1 code implementation • 24 Oct 2023 • Hiroto Kurita, Goro Kobayashi, Sho Yokoi, Kentaro Inui
The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss.
1 code implementation • 7 Jun 2023 • Yuki Arase, Han Bao, Sho Yokoi
Monolingual word alignment is crucial to model semantic interactions between sentences.
no code implementations • 29 May 2023 • Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui
Prediction head is a crucial component of Transformer language models.
1 code implementation • 1 Feb 2023 • Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui
Transformers are ubiquitous in wide tasks.
no code implementations • 19 Dec 2022 • Momose Oyama, Sho Yokoi, Hidetoshi Shimodaira
Distributed representations of words encode lexical semantic information, but what type of information is encoded and how?
1 code implementation • 11 Nov 2022 • Hiroaki Yamagiwa, Sho Yokoi, Hidetoshi Shimodaira
The proposed method is based on the Fused Gromov-Wasserstein distance, which simultaneously considers the similarity of the word embedding and the SAM for calculating the optimal transport between two sentences.
1 code implementation • 24 Oct 2022 • Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, Satoshi Nakamura
In the field of natural language processing (NLP), continuous vector representations are crucial for capturing the semantic meanings of individual words.
no code implementations • 28 Sep 2021 • Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, Kentaro Inui
Interpretable rationales for model predictions are crucial in practical applications.
2 code implementations • EMNLP 2021 • Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui
Transformer architecture has become ubiquitous in the natural language processing field.
no code implementations • 18 May 2021 • Masahiro Naito, Sho Yokoi, Geewook Kim, Hidetoshi Shimodaira
(Q2) Ordinary additive compositionality can be seen as an AND operation of word meanings, but it is not well understood how other operations, such as OR and NOT, can be computed by the embeddings.
no code implementations • EACL 2021 • Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada
The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation.
no code implementations • EMNLP (sustainlp) 2020 • Sosuke Kobayashi, Sho Yokoi, Jun Suzuki, Kentaro Inui
Understanding the influence of a training instance on a neural network model leads to improving interpretability.
no code implementations • COLING 2020 • Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui
Events in a narrative differ in salience: some are more important to the story than others.
2 code implementations • ICLR 2021 • Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui
In this study, we investigated relevance metrics that can provide reasonable explanations to users.
1 code implementation • EMNLP 2020 • Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki, Kentaro Inui
Accordingly, we propose a method that first decouples word vectors into their norm and direction, and then computes alignment-based similarity using earth mover's distance (i. e., optimal transport cost), which we refer to as word rotator's distance.
1 code implementation • ACL 2020 • Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Ryuto Konno, Kentaro Inui
Interpretable rationales for model predictions play a critical role in practical applications.
1 code implementation • EMNLP 2020 • Reina Akama, Sho Yokoi, Jun Suzuki, Kentaro Inui
Large-scale dialogue datasets have recently become available for training neural dialogue agents.
1 code implementation • EMNLP 2020 • Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui
Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing.
no code implementations • EMNLP 2018 • Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui
As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC).
no code implementations • ACL 2018 • Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui
This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner.