Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

Anonymous

Paper Link: https://openreview.net/forum?id=kQWGURqrAW_

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract: Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a target sequence with a generated sequence. Such training objective is sub-optimal when the target sequence is not perfect, e.g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available. To address the challenge, we propose a novel Edit-Invariant Sequence Loss (EISL), which computes the matching loss of a target $n$-gram with all $n$-grams in the generated sequence. EISL is designed to be robust to various noises and edits in the target sequences. Moreover, the EISL computation is essentially an approximate convolution operation with target $n$-grams as kernels, which is easy to implement and efficient to compute with existing libraries. To demonstrate the effectiveness of EISL, we conduct experiments on a wide range of tasks, including machine translation with noisy target sequences, unsupervised text style transfer with only weak training signals, and non-autoregressive generation with non-predefined generation order. Experimental results show our method significantly outperforms the common CE loss and other strong baselines on all the tasks. EISL has a simple API that can be used as a drop-in replacement of the CE loss: https://github.com/guangyliu/EISL.

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC+8

Copyright Consent Signature (type Name Or NA If Not Transferrable): Guangyi Liu

Copyright Consent Name And Address: Chinese University of Hong Kong, Shenzhen, 2001 Longxiang Boulevard, Longgang District, Shenzhen, China