Papers with bigrams

4 papers
Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition (N19-1)

Copied to clipboard

Challenge: Existing datasets of semantic relatedness only include pairs of unigrams (single words) Existing data suffer from inconsistent annotations and scale region bias due to rating scales.
Approach: They propose to use a large, fine-grained, bigram relatedness dataset to compare the relatedness of 3,345 English term pairs using a comparative annotation technique called Best–Worst Scaling.
Outcome: The proposed datasets are highly reliable and have a split-half reliability of 0.937.
Finding Dataset Shortcuts with Grammar Induction (2022.emnlp-main)

Copied to clipboard

Challenge: Prior work on shortcut detection focused on enumerating features like unigrams or bigrams . prior work relied on post-hoc models that reveal qualitative patterns without a clear statistical interpretation .
Approach: They propose to use probabilistic grammars to characterize and discover shortcuts in NLP datasets using context-free grammars and synchronous context- free grammars.
Outcome: The proposed grammars reveal interesting shortcut features in a number of datasets, including simple and high-level features, and automatically identify groups of test examples on which conventional classifiers fail.
Mutual Gaze and Linguistic Repetition in a Multimodal Corpus (2022.lrec-1)

Copied to clipboard

Challenge: a study of linguistic repetitions and mutual understanding is conducted . we find no compelling correlation between mutual gaze and duration of the event .
Approach: They investigate the correlation between mutual gaze and linguistic repetition, a form of alignment, which they take as evidence of mutual understanding.
Outcome: The proposed method is based on the Multisimo corpus, a multimodal corpus which provides authentic task-based interactions among three participants.
Identifying Sentiments in Algerian Code-switched User-generated Comments (2020.lrec-1)

Copied to clipboard

Challenge: a recent study has focused on sentiment analysis for the Arabic variety, but it has been extended to other domains.
Approach: They build a corpus of 36,000 code-switched user-generated comments annotated for sentiments in Algerian Arabic.
Outcome: The proposed model performs better on unedited code-switched and unbalanced data across sentiment classes.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations