandingParaphrase GenerationSemantic Textual Similarity+3