59 citations · 282 across the 34 of their papers we have counts for
34 papers
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding
Kaiyan Zhao, Qiyu Wu, Xin-Qiang Cai +1
Learning multi-lingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both mono-lingual and multi-lingual sentence embeddings a…
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction
Qiyu Wu, Masaaki Nagata, Yoshimasa Tsuruoka
Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broad…
EASE: Entity-Aware Contrastive Learning of Sentence Embedding
Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada +2
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is…
Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models
Ryokan Ri, Yoshimasa Tsuruoka
We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language. We design artificial languages with structural p…
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka
Recent studies have shown that multilingual pretrained language models can be effectively improved with cross-lingual alignment information from Wikipedia entities. However, existi…
A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification
Sosuke Nishikawa, Ikuya Yamada, Yoshimasa Tsuruoka +1
We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained langu…
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
Takuya Hiraoka, Takahisa Imagawa, Taisei Hashimoto +2
Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks.…
Modeling Target-side Inflection in Placeholder Translation
Ryokan Ri, Toshiaki Nakazawa, Yoshimasa Tsuruoka
Placeholder translation systems enable the users to specify how a specific phrase is translated in the output sentence. The system is trained to output special placeholder tokens,…
Zero-pronoun Data Augmentation for Japanese-to-English Translation
Ryokan Ri, Toshiaki Nakazawa, Yoshimasa Tsuruoka
For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the Engl…
Utilizing Skipped Frames in Action Repeats via Pseudo-Actions
Taisei Hashimoto, Yoshimasa Tsuruoka
In many deep reinforcement learning settings, when an agent takes an action, it repeats the same action a predefined number of times without observing the states until the next act…
Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-…
Meta-Model-Based Meta-Policy Optimization
Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt +3
Model-based meta-reinforcement learning (RL) methods have recently been shown to be a promising approach to improving the sample efficiency of RL in multi-task settings. However, t…
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings
Sosuke Nishikawa, Ryokan Ri, Yoshimasa Tsuruoka
Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingua…
Revisiting the Context Window for Cross-lingual Word Embeddings
Ryokan Ri, Yoshimasa Tsuruoka
Existing approaches to mapping-based cross-lingual word embeddings are based on the assumption that the source and target embedding spaces are structurally similar. The structures…
Optimistic Proximal Policy Optimization
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka
Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that…
Building a Computer Mahjong Player via Deep Convolutional Neural Networks
Shiqi Gao, Fuminori Okuya, Yoshihiro Kawahara +1
The evaluation function for imperfect information games is always hard to define but owns a significant impact on the playing strength of a program. Deep learning has made great ac…
Learning Robust Options by Conditional Value at Risk Optimization
Takuya Hiraoka, Takahisa Imagawa, Tatsuya Mori +2
Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options t…
Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning
Shumpei Kubosawa, Takashi Onishi, Yoshimasa Tsuruoka
Chemical plants are complex and dynamical systems consisting of many components for manipulation and sensing, whose state transitions depend on various factors such as time, distur…
Neural Fictitious Self-Play on ELF Mini-RTS
Keigo Kawamura, Yoshimasa Tsuruoka
Despite the notable successes in video games such as Atari 2600, current AI is yet to defeat human champions in the domain of real-time strategy (RTS) games. One of the reasons is…
Partially Non-Recurrent Controllers for Memory-Augmented Neural Networks
Naoya Taguchi, Yoshimasa Tsuruoka
Memory-Augmented Neural Networks (MANNs) are a class of neural networks equipped with an external memory, and are reported to be effective for tasks requiring a large long-term mem…
Multilingual Extractive Reading Comprehension by Runtime Machine Translation
Akari Asai, Akiko Eriguchi, Kazuma Hashimoto +1
Despite recent work in Reading Comprehension (RC), progress has been mostly limited to English due to the lack of large-scale datasets in other languages. In this work, we introduc…
Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients
Takuya Hiraoka, Takashi Onishi, Takahisa Imagawa +1
Hierarchical planners that produce interpretable and appropriate plans are desired, especially in its application to supporting human decision making. In the typical development of…
Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks
Seydou Ba, Takuya Hiraoka, Takashi Onishi +2
Monte Carlo Tree Search (MCTS) is particularly adapted to domains where the potential actions can be represented as a tree of sequential decisions. For an effective action selectio…
Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
Kazuma Hashimoto, Yoshimasa Tsuruoka
A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve th…