Improving Quality and Efficiency in Plan-based Neural Data-to-text Generation

Abstract

We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al. (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage. We suggest four extensions to that framework: (1) we introduce a trainable neural planning component that can generate effective plans several orders of magnitude faster than the original planner; (2) we incorporate typing hints that improve the model's ability to deal with unseen relations and entities; (3) we introduce a verification-by-reranking stage that substantially improves the faithfulness of the resulting texts; (4) we incorporate a simple but effective referring expression generation module. These extensions result in a generation process that is faster, more fluent, and more accurate.

A quantum‐like approach for text generation from knowledge graphs

“…LSTM/gate recurrent unit (GRU) was used by Moryossef et al. [8] to encode WebNLG graphs. Jafarbigloo et al.…”

Natural Language Explanations for Machine Learning Classification Decisions

“…Following [14], [33], [39], the final stage of the "Explainer Processor" involves linearization of the data into a flat string: p, v and the newly substituted c and f are formatted into the template below. A cap, top n, set at min(n, 10) or min(n, 20) during training, is used to limit the number of top features passed into the model and positive and negative features are subsets of the capped top features, such that top n + + top n − = top n; the lowest impact features are not affected.…”

Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity

“…Shen et al (2019) used techniques from computational pragmatics and modeled the generation task as a game between speakers and listeners. Despite following the generation-reranking paradigm explored previously in the data-to-text domain (Agarwal et al, 2018;Moryossef et al, 2019a;Dušek et al, 2019), and in other domains including machine translation (Shen et al, 2004), dialogue generation (Wen et al, 2015), and ASR (Morbini et al, 2012), our work has several distinctive aspects compared to previous works. First, we do not make extra assumptions, such as availability of precise MR parsers.…”

“…This error detection task has commonly relied on handwritten mappings from data values to potential realizations. Such rules were used to compute a Slot Error Rate (SER) metric (Dušek et al, 2019;Juraska et al, 2019;Moryossef et al, 2019a). For instance, Dušek et al (2019) use SER for reranking beam elements during decoding in an attention-based sequence-to-sequence model on the Cleaned E2E dataset.…”