Revisiting Unsupervised Relation Extraction

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 718–731 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 718 Improved Natural Language Generation via Loss Truncation Daniel Kang Stanford University ddkang@stanford.edu Tatsunori B. Hashimoto Stanford University thashim@stanford.edu Abstract Neural language models are usually trained to match the distributional properties of large- scale corpora by minimizing the log loss. While straightforward to optimize, this ap- proach forces the model to reproduce all vari- ations in the dataset, including noisy and in- valid references (e.g., misannotations and hal- lucinated facts). Even a small fraction of noisy data can degrade the performance of log loss. As an alternative, prior work has shown that minimizing the distinguishability of generated samples is a principled and robust loss that can handle invalid references. However, distin- guishability has not been used in practice due to challenges in optimization and estimation. We propose loss truncation: a simple and scal- able procedure which adaptively removes high log loss examples as a way to optimize for dis- tinguishability. Empirically, we demonstrate that loss truncation outperforms existing base- lines on distinguishability on a summarization task. Furthermore, we show that samples gen- erated by the loss truncation model have fac- tual accuracy ratings that exceed those of base- lines and match human references. 1 Introduction Learning to generate text is a core part of many NLP tasks, including summarization (Nallapati et al., 2016), image captioning (Lin et al., 2014), and story generation (Roemmele, 2016). A com- mon challenge to all these tasks is that references from the training distribution are not unique and contain substantial variations in phrasing and con- tent (Wiseman et al., 2017; Dhingra et al., 2019). Learning to generate under a set of diverse and noisy references is challenging as some variations ought to be learned (e.g., paraphrasing) while oth- ers should not (e.g., hallucinated facts, ignoring prompts). Existing training procedures for models seek to match the underlying distribution, leading to mod- els that replicate and sometimes even amplify un- wanted behaviors such as hallucination during gen- eration. For example, neural language models often produce fluent text that is unfaithful to the source (Tian et al., 2019; Wiseman et al., 2017; Lee et al., 2018). Existing work (Fan et al., 2018; Holtzman et al., 2019) has primarily addressed these issues by constructing decoders that implicitly remove unwanted variation when generating (see §6 for a detailed discussion of task-specific losses). In this work, we argue that this phenomenon is not model specific, but is due to the widely-used log loss: we demonstrate that log loss is not robust to noisy and invalid references (§2). In particular, log loss requires that models assign probabilities to all potential test reference sequences. As a result, log loss is sensitive to outliers: invalid or noisy references with small probability mass can cause large changes in model behavior. We show that the brittleness of log loss, together with the noise in existing generation datasets, lead to low-quality and unfaithful …

Content truncated to 500 words