Search Results for author:
Found 164 papers, 35 papers with code
Overview of the 9th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 9th workshop on Asian translation (WAT2022).
Construction of Hierarchical Structured Knowledge-based Recommendation Dialogue Dataset and Dialogue System
We work on a recommendation dialogue system to help a user understand the appealing points of some target (e. g., a movie).
Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning
Parallel texts of Japanese and a non-pro-drop language have the potential of improving the performance of Japanese zero anaphora resolution (ZAR) because pronouns dropped in the former are usually mentioned explicitly in the latter.
Overview of the 8th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021).
Flexible Visual Grounding
Existing visual grounding datasets are artificially made, where every query regarding an entity must be able to be grounded to a corresponding image region, i. e., answerable.
Improving Bridging Reference Resolution using Continuous Essentiality from Crowdsourcing
Bridging reference resolution is the task of finding nouns that complement essential information of another noun.
Static and Dynamic Speaker Modeling based on Graph Neural Network for Emotion Recognition in Conversation
Each person has a unique personality which affects how they feel and convey emotions.
Ranked #25 on
Emotion Recognition in Conversation
on MELD
A Method for Building a Commonsense Inference Dataset based on Basic Events
We present a scalable, low-bias, and low-cost method for building a commonsense inference dataset that combines automatic extraction from a corpus and crowdsourcing.
Kyoto University MT System Description for IWSLT 2017
We describe here our Machine Translation (MT) model and the results we obtained for the IWSLT 2017 Multilingual Shared Task.
Filtering of Noisy Web-Crawled Parallel Corpus: the Japanese-Bulgarian Language Pair
The corpus utilised to train machine translation models in the study is CCMatrix, provided by OPUS.
Explicit Use of Topicality in Dialogue Response Generation
In this study, we propose a dialogue system that responds appropriately following the topic by selecting the entity with the highest “topicality.” In topicality estimation, the model is trained through self-supervised learning that regards entities that appear in both context and response as the topic entities.
Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks
Contingent reasoning is one of the essential abilities in natural language understanding, and many language resources annotated with contingent relations have been constructed.
Meta Ensemble for Japanese-Chinese Neural Machine Translation: Kyoto-U+ECNU Participation to WAT 2020
This paper describes the Japanese-Chinese Neural Machine Translation (NMT) system submitted by the joint team of Kyoto University and East China Normal University (Kyoto-U+ECNU) to WAT 2020 (Nakazawa et al., 2020).
Overview of the 7th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 7th workshop on Asian translation (WAT2020).
Improving Event Duration Question Answering by Leveraging Existing Temporal Information Extraction Data
However, the amount of training data for tasks like duration question answering, i. e., McTACO, is very limited, suggesting a need for external duration information to improve this task.
JaMIE: A Pipeline Japanese Medical Information Extraction System with Novel Relation Annotation
In this paper, we first propose a novel relation annotation schema for investigating the medical and temporal relations between medical entities in Japanese medical reports.
Constructing a Culinary Interview Dialogue Corpus with Video Conferencing Tool
Interview is an efficient way to elicit knowledge from experts of different domains.
Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension
Thus, we propose a novel task, Causal Tree Extraction (CTE), which receives a case report and generates a causal tree with the primary disease as the root, providing an intuitive understanding of a case's diagnostic process.
Assessing Large Language Models in Agentic Multilingual National Bias
Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, while studies on risks associated with cross biases are limited to immediate context preferences.
Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
We examine the latent language of three typical categories of models for Japanese processing: Llama2, an English-centric model; Swallow, an English-centric model with continued pre-training in Japanese; and LLM-jp, a model pre-trained on balanced English and Japanese corpora.
LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs).
MELD-ST: An Emotion-aware Speech Translation Dataset
Emotion plays a crucial role in human conversation.
J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users.
AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data.
Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation.
RecMind: Japanese Movie Recommendation Dialogue with Seeker's Internal State
Since there are no existing annotated resources for the analysis, we constructed RecMind, a Japanese movie recommendation dialogue dataset with annotations of the seeker's internal state at the entity level.
Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts
To create the parallel corpora, we propose a dynamic programming based sentence alignment algorithm which leverages the cosine similarity of machine-translated sentences.
