We present FastKASSIM, a metric for utterance- and document-level syntactic similarity which pairs and averages the most similar constituency parse trees.

2022/03/15 · We present FastKASSIM, a metric for utterance- and document-level syntactic similarity which pairs and averages the most similar constituency parse trees.

FastKASSIM is more robust to syntactic dissimilarities and differences in length, and runs up to to 5.2 times faster than our baseline method over the documents ...

The former measures the number of dependencies in a dependency parse, and the latter the number of nodes in a phrase structure tree.

A fast, extensible metric for document-level syntactic similarity inspired by the Fast Tree Kernel [2] and CASSIM [3]

2023/05/02 · On-demand video platform giving you access to lectures from conferences worldwide.

FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric ... Syntax is a fundamental component of language, yet few metrics have been employed to capture ...

共著者 ; FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric. M Chen, C Chen, X Yu, Z Yu. EACL 2023, 2022. 6, 2022 ; LocalRQA: From Generating Data ...

FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric. M Chen, C Chen, X Yu, Z Yu. EACL 2023, 2023. 5, 2023. Return of the Student: Predicting Re ...

FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric · pdf icon · Maximillian Chen, Caitlyn Chen, Xiao Yu, Zhou Yu. 08 Jun 2023; OpenReview Archive ...