Papers by Koki Washio

6 papers
Bridging the Defined and the Defining: Exploiting Implicit Lexical Semantic Relations in Definition Modeling (D19-1)

Copied to clipboard

Challenge: Existing definition modeling methods do not utilize lexical semantic relations between defined words and defining words.
Approach: They propose definition modeling methods that use lexical semantic relations . they use unsupervised pattern-based word-pair embeddings that represent semantic relations of word pairs .
Outcome: The proposed methods improve definition generation and learning embeddings from definitions.
Undersampling Improves Hypernymy Prototypicality Learning (L18-1)

Copied to clipboard

Challenge: supervised hypernymy detection suffers from overfitting hypernies in training data.
Approach: They propose a method that can alleviate the problem of overfitting hypernyms in training data by using distributional representations for unknown word pairs.
Outcome: The proposed method alleviates the problem of overfitting hypernyms in training data and improves distributional prototypicality learning for unknown word pairs.
Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations (N18-1)

Copied to clipboard

Challenge: Existing approaches to recognize lexical semantic relations between word pairs require that word pairs co-occur in a sentence.
Approach: They propose to exploit lexico-syntactic paths between two target words to exploit the semantic relations between word pairs.
Outcome: The proposed model can generalize the co-occurrences of word pairs and dependency paths and extract features capturing relational information from word pairs.
On the Relationship between Zipf’s Law of Abbreviation and Interfering Noise in Emergent Languages (2021.acl-srw)

Copied to clipboard

Challenge: Existing studies have shown that emergent languages do not obey ZLA when neural agents play a signaling game.
Approach: They propose to add an explicit penalty on word lengths to a signaling game to simulate a ZLA-like tendency when interfering noises are added to the agents' environment.
Outcome: The proposed model shows that the noise on a speaker is one of the factors for ZLA, while noise on the listener and a channel is not.
Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space (D18-1)

Copied to clipboard

Challenge: Existing approaches to capture semantic relations of words in vector space are lacking information on lexico-syntactic patterns that connect word pairs in a corpus.
Approach: They propose a pattern-based approach that exploits lexico-syntactic patterns as word pairs . they propose NLRA to generalize co-occurrences of word pairs and lexicon-sensitized embeddings of the word pairs that do not co-occur.
Outcome: The proposed model outperforms existing models on measuring relational similarity . it can generalize word pairs and lexico-syntactic patterns and obtain embeddings of word pairs that do not co-occur .
Global Entity Disambiguation with BERT (2022.naacl-main)

Copied to clipboard

Challenge: Entity disambiguation (ED) is a task of assigning mentions to referent entities in a knowledge base.
Approach: They propose a global entity disambiguation (ED) model based on BERT . they train the model using a large entity-annotated corpus obtained from Wikipedia .
Outcome: The proposed model can disambiguate masked entities based on words and non-masked ones at the inference time.

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