Papers by Satoshi Sekine
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. |
An Empirical Study on Fine-Grained Named Entity Recognition (C18-1)
Copied to clipboard
Khai Mai, Thai-Hoang Pham, Minh Trung Nguyen, Tuan Duc Nguyen, Danushka Bollegala, Ryohei Sasano, Satoshi Sekine
| Challenge: | Named entity recognition (NER) is a well studied topic in natural language processing. |
| Approach: | They propose to remove the CNN layer and use dictionary and category embeddings to improve Japanese FG-NER performance. |
| Outcome: | The proposed method improves Japanese FG-NER F-score from 66.76% to 75.18%. |
What is the Real Intention behind this Question? Dataset Collection and Intention Classification (2023.acl-long)
Copied to clipboard
| Challenge: | Using the Wikipedia discussions, we identified positive/neutral and negative intentions in questions . questions can also reflect implicit offenses such as highlighting one’s lack of knowledge or bolstering an alleged superior knowledge, which can lead to conflict in conversations. |
| Approach: | They propose to use a dataset to identify questions with positive/neutral and negative intentions and the underlying intention categories within each group to highlight tacit and apparent intents. |
| Outcome: | The proposed method highlights tacit and apparent intents and uses Transformers augmented by TF-IDF-based features to classify the main intention categories. |
Co-Teaching Student-Model through Submission Results of Shared Task (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Shared tasks require participants to submit only system outputs and descriptions. |
| Approach: | They propose to utilize all system outputs in a shared task to build a unified system that performs better than the task's single best system. |
| Outcome: | The proposed scheme outperforms the best system in the SHINRA2019-JP shared task with nine participants. |
Select and Attend: Towards Controllable Content Selection in Text Generation (D19-1)
Copied to clipboard
| Challenge: | Recent neural network models conflate content selection and surface realization into a black-box architecture, resulting in content to be described in text cannot be explicitly controlled. |
| Approach: | They propose to decouple content selection from the decoder to allow finer-grained control over the generation. |
| Outcome: | The proposed model can be trained end-to-end without human annotations and achieves promising results in data-totext and headline generation tasks. |
JEMHopQA: Dataset for Japanese Explainable Multi-Hop Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | a dataset for explainable QA in Japanese is available for many languages, but not in other languages. |
| Approach: | They present a multi-hop QA dataset based on Japanese Wikipedia . it includes question-answer pairs and supporting evidence in the form of derivation triples . they show that the dataset is sufficiently challenging for state-of-the-art LLMs based upon this dataset . |
| Outcome: | The proposed dataset is based on Japanese Wikipedia and can be used to evaluate QA tasks. |
Resource of Wikipedias in 31 Languages Categorized into Fine-Grained Named Entities (2022.coling-1)
Copied to clipboard
| Challenge: | a resource of Wikipedias in 31 languages is categorized into Extended Named Entity (ENE) ENE version 8 has 219 fine-grained NE categories. |
| Approach: | They describe a resource of Wikipedias in 31 languages categorized into Extended Named Entity (ENE) they first categorized 920 K Japanese Wikipedia pages using machine learning, then shared a task of Wikipedia categorization into 30 languages . |
| Outcome: | The proposed system is based on a dataset of Japanese Wikipedia pages . the dataset shows the best performance among the 30 languages . |
Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing classification models struggle with large datasets using fine-grained tag sets. |
| Approach: | They propose to structure Wikipedia into a large multi-lingual dataset using an Extended Named Entity tag set. |
| Outcome: | The proposed model fails to describe why Wikipedia articles are used to summarize, translate or answer questions. |
What Makes Reading Comprehension Questions Easier? (D18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that questions require a deeper understanding of language to answer beyond using superficial cues. |
| Approach: | They propose to use simple heuristics to split MRC datasets into easy and hard subsets and manually annotate questions from each subset with validity and reasoning skills to investigate which skills explain the difference between easy and harder questions. |
| Outcome: | The proposed model performs better for hard and easy questions than for easy questions. |
Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling (2022.coling-1)
Copied to clipboard
| Challenge: | Semantic role labeling is the task of labeling semantic arguments for marked semantic predicates. |
| Approach: | They propose a model which combines global decoding and iterative identification for the semantic arguments to consider their roles and relations in the labeling order. |
| Outcome: | The proposed model outperforms existing models in the benchmark datasets of span-based SRL: CoNLL-2005 and CoNll-2012. |