Search Results for author:
Found 57 papers, 16 papers with code
Direct Quantized Training of Language Models with Stochastic Rounding
Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory footprints.
M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models
To address these challenges, we propose an automated music generation pipeline that produces background music for an input manga book.
Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning
Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment.
Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback
Specifically, we use relation tuples, which are not only human-readable but also machine-friendly and easier to verify than natural language.
Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences
We evaluate how accurately PIToD estimates the influence of experiences and its efficiency compared to LOO.
Word Alignment as Preference for Machine Translation
In this work, we mitigate the problem in an LLM-based MT model by guiding it to better word alignment.
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora.
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding
Learning multi-lingual sentence embeddings is a fundamental task in natural language processing.
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction
Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness.
Unsupervised Discovery of Continuous Skills on a Sphere
However, most of the existing methods learn a finite number of discrete skills, and thus the variety of behaviors that can be exhibited with the learned skills is limited.
Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout
In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance.
Soft Sensors and Process Control using AI and Dynamic Simulation
During the operation of a chemical plant, product quality must be consistently maintained, and the production of off-specification products should be minimized.
EASE: Entity-Aware Contrastive Learning of Sentence Embedding
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.
Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models
We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language.
Railway Operation Rescheduling System via Dynamic Simulation and Reinforcement Learning
The system leverages reinforcement learning and a dynamic simulator that can simulate the railway traffic and passenger flow of a whole line.
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
We train a multilingual language model with 24 languages with entity representations and show the model consistently outperforms word-based pretrained models in various cross-lingual transfer tasks.
Ranked #1 on
Cross-Lingual Question Answering
on XQuAD
(Average F1 metric, using extra
training data)
A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification
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 language model (e. g., M-BERT).
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
To make REDQ more computationally efficient, we propose a method of improving computational efficiency called DroQ, which is a variant of REDQ that uses a small ensemble of dropout Q-functions.
Zero-pronoun Data Augmentation for Japanese-to-English Translation
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 English sentence.
Utilizing Skipped Frames in Action Repeats via Pseudo-Actions
The key idea of our method is making the transition between action-decision points usable as training data by considering pseudo-actions.
Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces
It learns a belief model over the embedding space and a belief-conditional policy and Q-function.
Meta-Model-Based Meta-Policy Optimization
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.
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings
Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora.
Revisiting the Context Window for Cross-lingual Word Embeddings
Existing approaches to mapping-based cross-lingual word embeddings are based on the assumption that the source and target embedding spaces are structurally similar.
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+1
Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation
Traditional model training for sentence generation employs cross-entropy loss as the loss function.
Optimistic Proximal Policy Optimization
Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains.
Building a Computer Mahjong Player via Deep Convolutional Neural Networks
The evaluation function for imperfect information games is always hard to define but owns a significant impact on the playing strength of a program.
Incorporating Source-Side Phrase Structures into Neural Machine Translation
In those NMT models, sentences are simply treated as sequences of words without any internal structure.
Learning Robust Options by Conditional Value at Risk Optimization
While there are several methods to learn options that are robust against the uncertainty of model parameters, these methods only consider either the worst case or the average (ordinary) case for learning options.
Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning
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, disturbance, and operation procedures.
Neural Fictitious Self-Play on ELF Mini-RTS
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.
Partially Non-Recurrent Controllers for Memory-Augmented Neural Networks
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 memory and its selective use.
Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients
In this paper, we propose a framework that can automatically refine symbol grounding functions and a high-level planner to reduce human effort for designing these modules.
Multilingual Extractive Reading Comprehension by Runtime Machine Translation
Given a target language without RC training data and a pivot language with RC training data (e. g. English), our method leverages existing RC resources in the pivot language by combining a competitive RC model in the pivot language with an attentive Neural Machine Translation (NMT) model.
Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks
The evaluation results show that, with variable simulation times, the proposed approach outperforms the conventional MCTS in the evaluated continuous decision space tasks and improves the performance of MCTS in most of the ALE tasks.
Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
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.
Hierarchical Reinforcement Learning with Abductive Planning
One potential solution to this problem is to combine reinforcement learning with automated symbol planning and utilize prior knowledge on the domain.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Learning to Parse and Translate Improves Neural Machine Translation
There has been relatively little attention to incorporating linguistic prior to neural machine translation.
Neural Machine Translation with Source-Side Latent Graph Parsing
This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences.
Character-based Decoding in Tree-to-Sequence Attention-based Neural Machine Translation
This paper reports our systems (UT-AKY) submitted in the 3rd Workshop of Asian Translation 2016 (WAT{'}16) and their results in the English-to-Japanese translation task.
Domain Adaptation and Attention-Based Unknown Word Replacement in Chinese-to-Japanese Neural Machine Translation
This paper describes our UT-KAY system that participated in the Workshop on Asian Translation 2016.
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks.
Ranked #3 on
Chunking
on Penn Treebank
Domain Adaptation for Neural Networks by Parameter Augmentation
Recently, recurrent neural networks have been shown to be successful on a variety of NLP tasks such as caption generation; however, the existing domain adaptation techniques are limited to (1) tune the model parameters by the target dataset after the training by the source dataset, or (2) design the network to have dual output, one for the source domain and the other for the target domain.
Asymmetric Move Selection Strategies in Monte-Carlo Tree Search: Minimizing the Simple Regret at Max Nodes
We develop the Asymmetric-MCTS algorithm, which is an MCTS variant that applies a simple regret algorithm on max nodes, and the UCB algorithm on min nodes.
A Japanese Chess Commentary Corpus
We describe a detailed definition of named entities and show some statistics of our game commentary corpus.
Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings
We present a novel method for jointly learning compositional and non-compositional phrase embeddings by adaptively weighting both types of embeddings using a compositionality scoring function.
Tree-to-Sequence Attentional Neural Machine Translation
Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information.
Adapting Improved Upper Confidence Bounds for Monte-Carlo Tree Search
The UCT algorithm, which combines the UCB algorithm and Monte-Carlo Tree Search (MCTS), is currently the most widely used variant of MCTS.
Task-Oriented Learning of Word Embeddings for Semantic Relation Classification
We present a novel learning method for word embeddings designed for relation classification.
