Generative Alignment and Semantic Parsing for Learning from Ambiguous Supervision

By Joohyun Kim, Raymond J. Mooney. 2010

87 citations recorded by the source corpus.

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

Citations in the corpus

Neural Generation for Czech: Data and Baselines (2019, methodology): “We train the resulting 12 model variants using the Adam optimizer (Kingma and Ba, 2015) to minimize cross entropy on the training set; this approach is used for all parts of the system: the main seq2seq generator, the reranker, and the RNN LM lexicalizer.”
Challenges in Data-to-Document Generation (2017, background): “In the late 2000s and early 2010s, a number of systems were proposed that did both (Liang et al., 2009; Angeli et al., 2010; Kim and Mooney, 2010; Lu and Ng, 2011; Konstas and Lapata, 2013).”
Neural Text Generation from Structured Data with Application to the Biography Domain (2016, methodology): “This contrasts with less flexible strategies that assume the generation to follow either a hybrid alignment tree (Kim and Mooney, 2010), a probabilistic context-free grammar (Konstas and Lapata, 2013), or a tree adjoining grammar (Gyawali and Gardent, 2014).”
Learning to Interpret Natural Language Navigation Instructions from Observations (2011, methodology): “…a semantic parser/language generator to disambiguate the context (Kate and Mooney 2007; Chen, Kim, and Mooney 2010), building a generative model of the content selection process (Liang, Jordan, and Klein 2009; Kim and Mooney 2010), and using a ranking approach (Bor-des, Usunier, and Weston 2010).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “Kiros et al. (2014) introduced multimodal neural language models (mrnn), experimenting with two main architectures.”
Data-to-Text Generation with Content Selection and Planning (2018, background): “…developed for various domains which are either hand-built (Kukich 1983; McKeown 1992; Reiter and Dale 1997; Duboue and McKeown 2003) or learned from data (Barzilay and Lapata 2005; Duboue and McKeown 2001; 2003; Liang et al. 2009; Angeli et al. 2010; Kim and Mooney 2010; Konstas and Lapata 2013).”
Unsupervised Concept-to-text Generation with Hypergraphs (2012, methodology): “A common modeling strategy is to break up the generation process into a sequence of local decisions, each learned separately (Reiter et al., 2005; Belz, 2008; Chen and Mooney, 2008; Angeli et al., 2010; Kim and Mooney, 2010).”
Text Generation from Knowledge Graphs with Graph Transformers (2019, unknown): “Kim and Mooney (2010) improve this technique by learning a semantic parse to logical forms.”
Fast Online Lexicon Learning for Grounded Language Acquisition (2012, background): “Kim and Mooney (2010) further improved the generative alignment model by incorporating the full semantic parsing model from Lu et al. (2008).”
Grounded Unsupervised Semantic Parsing (2013, background): “More recently, several groundedlearning approaches have been proposed to alleviate the annotation burden (Chen and Mooney, 2008; Kim and Mooney, 2010; Börschinger et al., 2011; Clarke et al., 2010; Liang et al., 2011).”
Automatic Text Evaluation through the Lens of Wasserstein Barycenters (2021, background): “Data2text generation aims at generating text from structured data (Kim and Mooney, 2010; Chen and Mooney, 2008; Wiseman et al., 2017).”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “…selection and surface realization (Reiter and Dale 1997; Duboue and McKeown 2002; Barzilay and Lapata 2005, 2006; Belz 2008), which carefully learns the alignment between data and text(Liang, Jordan, and Klein 2009; Angeli, Liang, and Klein 2010; Kim and Mooney 2010; Konstas and Lapata 2013).”
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples (2017, background): “More recently, data-driven approaches which “learn” to perform content selection and realisation under a single framework have been proposed [18, 19].”
Table-to-text Generation by Structure-aware Seq2seq Learning (2017, methodology): “Other effective approaches include hybrid alignment tree (Kim and Mooney 2010), tree conditional random ﬁelds (Lu, Ng, and Lee 2009), tree adjoining grammar (Gyawali 2016) and template extraction in a log-linear framework (Angeli, Liang, and Klein 2010).”
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence (2020, methodology): “Traditional statistical methods usually tackle this problem by breaking the generation process into a set of local decisions that are learned separately (Belz, 2008; Angeli et al., 2010; Kim and Mooney, 2010; Oya et al., 2014).”
Generating Text from Structured Data with Application to the Biography Domain (2016, background): “This factorization allows us to scale to a large number of words and ﬁelds compared to Liang et al. (2009) and Kim and Mooney (2010) where the number of parameters grows as the product of the number of words and ﬁelds.”
Building a Neural Semantic Parser from a Domain Ontology (2018, background): “The model, especially the generative process, was extend by Kim and Mooney (2010) to learn from ambiguous supervisions.”