Learning to Select, Track, and Generate for Data-to-Text

By Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura. 2019

50 citations recorded by the source corpus.

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Recently, neural encoder-decoder models based on attention and copy mechanisms have shown promising results (Wiseman et al., 2017; Liu et al., 2018; Gehrmann et al., 2018; Puduppully et al., 2018, 2019; Iso et al., 2019; Castro Ferreira et al., 2019; Shen et al., 2019; Roberti et al., 2019; Zhu et a”
Generation Challenges: Results of the Accuracy Evaluation Shared Task (2021, methodology): “Other systems in this domain which could be used for evaluation include Puduppully et al. (2019b), Wang (2019), Gong et al. (2019), and Iso et al. (2019).”
Revisiting Challenges in Data-to-Text Generation with Fact Grounding (2020, background): “Although this excellent resource has received great research attention, very few works (Li and Wan, 2018; Puduppully et al., 2019a,b; Iso et al., 2019) have attempted to tackle the challenges on ensuring data fidelity.”
A Survey of Knowledge-enhanced Text Generation (2020, background): “For example, a sports journalist may use particular expressions and language styles to describe specific kinds of games [68].”
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “, 2016) have shown promising results on table-to-text tasks (Wiseman et al., 2017; Gehrmann et al., 2018; Puduppully et al., 2019a,b; Iso et al., 2019; Castro Ferreira et al., 2019; Zhao et al., 2020; Chen et al., 2020a).”
Shared Task on Evaluating Accuracy (2020, methodology): “Other systems in this domain which could be used for evaluation include Puduppully et al. (2019b), Wang (2019), Gong et al. (2019), and Iso et al. (2019).”
Data-to-text Generation with Macro Planning (2021, background): “Attempts to remedy some of these issues focus on changing the way entities are represented (Puduppully et al., 2019b; Iso et al., 2019), allowing the decoder to skip low-conﬁdence to-kens to enhance faithful generation (Tian et al., 2019), and making the encoder-decoder architecture more modular by…”