Data Science Special Lecture-1（2023）

Date & Time: Friday, 13 October 15:10-16:40
Place: AI,Inc. Seminar Hall[L1]（IS）and Online(webex)
Language: Japanese

Lecturer: Daichi Mochihashi (Associate Professor, The Institute of Statistical Mathematics)

Title: Holographic CCG Parsing

Abstract:
We propose a method for formulating CCG as a recursive composition in a continuous vector space. Recent CCG supertagging and parsing models generally demonstrate high performance, yet rely on black-box neural architectures to implicitly model phrase structure dependencies.
Instead, we leverage the method of holographic embeddings (Nickel et al., 2016) as a compositional operator to explicitly model the dependencies between words and phrase structures in the embedding space. Experimental results revealed that holographic composition effectively improves the supertagging accuracy to achieve state-of-the-art parsing performance when using a C&C parser. The proposed span-based parsing algorithm using holographic composition achieves performance comparable to state-of-the-art neural parsing with Transformers. Furthermore, our model can semantically and syntactically infill text at the phrase level due to the decomposability of holographic composition.

References:
“Holographic CCG Parsing”. Ryosuke Yamaki, Tadahiro Taniguchi, Daichi Mochihashi.
ACL 2023, pp.262-276, 2023. (Long, Oral)
http://chasen.org/~daiti-m/paper/yamaki23holccg.pdf