@conference {4109, title = {Grounding language acquisition by training semantic parsersusing captioned videos}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), }, year = {2018}, month = {10/2018 }, address = {Brussels, Belgium}, abstract = {

We develop a semantic parser that is trained ina grounded setting using pairs of videos cap-tioned with sentences. This setting is bothdata-efficient, requiring little annotation, andsimilar to the experience of children wherethey observe their environment and listen tospeakers. The semantic parser recovers themeaning of English sentences despite not hav-ing access to any annotated sentences. It doesso despite the ambiguity inherent in visionwhere a sentence may refer to any combina-tion of objects, object properties, relations oractions taken by any agent in a video. For thistask, we collected a new dataset for groundedlanguage acquisition. Learning a grounded se-mantic parser {\textemdash} turning sentences into logi-cal forms using captioned videos {\textemdash} can sig-nificantly expand the range of data that parserscan be trained on, lower the effort of training asemantic parser, and ultimately lead to a betterunderstanding of child language acquisition.

}, isbn = {978-1-948087-84-1}, url = {http://aclweb.org/anthology/D18-1285}, author = {Candace Ross and Andrei Barbu and Yevgeni Berzak and Battushig Myanganbayar and Boris Katz} }