Sue Felshin


2022

pdf bib
The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank
Adam Yaari | Jan DeWitt | Henry Hu | Bennett Stankovits | Sue Felshin | Yevgeni Berzak | Helena Aparicio | Boris Katz | Ignacio Cases | Andrei Barbu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Treebanks have traditionally included only text and were derived from written sources such as newspapers or the web. We introduce the Aligned Multimodal Movie Treebank (AMMT), an English language treebank derived from dialog in Hollywood movies which includes transcriptions of the audio-visual streams with word-level alignment, as well as part of speech tags and dependency parses in the Universal Dependencies formalism. AMMT consists of 31,264 sentences and 218,090 words, that will amount to the 3rd largest UD English treebank and the only multimodal treebank in UD. To help with the web-based annotation effort, we also introduce the Efficient Audio Alignment Annotator (EAAA), a companion tool that enables annotators to significantly speed-up their annotation processes.

2016

pdf bib
Learning to Answer Questions from Wikipedia Infoboxes
Alvaro Morales | Varot Premtoon | Cordelia Avery | Sue Felshin | Boris Katz
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2001

pdf bib
Gathering Knowledge for a Question Answering System from Heterogeneous Information Sources
Boris Katz | Jimmy Lin | Sue Felshin
Proceedings of the ACL 2001 Workshop on Human Language Technology and Knowledge Management

1989

pdf bib
An Efficient Method for Parsing Erroneous Input
Stuart Malone | Sue Felshin
Proceedings of the First International Workshop on Parsing Technologies

In a natural language processing system designed for language learners, it is necessary to accept both well-formed and ill-formed input. This paper describes a method of maintaining parsing efficiency for well-formed sentences while still accepting a wide range of ill-formed input.