Video-Helpful Multimodal Machine Translation
In addition to the extensive training set, EVA contains a video-helpful evaluation set in which subtitles are ambiguous, and videos are guaranteed helpful for disambiguation.
Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i. e. event, time, and document creation time (DCT).
Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain
In the zero-shot setting of four Chinese legal tasks, our method improves accuracy by 33. 3\% compared to the direct generation by GPT-4.
MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting
Large language models (LLMs) have achieved impressive performance on various reasoning tasks.
Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation
The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translation.
Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation
This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST).
Towards Speech Dialogue Translation Mediating Speakers of Different Languages
We present a new task, speech dialogue translation mediating speakers of different languages.
SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation
In this paper, we provide a feasible definition of dialogue segmentation points with the help of document-grounded dialogues and release a large-scale supervised dataset called SuperDialseg, containing 9, 478 dialogues based on two prevalent document-grounded dialogue corpora, and also inherit their useful dialogue-related annotations.
Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoning
Numerical reasoning over table-and-text hybrid passages, such as financial reports, poses significant challenges and has numerous potential applications.
GPT-RE: In-context Learning for Relation Extraction using Large Language Models
In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e. g., GPT-3), they still lag significantly behind fully-supervised baselines (e. g., fine-tuned BERT) in relation extraction (RE).
Textual Enhanced Contrastive Learning for Solving Math Word Problems
Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information.
Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction
Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models.
ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision
To address this problem, we propose a novel search algorithm with combinatorial strategy \textbf{ComSearch}, which can compress the search space by excluding mathematically equivalent equations.
Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions.
EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning
Massively multilingual sentence representation models, e. g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks.
Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks.
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Meanwhile, the contrastive objective can implicitly utilize automatically learned word alignment, which has not been explored in many-to-many NMT.
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition
Low-resource speech recognition has been long-suffering from insufficient training data.
Linguistically-driven Multi-task Pre-training for Low-resource Neural Machine Translation
In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English.
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+2
VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation
Existing multimodal machine translation (MMT) datasets consist of images and video captions or general subtitles, which rarely contain linguistic ambiguity, making visual information not so effective to generate appropriate translations.
Cross-lingual Adaption Model-Agnostic Meta-Learning for Natural Language Understanding
Meta learning with auxiliary languages has demonstrated promising improvements for cross-lingual natural language processing.
JaMIE: A Pipeline Japanese Medical Information Extraction System
We present an open-access natural language processing toolkit for Japanese medical information extraction.
Video-guided Machine Translation with Spatial Hierarchical Attention Network
Video-guided machine translation, as one type of multimodal machine translations, aims to engage video contents as auxiliary information to address the word sense ambiguity problem in machine translation.
Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis
The model is trained to maximize the similarity between the representation of the target sentence with its context and that of the masked target sentence with the same context.
Lightweight Cross-Lingual Sentence Representation Learning
Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks.
Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model
With advances in neural language models, the focus of linguistic steganography has shifted from edit-based approaches to generation-based ones.
Extractive Summarization Considering Discourse and Coreference Relations based on Heterogeneous Graph
In this paper, we propose a heterogeneous graph based model for extractive summarization that incorporates both discourse and coreference relations.
Modeling and Utilizing User's Internal State in Movie Recommendation Dialogue
In this paper, we model the UIS in dialogues, taking movie recommendation dialogues as examples, and construct a dialogue system that changes its response based on the UIS.
BERT-based Cohesion Analysis of Japanese Texts
The meaning of natural language text is supported by cohesion among various kinds of entities, including coreference relations, predicate-argument structures, and bridging anaphora relations.
Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers
We propose a novel task of native-like expression identification by contrasting texts written by native speakers and those by proficient second language speakers.
Reverse Operation based Data Augmentation for Solving Math Word Problems
Automatically solving math word problems is a critical task in the field of natural language processing.
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets.
A System for Worldwide COVID-19 Information Aggregation
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
Pre-training via Leveraging Assisting Languages for Neural Machine Translation
Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks.
Building a Japanese Typo Dataset from Wikipedia's Revision History
User generated texts contain many typos for which correction is necessary for NLP systems to work.
