Learning to sportscast

Chen, David L.; Mooney, Raymond J.

doi:10.1145/1390156.1390173

Cited by 338 publications

(445 citation statements)

References 14 publications

Supporting

Mentioning

441

Contrasting

Order By: Relevance

“…A lot of attention has been paid to individual content selection and selective realization sub-problems (Barzilay and Lee, 2004;Barzilay and Lapata, 2005;Liang et al, 2009). Recent works (Chen and Mooney, 2008;Chen et al, 2010;Mei et al, 2016) explore full selective generation and learn alignments between generated texts and input data using a translation model.…”

Section: Related Workmentioning

confidence: 99%

Routing Enforced Generative Model for Recipe Generation

Zang²,

Wan

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

One of the most challenging part of recipe generation is to deal with the complex restrictions among the input ingredients. Previous researches simplify the problem by treating the inputs independently and generating recipes containing as much information as possible.In this work, we propose a routing method to dive into the content selection under the internal restrictions. The routing enforced generative model (RGM) can generate appropriate recipes according to the given ingredients and user preferences. Our model yields new stateof-the-art results on the recipe generation task with significant improvements on BLEU, F1 and human evaluation.

show abstract

Section: Related Workmentioning

confidence: 99%

Routing Enforced Generative Model for Recipe Generation

Zang²,

Wan

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…The RW corpus we studied is from the sports domain which has attracted great interests (Chen and Mooney, 2008;Mei et al, 2016;Puduppully et al, 2019b). However, unlike generating the one-entity descriptions (Lebret et al, 2016; or having the output strictly bounded by the inputs (Novikova et al, 2017), this corpus poses additional challenges since the targets contain ungrounded contents.…”

Section: Related Workmentioning

confidence: 99%

Revisiting Challenges in Data-to-Text Generation with Fact Grounding

Wang

2019

Proceedings of the 12th International Conference on Natural Language Generation

View full text Add to dashboard Cite

Data-to-text generation models face challenges in ensuring data fidelity by referring to the correct input source. To inspire studies in this area, introduced the RotoWire corpus on generating NBA game summaries from the box-and line-score tables. However, limited attempts have been made in this direction and the challenges remain. We observe a prominent bottleneck in the corpus where only about 60% of the summary contents can be grounded to the boxscore records. Such information deficiency tends to misguide a conditioned language model to produce unconditioned random facts and thus leads to factual hallucinations. In this work, we restore the information balance and revamp this task to focus on fact-grounded data-to-text generation. We introduce a purified and larger-scale dataset, RotoWire-FG (Fact-Grounding), with 50% more data from the year 2017-19 and enriched input tables, hoping to attract more research focuses in this direction. Moreover, we achieve improved data fidelity over the stateof-the-art models by integrating a new form of table reconstruction as an auxiliary task to boost the generation quality.

show abstract

“…"Noisy" triples, such as: dbr:Sequoyah dbo:occupation dbr:Sequoyah 1 and dbr:Acie Law dbo:termPeriod Acie Law [1][2][3][4][5][6][7][8][9][10], are very common in the DBpedia triples allocated to the Wikipedia biographies. Since, their information is not verbalised in the text, our systems learn to disregard them, explaining the lower scores that these model achieve with respect to the number of summarised triples.…”

Section: Modelmentioning

confidence: 99%

“…The difficulty is that data that is available in knowledge bases needs to be aligned with the corresponding texts. Existing solutions for data-to-text generation either focus mainly on creating a small, domain-specific corpus where data and text are manually aligned by a small group of experts, such as the WeatherGov [9] and RoboCup [10] datasets, or rely heavily on crowdsourcing [11,12], which makes them costly to apply for large domains. We rely on the alignment of DBpedia and Wikidata with Wikipedia in order to create two corpora of knowledge base triples from DBpedia and Wikidata, and their corresponding textual summaries.…”

Section: Introductionmentioning

confidence: 99%

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

et al. 2018

View full text Add to dashboard Cite

Most people need textual or visual interfaces in order to make sense of Semantic Web data. In this paper, we investigate the problem of generating natural language summaries for Semantic Web data using neural networks. Our end-to-end trainable architecture encodes the information from a set of triples into a vector of fixed dimensionality and generates a textual summary by conditioning the output on the encoded vector. We explore a set of different approaches that enable our models to verbalise entities from the input set of triples in the generated text. Our systems are trained and evaluated on two corpora of loosely aligned Wikipedia snippets with triples from DBpedia and Wikidata, with promising results.

show abstract

Learning to sportscast

Cited by 338 publications

References 14 publications

Routing Enforced Generative Model for Recipe Generation

Routing Enforced Generative Model for Recipe Generation

Revisiting Challenges in Data-to-Text Generation with Fact Grounding

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

Contact Info

Product

Resources

About