paper-with-me

홈 › Papers

Generating Sentences from Disentangled Syntactic and Semantic Spaces

2019-07-06 · ACL 2019 7 · Yu Bao, Hao Zhou, Shu-Jian Huang, Lei LI, Lili Mou, Olga Vechtomova, Xin-yu Dai, Jia-Jun Chen

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces. Our proposed method explicitly models syntactic information in the VAE's latent space by using the linearized tree sequence, leading to better performance of language generation. Additionally, the advantage of sampling in the disentangled syntactic and semantic latent spaces enables us to perform novel applications, such as the unsupervised paraphrase generation and syntax-transfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.

📄 PDF Abstract BibTeX arXiv:1907.05789

Code (1)

baoy-nlp/DSS-VAE 공식 구현 pytorch

Tasks

Paraphrase GenerationText Generation

Similar Papers 제목 키워드 기반

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

Learning Disentangled Representations for Natural Language Definitions

2022-09-22 · Danilo S. Carvalho, Giangiacomo Mercatali, Yingji Zhang, Andre Freitas

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement method…

DisentanglementSentence

Learning Disentangled Representations in Natural Language Definitions with Semantic Role Labeling Supervision

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. However, most disentanglement methods …

DisentanglementSemantic Role LabelingSentence

Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT

2021-01-26 · EACL 2021 2 · Isabel Papadimitriou, Ethan A. Chi, Richard Futrell, Kyle Mahowald

We investigate how Multilingual BERT (mBERT) encodes grammar by examining how the high-order grammatical feature of morphosyntactic alignment (how different languages define what counts as a "subject") is manifested acro…

Sentence

Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders

2023-11-14 · Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann 외

The injection of syntactic information in Variational AutoEncoders (VAEs) has been shown to result in an overall improvement of performances and generalisation. An effective strategy to achieve such a goal is to separate…

Language ModellingMulti-Task Learning