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
Monolingual pre-training approaches such as MASS (MAsked Sequence to Sequence) are extremely effective in boosting NMT quality for languages with small parallel corpora.
Towards a Versatile Medical-Annotation Guideline Feasible Without Heavy Medical Knowledge: Starting From Critical Lung Diseases
Applying natural language processing (NLP) to medical and clinical texts can bring important social benefits by mining valuable information from unstructured text.
Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives
BERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks.
General Classification
Implicit Discourse Relation Classification
+4
Development of a Japanese Personality Dictionary based on Psychological Methods
In this study, we collect personality words, using word embeddings, and construct a personality dictionary with weights for Big Five traits.
Acquiring Social Knowledge about Personality and Driving-related Behavior
Using them, we automatically extracted collocations between personality descriptors and driving-related behavior from a driving behavior and subjectivity corpus (1, 803, 328 sentences after filtering) and obtained unique 5, 334 collocations.
Pre-training via Leveraging Assisting Languages and Data Selection for Neural Machine Translation
To this end, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI.
Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
To address this, we examine a language independent framework for parallel corpus mining which is a quick and effective way to mine a parallel corpus from publicly available lectures at Coursera.
Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysis
Our network also boosts the performance of emotion analysis by 5 F-score points on Stance Sentiment Emotion Corpus.
Machine Comprehension Improves Domain-Specific Japanese Predicate-Argument Structure Analysis
To improve the accuracy of predicate-argument structure (PAS) analysis, large-scale training data and knowledge for PAS analysis are indispensable.
Overview of the 6th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 6th workshop on Asian translation (WAT2019) including Ja↔En, Ja↔Zh scientific paper translation subtasks, Ja↔En, Ja↔Ko, Ja↔En patent translation subtasks, Hi↔En, My↔En, Km↔En, Ta↔En mixed domain subtasks and Ru↔Ja news commentary translation task.
Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction
Typical event sequences are an important class of commonsense knowledge.
Minimally Supervised Learning of Affective Events Using Discourse Relations
Recognizing affective events that trigger positive or negative sentiment has a wide range of natural language processing applications but remains a challenging problem mainly because the polarity of an event is not necessarily predictable from its constituent words.
Kyoto University Participation to the WMT 2019 News Shared Task
We describe here the experiments we did for the the news translation shared task of WMT 2019.
Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data
Argument compatibility is a linguistic condition that is frequently incorporated into modern event coreference resolution systems.
Shrinking Japanese Morphological Analyzers With Neural Networks and Semi-supervised Learning
Morphological analyzers are trained on data hand-annotated with segmentation boundaries and part of speech tags.
FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance
On the other hand, the relevance between the query and answer can be learned by using QA pairs in a FAQ database.
Juman++: A Morphological Analysis Toolkit for Scriptio Continua
We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries.
A Multi-task Ensemble Framework for Emotion, Sentiment and Intensity Prediction
In this paper, through multi-task ensemble framework we address three problems of emotion and sentiment analysis i. e. "emotion classification & intensity", "valence, arousal & dominance for emotion" and "valence & arousal} for sentiment".
A Knowledge-Augmented Neural Network Model for Implicit Discourse Relation Classification
Identifying discourse relations that are not overtly marked with discourse connectives remains a challenging problem.
General Classification
Implicit Discourse Relation Classification
+4
Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion
Considerable effort has been devoted to building commonsense knowledge bases.
Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis
Our experimental results demonstrate the proposed method can improve the performance of the inter-sentential zero anaphora resolution drastically, which is a notoriously difficult task in predicate argument structure analysis.
Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
Japanese predicate-argument structure (PAS) analysis involves zero anaphora resolution, which is notoriously difficult.
Knowledge-enriched Two-layered Attention Network for Sentiment Analysis
We propose a novel two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis.
Overview of the 4th Workshop on Asian Translation
For the WAT2017, 12 institutions participated in the shared tasks.
Kyoto University Participation to WAT 2017
We describe here our approaches and results on the WAT 2017 shared translation tasks.
