Unsupervised Concept-to-text Generation with Hypergraphs

By Ioannis Konstas, Mirella Lapata. 2012

100 citations recorded by the source corpus.

Subfields: Natural Language Processing, Graph Learning, 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 Natural Language Processing

In Graph Learning

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “…2008; Wiseman et al., 2017; Wang, 2019; Taniguchi et al., 2019), weather forecasts (Goldberg et al., 1994; Reiter et al., 2005; Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 2016), biographical texts (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018; Vou-giouklis et al., 2018;…”
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment (2015, methodology): “Table 1 compares our test results against previous meth-ods that include KL12 (Konstas and Lapata, 2012), KL13 (Konstas and Lapata, 2013), and ALK10 (An-geli et al., 2010).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “This enables them to handle long-range dependencies, such as coherence relations, more flexibly (e.g., a model can incorporate the information that a weather report which describes wind speed should do so after mentioning wind direction; see Barzilay & Lapata, 2005, for similar insights based on glo”
Few-Shot NLG with Pre-Trained Language Model (2019, background): “Later works (Konstas and Lapata 2012; 2013) investigated modeling context selection and surface realization in an uni-ﬁed framework.”
Data-to-Text Generation with Content Selection and Planning (2018, background): “However, most models make simplifying assumptions such as generation without any content selection or planning (Belz 2008; Wong and Mooney 2007) or content selection without planning (Konstas and Lapata 2012; Angeli et al. 2010; Kim and Mooney 2010).”
Mechanism-Aware Neural Machine for Dialogue Response Generation (2017, background): “Konstas et al. (2012) proposed a joint model for content selection and surface realization with a probabilistic context-free grammar.”
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “…commentaries from game records (Tanaka-Ishii et al., 1998; Chen and Mooney, 2008; Taniguchi et al., 2019), weather forecasts (Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 2016), biographical texts from Wikipedia infoboxes (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018;…”
Describing a Knowledge Base (2018, background): “…is to directly generate a sequence of words using language model (Belz, 2008; Chen and Mooney, 2008; Liang et al., 2009; Angeli et al., 2010; Konstas and Lapata, 2012a,b, 2013a,b; Mahapatra et al., 2016) or deep neural networks (Sutskever et al., 2011; Wen et al., 2015; Kiddon et al., 2016;…”
Obj2Text: Generating Visually Descriptive Language from Object Layouts (2017, background): “There have already been several successes in applications such as ﬁnancial reporting (Kukich, 1983; Smadja and McKeown, 1990), or weather forecasts (Konstas and Lapata, 2012; Wen et al., 2015), however it is still a challenging task for less structured and open domains.”
The aNALoGuE Challenge: Non Aligned Language GEneration (2016, background): “(Angeli et al., 2010; Konstas and Lapata, 2012; Mairesse and Young, 2014), but require high quality training data consisting of meaning representations (MR) paired with natural language (NL) utterances, augmented by alignments between elements of meaning representation and natural language words.”
Table-to-text Generation by Structure-aware Seq2seq Learning (2017, methodology): “Recent work combines content selection and surface realization in a unified framework (Ratnaparkhi 2002; Konstas and Lapata 2012; 2013; Sha et al. 2017) Our model borrowed the idea of representing a structured table by its field and content information from (Lebret, Grangier, and Auli 2016).”
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (2019, methodology): “Our plan selection procedure is admittedly simple, and can be improved by integrating insights from previous text planning works (Barzilay and Lapata, 2006; Konstas and Lapata, 2012, 2013).”