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

Abstract

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.

Data-to-Text Generation with Content Selection and Planning

“…Despite being able to generate fluent text, neural data-to-text generation models are often imprecise, prone to hallucination (i.e., generate text that is not supported by the input), and poor at content selection and document structuring (Wiseman et al, 2017). 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 tokens to enhance faithful generation (Tian et al, 2019), and making the encoder-decoder architecture more modular by introducing micro planning (Puduppully et al, 2019a;Moryossef et al, 2019). Micro planning operates at the record level (see Tables (A) Figure 1; e.g., C.Mullins BH 2, J.Villar TEAM Orioles), it determines which facts should be men-arXiv:2102.02723v1 [cs.CL] inning with (T)op/(B)ottom, PL-ID: play id.…”

Tweet Classification Toward Twitter-Based Disease Surveillance: New Data, Methods, and Evaluations

“…One of the most popular medical applications is disease surveillance, which aims to predict disease epidemics based on the use of disease-related terms. Particularly, influenza surveillance using social media has been extensively studied [17-27,55]. As most previous studies have relied on shallow textual clues in messages, such as the number of occurrences of specific keywords (eg, flu or influenza ), there are several noisy messages.…”

“…On the other hand, with the widespread use of the internet, considerable material concerning medical or health care has been shared on the Web, and several Web mining techniques for utilizing the material have been developed. One of the most popular medical applications of Web mining is flu surveillance [17-27]. Although most previous studies have relied on shallow textual clues in messages, such as the number of occurrences of specific keywords (eg, flu or influenza ), such simple approaches have difficulty coping with the volume of noisy messages.…”

Generating Market Comments from Stock Prices

“…2018; Taniguchi, Feng, Takamura, and Okumura 2019), (Gkatzia, Hastie, and Lemon 2014) Data-to-Text (Goldberg, Driedger, and Kittredge 1994;Dale, Geldof, and Prost 2003;Reiter, Sripada, Hunter, Yu, and Davy 2005) (Liu, Wang, Sha, Chang, and Sui 2018;Iso, Uehara, Ishigaki, Noji, Aramaki, Kobayashi, Miyao, Okazaki, and Takamura 2019) (Vinyals, Toshev, Bengio, and Erhan 2015) (Mei, Bansal, and Walter 2016b) Data-to-Text Data-to-Text (content selection) (surface realization) 2 (Barzilay and Lapata 2005;Wong and Mooney 2007;Lu, Ng, and Lee 2009) 1 (Chen and Mooney 2008;Kim and Mooney 2010;Angeli et al 2010;Lapata 2012, 2013) (Sutskever et al 2014;Cho, van Merrienboer, Gulcehre, Bahdanau, Bougares, Schwenk, and Bengio 2014) Data-to-Text (Mei et al 2016b;Lebret, Grangier, and Auli 2016;Sha, Mou, Liu, Poupart, Li, Chang, and Sui 2018)…”