MMCR4NLP: Multilingual Multiway Corpora Repository for Natural Language Processing
Multilinguality is gradually becoming ubiquitous in the sense that more and more researchers have successfully shown that using additional languages help improve the results in many Natural Language Processing tasks.
Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis
This paper presents a joint model for morphological and dependency analysis based on automatically acquired lexical knowledge.
Automatic Extraction of High-Quality Example Sentences for Word Learning Using a Determinantal Point Process
Flashcard systems are effective tools for learning words but have their limitations in teaching word usage.
Improving Shared Argument Identification in Japanese Event Knowledge Acquisition
Shared arguments of event knowledge encode patterns of role shifting in successive events.
Neural Joint Model for Transition-based Chinese Syntactic Analysis
We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing.
An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
In this paper, we propose a novel domain adaptation method named {``}mixed fine tuning{''} for neural machine translation (NMT).
Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames
To compensate the deficiency of the surface case frames, we compile deep case frames from automatic semantic roles.
Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages
In this paper, we explore a simple solution to "Multi-Source Neural Machine Translation" (MSNMT) which only relies on preprocessing a N-way multilingual corpus without modifying the Neural Machine Translation (NMT) architecture or training procedure.
An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
In this paper, we propose a novel domain adaptation method named "mixed fine tuning" for neural machine translation (NMT).
Reading Comprehension using Entity-based Memory Network
This paper introduces a novel neural network model for question answering, the \emph{entity-based memory network}.
Kyoto University Participation to WAT 2016
We report very good translation results, especially when using neural MT for Chinese-to-Japanese translation.
Consistent Word Segmentation, Part-of-Speech Tagging and Dependency Labelling Annotation for Chinese Language
In this paper, we propose a new annotation approach to Chinese word segmentation, part-of-speech (POS) tagging and dependency labelling that aims to overcome the two major issues in traditional morphology-based annotation: Inconsistency and data sparsity.
Overview of the 3rd Workshop on Asian Translation
For the WAT2016, 15 institutions participated in the shared tasks.
Large-Scale Acquisition of Commonsense Knowledge via a Quiz Game on a Dialogue System
Commonsense knowledge is essential for fully understanding language in many situations.
SCTB: A Chinese Treebank in Scientific Domain
Treebanks are curial for natural language processing (NLP).
Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs
As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser.
Paraphrasing Out-of-Vocabulary Words with Word Embeddings and Semantic Lexicons for Low Resource Statistical Machine Translation
Out-of-vocabulary (OOV) word is a crucial problem in statistical machine translation (SMT) with low resources.
Simultaneous Sentence Boundary Detection and Alignment with Pivot-based Machine Translation Generated Lexicons
Sentence alignment is a task that consists in aligning the parallel sentences in a translated article pair.
ASPEC: Asian Scientific Paper Excerpt Corpus
In this paper, we describe the details of the ASPEC (Asian Scientific Paper Excerpt Corpus), which is the first large-size parallel corpus of scientific paper domain.
Parallel Sentence Extraction from Comparable Corpora with Neural Network Features
Parallel corpora are crucial for machine translation (MT), however they are quite scarce for most language pairs and domains.
Bilingual Dictionary Construction with Transliteration Filtering
In this paper we present a bilingual transliteration lexicon of 170K Japanese-English technical terms in the scientific domain.
A Large Scale Database of Strongly-related Events in Japanese
This paper presents a large scale database of strongly-related events in Japanese, which has been acquired with our proposed method (Shibata and Kurohashi, 2011).
Constructing a Chinese---Japanese Parallel Corpus from Wikipedia
Using the system, we construct a Chinese―Japanese parallel corpus with more than 126k highly accurate parallel sentences from Wikipedia.
A Framework for Compiling High Quality Knowledge Resources From Raw Corpora
The identification of various types of relations is a necessary step to allow computers to understand natural language text.
Constructing a Corpus of Japanese Predicate Phrases for Synonym/Antonym Relations
We construct a large corpus of Japanese predicate phrases for synonym-antonym relations.
Chinese Characters Mapping Table of Japanese, Traditional Chinese and Simplified Chinese
Chinese characters are used both in Japanese and Chinese, which are called Kanji and Hanzi respectively.
