Papers by Hideaki Takeda

4 papers
Transformer-based Lexically Constrained Headline Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing automatic headline generation methods cannot include a given phrase in the generated headline.
Approach: They propose a Transformer-based method that guarantees to include a given phrase in a generated headline.
Outcome: The proposed method achieves ROUGE scores comparable to previous methods with Japanese news corpus.
Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia (2020.emnlp-demos)

Copied to clipboard

Challenge: Existing tools for learning the embeddings of words and entities from Wikipedia are not yet available.
Approach: They propose a Python-based tool for learning Wikipedia embeddings from Wikipedia . they use a Wikipedia dump file as an argument to issue a single command .
Outcome: The proposed tool achieves state-of-the-art results on the KORE entity relatedness dataset and competitive results on benchmark datasets.
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for entity representations do not capture information in a knowledge base, and cannot represent entities that do not exist in the KB.
Approach: They propose a pretrained contextualized representation of words and entities based on the bidirectional transformer.
Outcome: The proposed model achieves impressive empirical performance on a wide range of entity-related tasks.
A Vietnamese Dialog Act Corpus Based on ISO 24617-2 standard (L18-1)

Copied to clipboard

Challenge: standardized dialog act corpora are used for conversation mining research . different corporations often use different methods to understand interaction structure .
Approach: They propose to annotate dialog acts using ISO 24617-2 standard (2012) . they also annotated emotions using Ekman's six primitives and sentiment using tags "positive", "negative" and "neutral"
Outcome: The proposed corpus is constructed using the ISO 24617-2 standard (2012) . it is used for emotions, sentiment and positive, negative and neutral tags .

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