Papers by Masayuki Asahara

8 papers
Word Familiarity Rate Estimation Using a Bayesian Linear Mixed Model (D19-59)

Copied to clipboard

Challenge: 96,557 words were rated using the ‘Word List by Semantic Principles’ . 96 participants were surveyed using Yahoo! crowdsourcing .
Approach: They used Bayesian linear mixed models to estimate word familiarity rates using the ‘Word List by Semantic Principles’ and the semantic labels used in the study.
Outcome: The proposed method estimated word familiarity rates using Bayesian linear mixed models and semantic labels.
Design of BCCWJ-EEG: Balanced Corpus with Human Electroencephalography (2020.lrec-1)

Copied to clipboard

Challenge: Recent research has focused on the fusion of NLP and neuroscience of language.
Approach: They propose to use a balanced corpus of written Japanese (BCCWJ) annotated with human electroencephalography to improve annotations and annotations.
Outcome: The proposed language resource is annotated with human electroencephalography (EEG) and can improve on annotations, genres, languages, etc.
Universal Dependencies Version 2 for Japanese (L18-1)

Copied to clipboard

Challenge: UD Japanese resources are built on automatic conversion from several treebanks.
Approach: They propose to port the word delimitation, POS, and syntactic relations of existing treebanks to UD Japanese . they discuss the issues of the UD scheme found through porting of the Japanese language .
Outcome: The proposed UD Japanese resources are based on automatic conversion from treebanks.
Reading Time and Vocabulary Rating in the Japanese Language: Large-Scale Japanese Reading Time Data Collection Using Crowdsourcing (2022.lrec-1)

Copied to clipboard

Challenge: a study examines how differences in human vocabulary affect reading time . vocabulary size is inversely correlated to reading time due to the COVID-19 pandemic .
Approach: They assume that vocabulary is random effect of research participants . they then asked participants to take part in a self-paced reading task to collect reading times .
Outcome: The proposed method clarifies the tendency that vocabulary differences give to reading time.
All-words Word Sense Disambiguation Using Concept Embeddings (L18-1)

Copied to clipboard

Challenge: Existing work on all-words word sense disambiguation (all-word WSD) uses word embeddings to identify the senses of words in documents.
Approach: They propose a new concept embedding method to predict target word senses . concept embeds are constructed from concept tag sequences created from previous predictions .
Outcome: The proposed concept embeddings improve Japanese all-words word sense disambiguation task.
Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models with independent classifiers for each TLINK category hinder from using the whole data.
Approach: They propose a temporal relation classification model that manages dynamic event representations across multiple TLINKs using multi-task learning to leverage the full size of data.
Outcome: The proposed model outperforms state-of-the-art models and two strong transfer learning baselines on English and Japanese data.
KOTONOHA: A Corpus Concordance System for Skewer-Searching NINJAL Corpora (2020.lrec-1)

Copied to clipboard

Challenge: NINJAL has developed several types of corpora for linguistic research . for each corpus NINJAL provided an online search environment, ‘Chunagon’ .
Approach: NINJAL has developed several types of corpora for linguistic research . for each corpus NINJAL provided an online search environment, ‘Chunagon’, which is a morphological-information-annotation-based concordance system made publicly available in 2011 . NINjal has now provided a system ‘Kotonoha’ based on the ‘Chunegon’ systems .
Outcome: NINJAL has provided a skewer-search system ‘Kotonoha’ based on ‘Chunagon’ systems.
Lower Perplexity is Not Always Human-Like (2021.acl-long)

Copied to clipboard

Challenge: Existing efforts to build human-like computational models have focused on English . a cross-lingual evaluation is needed to build such models, but current research has focused on Japanese .
Approach: They re-examine an established generalization that lower perplexity is not always human-like in Japanese . they propose a cross-lingual evaluation to build human-type computational models .
Outcome: The proposed model lacks universality and lower perplexity is not always human-like . the results suggest a cross-lingual evaluation will be necessary to build human-type models .

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