Kotaro Funakoshi
YOU?
Author Swipe
View article: Breathe and Speak Attentively: Implementing Respiratory Awareness Into Conversational Robots
Breathe and Speak Attentively: Implementing Respiratory Awareness Into Conversational Robots Open
View article: Live Football Commentary System Providing Background Information
Live Football Commentary System Providing Background Information Open
View article: Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation Open
View article: Dataset Distillation with Attention Labels for Fine-tuning BERT
Dataset Distillation with Attention Labels for Fine-tuning BERT Open
View article: DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation
DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation Open
View article: Contrastive Knowledge Distillation for Robust Multimodal Sentiment Analysis
Contrastive Knowledge Distillation for Robust Multimodal Sentiment Analysis Open
Multimodal sentiment analysis (MSA) systems leverage information from different modalities to predict human sentiment intensities. Incomplete modality is an important issue that may cause a significant performance drop in MSA systems. By g…
View article: Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation Open
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probability does not always lead to high translation quality. Minimum…
View article: DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation
DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation Open
Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text …
View article: Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition
Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition Open
View article: Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification
Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification Open
View article: Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition Open
Multimodal emotion recognition aims to recognize emotions for each utterance of multiple modalities, which has received increasing attention for its application in human-machine interaction. Current graph-based methods fail to simultaneous…
View article: Active Learning Based Fine-Tuning Framework for Speech Emotion Recognition
Active Learning Based Fine-Tuning Framework for Speech Emotion Recognition Open
Speech emotion recognition (SER) has drawn increasing attention for its applications in human-machine interaction. However, existing SER methods ignore the information gap between the pre-training speech recognition task and the downstream…
View article: Automatic Answerability Evaluation for Question Generation
Automatic Answerability Evaluation for Question Generation Open
Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for natural language generation (NLG) tasks, are based on measuring the n-gram overlap between the generated and reference text. These simple metrics may be insuf…
View article: Coherent Story Generation with Structured Knowledge
Coherent Story Generation with Structured Knowledge Open
The emergence of pre-trained language models has taken story generation, which is the task of automatically generating a comprehensible story from limited information, to a new stage.Although generated stories from the language models are …
View article: Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimoda Emotion Recognition
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimoda Emotion Recognition Open
Multimodal emotion recognition aims to recognize emotions for each utterance from multiple modalities, which has received increasing attention for its application in human-machine interaction. Current graph-based methods fail to simultaneo…
View article: Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization
Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization Open
Timeline summarization (TLS) is defined as a task for summarizing events in chronological order, which gives readers a comprehensive understanding of an evolutionary story. Previous studies on the timeline summarization (TLS) task ignored …
View article: LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation
LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation Open
A character sequence comprises at least one or more segmentation alternatives. This can be considered segmentation ambiguity and may weaken segmentation performance in word segmentation. Proper handling of such ambiguity lessens ambiguous …
View article: Generative Replay Inspired by Hippocampal Memory Indexing for Continual Language Learning
Generative Replay Inspired by Hippocampal Memory Indexing for Continual Language Learning Open
Continual learning aims to accumulate knowledge to solve new tasks without catastrophic forgetting for previously learned tasks. Research on continual learning has led to the development of generative replay, which prevents catastrophic fo…
View article: Plug-and-Play Attribute-Aware Text Infilling via A New Attention Mechanism and Two-Level Positional Encoding
Plug-and-Play Attribute-Aware Text Infilling via A New Attention Mechanism and Two-Level Positional Encoding Open
Text infilling aims to restore incomplete texts by filling in blanks and has attracted increasing attention recently because of its wide application in ancient text restoration, conversation generation, and text rewriting. However, attribu…
View article: Dataset Distillation with Attention Labels for Fine-tuning BERT
Dataset Distillation with Attention Labels for Fine-tuning BERT Open
Dataset distillation aims to create a small dataset of informative synthetic samples to rapidly train neural networks that retain the performance of the original dataset. In this paper, we focus on constructing distilled few-shot datasets …
View article: Generating Dialog Responses with Specified Grammatical Items for Second Language Learning
Generating Dialog Responses with Specified Grammatical Items for Second Language Learning Open
This paper proposes a new second language learning task of generating a response including specified grammatical items. We consider two approaches: 1) fine-tuning a pre-trained language model (DialoGPT) by reinforcement learning and 2) pro…
View article: Feedback comment generation using predicted grammatical terms
Feedback comment generation using predicted grammatical terms Open
View article: Non-Axiomatic Term Logic: A Theory of Cognitive Symbolic Reasoning
Non-Axiomatic Term Logic: A Theory of Cognitive Symbolic Reasoning Open
This paper presents Non-Axiomatic Term Logic (NATL) as a theoretical computational framework of humanlike symbolic reasoning in artificial intelligence. NATL unites a discrete syntactic system inspired from Aristotle's term logic and a con…
View article: Non-Axiomatic Term Logic: A Computational Theory of Cognitive Symbolic Reasoning
Non-Axiomatic Term Logic: A Computational Theory of Cognitive Symbolic Reasoning Open
This paper presents Non-Axiomatic Term Logic (NATL) as a theoretical computational framework of humanlike symbolic reasoning in artificial intelligence. NATL unites a discrete syntactic system inspired from Aristotle's term logic and a con…
View article: Generating Repetitions with Appropriate Repeated Words
Generating Repetitions with Appropriate Repeated Words Open
A repetition is a response that repeats words in the previous speaker's utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repeti…
View article: Generating Repetitions with Appropriate Repeated Words
Generating Repetitions with Appropriate Repeated Words Open
Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.
View article: Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization
Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization Open
Jingyi You, Dongyuan Li, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.
View article: Attitude towards Dialogue Robot as Interactional Practice
Attitude towards Dialogue Robot as Interactional Practice Open
The questions "How human-like is this dialogue robot?" and "How natural was the conversation with this dialogue robot?" are major concerns for dialogue robot researchers and developers. However, they have overlooked the way that unique con…
View article: Towards Table-to-Text Generation with Numerical Reasoning
Towards Table-to-Text Generation with Numerical Reasoning Open
Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, Hiroya Takamura. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural L…
View article: Generating Weather Comments from Numerical Weather Prediction
Generating Weather Comments from Numerical Weather Prediction Open
本研究では,数値気象予報のシミュレーション結果から天気予報コメントを自動生成するタスクに取り組む. 天気予報コメントの生成タスクには,(i) 様々な物理量の数値変化を考慮する必要がある,(ii) コメントの配信時刻や対象エリアに依存した表現が使われる,(iii) 天気予報コメントにおいて情報の有用性が重要視されている,といった特徴的な課題がある.本研究では,数値気象予報のシミュレーション結果,気象観測値,コメントのメタ情報を入力として, 上記の特徴を捉えた上でテキスト化する…