Learning to sportscast: a test of grounded language acquisition

By David L. Chen, Raymond J. Mooney. 2008

270 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Experience Grounds Language (2020, background): “This idea is not new (Chen and Mooney, 2008; Feng and Lapata, 2010; Bruni et al., 2014; Lazaridou et al., 2016) and has accelerated in the last few years.”
Creating Training Corpora for NLG Micro-Planners (2017, background): “In the sports domain, Chen and Mooney (2008) constructed a dataset mapping soccer games events to text which consists of 1,539 data-text pairs and a vocabulary of 214 words. For weather forecast generation, the dataset of Liang et al. (2009) includes 29,528 data-text pairs with a vocabulary of 345 w”
The E2E Dataset: New Challenges For End-to-End Generation (2017, background): “, 2015), or RoboCup (Chen and Mooney, 2008).”
Grounded Language Learning in a Simulated 3D World (2017, background): “nk objects and events in stick-gure animations to language. Broadly this can be seen as a precursor to more recent work on mapping language to actions in video and similar modalities (Siskind, 2001; Chen and Mooney, 2008; Yu and Siskind, 2013). In a similar vein, the work of Roy and Pentland (2002) ”
DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Applications include generating sports commentaries (Chen and Mooney, 2008; Wiseman et al., 2017), weather forecasts (Liang et al.”
Learning Dependency-Based Compositional Semantics (2011, background): “Some can learn from utterances paired with a set of logical forms, one of which is correct (Kate and Mooney, 2007; Chen and Mooney, 2008).”
Challenges in Data-to-Document Generation (2017, methodology): “Several benchmark datasets have been used in recent years for the text generation task, the most popular of these being W EATHER G OV (Liang et al., 2009) and R OBOCUP (Chen and Mooney, 2008).”
ToTTo: A Controlled Table-To-Text Generation Dataset (2020, background): “Task Design Most existing table-to-text datasets are restricted in topic and schema such as W EATH - ER G OV (Liang et al., 2009), R OBO C UP (Chen and Mooney, 2008), Rotowire (Wiseman et al., 2017, basketball), E2E (Novikova et al., 2016, 2017, restaurants), KBGen (Banik et al., 2013, biology),…”
Learning Semantic Correspondences with Less Supervision (2009, methodology): “We used the dataset created by Chen and Mooney (2008), which contains 1919 scenarios from the 2001–2004 Robocup ﬁnals.”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “So far, end-to-end approaches to NLG have been limited to small, delexicalised datasets, e.g. BAGEL (Mairesse et al. 2010), SF Hotels/Restaurants (Wen et al. 2015b), or RoboCup (Chen and Mooney 2008).”
Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World (2013, background): “…language acquisition leverages semantic parsing to map from natural language to a formal representation of an environment (Kate and Mooney, 2007; Chen and Mooney, 2008; Shimizu and Haas, 2009; Matuszek relation. et al., 2010; Dzifcak et al., 2009; Cantrell et al., 2010; Chen and Mooney, 2011).”
Reinforcement Learning for Mapping Instructions to Actions (2009, methodology): “In this paper, we present a reinforcement learning framework for inducing mappings from text to actions without the need for annotated training examples.”
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment (2015, methodology): “For ROBOCUP, we follow the evaluation methodology of previous work (Chen and Mooney, 2008; Kim and Mooney, 2010; Angeli et al., 2010; Konstas and Lapata, 2012), performing three-fold crossvalidation whereby we train on three games and test on the fourth.”
Learning to Win by Reading Manuals in a Monte-Carlo Framework (2011, background): “Chen and Mooney (2008) represent action sequences using first order logic.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “The work of Mooney and colleagues (Wong & Mooney, 2007; Chen & Mooney, 2008; Kim & Mooney, 2010) has compared a number of different generation strategies inspired by the wasp semantic parser (Wong & Mooney, 2007), which uses probabilistic synchronous cfg rules learned from pairs of utterances and…”
Reading to Learn: Constructing Features from Semantic Abstracts (2009, background): “…on extracting logical forms from surface text (Zettlemoyer and Collins, 2005; Ge and Mooney, 2005; Downey et al., 2005; Liang et al., 2009), interpreting language in the context of a domain (Chen and Mooney, 2008), and using an actionable domain to guide text interpretation (Branavan et al., 2009).”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, methodology): “Picking from the top 5 generated sentences also added variability to the machine-generated sportscasts that improved the results compared with earlier experiments presented by Chen and Mooney (2008). However, the machine still sometimes misses significant plays such as scoring or corner kicks.”
Findings of the E2E NLG Challenge (2018, background): “The resulting dataset (Novikova et al., 2017b) contains over 50k references for 6k distinct MRs (cf. Table 2), which is 10 times bigger than previous sets in comparable domains (BAGEL, SF Ho-tels/Restaurants, RoboCup).”
Analysing Data-To-Text Generation Benchmarks (2017, background): “Recently, several datasets have been created to train data-to-text generators (Wen et al., 2015a; Liang et al., 2009; Lebret et al., 2016; Novikova et al., 2016; Chen and Mooney, 2008).”