Search Results for author: Hidetaka Kamigaito

Found 88 papers, 31 papers with code

Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization

no code implementations NAACL 2022 Jingyi You, Dongyuan Li, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

Previous studies on the timeline summarization (TLS) task ignored the information interaction between sentences and dates, and adopted pre-defined unlearnable representations for them.

Event Detection Graph Attention +1

Improving Character-Aware Neural Language Model by Warming up Character Encoder under Skip-gram Architecture

no code implementations RANLP 2021 Yukun Feng, Chenlong Hu, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

Character-aware neural language models can capture the relationship between words by exploiting character-level information and are particularly effective for languages with rich morphology.

Language Modeling Language Modelling

Making Your Tweets More Fancy: Emoji Insertion to Texts

no code implementations RANLP 2021 Jingun Kwon, Naoki Kobayashi, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

The results demonstrate that the position of emojis in texts is a good clue to boost the performance of emoji label prediction.

Position Prediction

Abstractive Document Summarization with Word Embedding Reconstruction

no code implementations RANLP 2021 Jingyi You, Chenlong Hu, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

Neural sequence-to-sequence (Seq2Seq) models and BERT have achieved substantial improvements in abstractive document summarization (ADS) without and with pre-training, respectively.

Document Summarization Word Embeddings

SODA: Story Oriented Dense Video Captioning Evaluation Framework

1 code implementation ECCV 2020 Soichiro Fujita, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

This paper proposes a new evaluation framework, Story Oriented Dense video cAptioning evaluation framework (SODA), for measuring the performance of video story description systems.

Dense Video Captioning

Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability

no code implementations18 Jun 2025 Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

To address this, we propose Ordered CommonGen, a benchmark designed to evaluate the compositional generalization and instruction-following abilities of LLMs.

Diversity Instruction Following

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws

no code implementations29 May 2025 Hidetaka Kamigaito, Ying Zhang, Jingun Kwon, Katsuhiko Hayashi, Manabu Okumura, Taro Watanabe

Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws.

Diversity

IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation

no code implementations13 May 2025 Kazuki Hayashi, Hidetaka Kamigaito, Shinya Kouda, Taro Watanabe

Retrieval-Augmented Generation (RAG) has emerged as a way to complement the in-context knowledge of Large Language Models (LLMs) by integrating external documents.

RAG Retrieval +1

Long-Tail Crisis in Nearest Neighbor Language Models

no code implementations28 Mar 2025 Yuto Nishida, Makoto Morishita, Hiroyuki Deguchi, Hidetaka Kamigaito, Taro Watanabe

The $k$-nearest-neighbor language model ($k$NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference.

Language Modeling Language Modelling +2

Considering Length Diversity in Retrieval-Augmented Summarization

1 code implementation12 Mar 2025 Juseon-Do, Jaesung Hwang, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura

This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work.

Diversity Informativeness +1

Tonguescape: Exploring Language Models Understanding of Vowel Articulation

1 code implementation29 Jan 2025 Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

In this study, we created video and image datasets from the existing real-time MRI dataset and investigated whether LMs can understand vowel articulation based on tongue positions using vision-based information.

Can Impressions of Music be Extracted from Thumbnail Images?

no code implementations5 Jan 2025 Takashi Harada, Takehiro Motomitsu, Katsuhiko Hayashi, Yusuke Sakai, Hidetaka Kamigaito

In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs.

Retrieval

Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding

no code implementations19 Oct 2024 Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe

We also introduce a new MBR approach, Metric-augmented MBR (MAMBR), which increases diversity by adjusting the behavior of utility functions without altering the pseudo-references.

Diversity Text Generation

BQA: Body Language Question Answering Dataset for Video Large Language Models

no code implementations17 Oct 2024 Shintaro Ozaki, Kazuki Hayashi, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

To address this, we propose a dataset, BQA, a body language question answering dataset, to validate whether the model can correctly interpret emotions from short clips of body language comprising 26 emotion labels of videos of body language.

Question Answering

Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation

1 code implementation8 Sep 2024 Zhe Cao, Zhi Qu, Hidetaka Kamigaito, Taro Watanabe

Furthermore, we propose architecture learning techniques and introduce a gradual pruning schedule during fine-tuning to exhaustively explore the optimal setting and the minimal intrinsic subspaces for each language, resulting in a lightweight yet effective fine-tuning procedure.

Machine Translation

Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models

no code implementations3 Sep 2024 Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow.

Machine Translation Translation

Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates

no code implementations22 Aug 2024 Yusuke Sakai, Adam Nohejl, Jiangnan Hang, Hidetaka Kamigaito, Taro Watanabe

In this study, we provide English and Japanese cross-lingual datasets for evaluating the NLU performance of LLMs, which include multiple instruction templates for fair evaluation of each task, along with regular expressions to constrain the output format.

Natural Language Understanding

How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments

no code implementations19 Aug 2024 Yusuke Ide, Yuto Nishida, Miyu Oba, Yusuke Sakai, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe

The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is acceptable.

mbrs: A Library for Minimum Bayes Risk Decoding

1 code implementation8 Aug 2024 Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub.

Text Generation

Multi-Frame Vision-Language Model for Long-form Reasoning in Driver Behavior Analysis

no code implementations3 Aug 2024 Hiroshi Takato, Hiroshi Tsutsui, Komei Soda, Hidetaka Kamigaito

Identifying risky driving behavior in real-world situations is essential for the safety of both drivers and pedestrians.

Form Language Modeling +1

Multi-label Learning with Random Circular Vectors

1 code implementation8 Jul 2024 Ken Nishida, Kojiro Machi, Kazuma Onishi, Katsuhiko Hayashi, Hidetaka Kamigaito

The extreme multi-label classification~(XMC) task involves learning a classifier that can predict from a large label set the most relevant subset of labels for a data instance.

Extreme Multi-Label Classification MUlTI-LABEL-ClASSIFICATION +1

Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding

1 code implementation5 Jul 2024 Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

This paper provides theoretical interpretations of the smoothing methods for the NS loss in KGE and induces a new NS loss, Triplet Adaptive Negative Sampling (TANS), that can cover the characteristics of the conventional smoothing methods.

Knowledge Graph Embedding Knowledge Graphs +1

Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?

1 code implementation2 Jul 2024 Wataru Hashimoto, Hidetaka Kamigaito, Taro Watanabe

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks.

Data Augmentation named-entity-recognition +2

Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks

no code implementations2 Jul 2024 Wataru Hashimoto, Hidetaka Kamigaito, Taro Watanabe

Trustworthy prediction in Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs) is important for safety-critical applications in the real world.

Dimensionality Reduction named-entity-recognition +4

Towards Temporal Change Explanations from Bi-Temporal Satellite Images

no code implementations27 Jun 2024 Ryo Tsujimoto, Hiroki Ouchi, Hidetaka Kamigaito, Taro Watanabe

Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring.

Image Captioning

Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters

1 code implementation18 Jun 2024 Zhiyu Guo, Hidetaka Kamigaito, Taro Watanabe

Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e. g., book summarization.

All Book summarization

Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation

no code implementations17 Jun 2024 Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability.

Machine Translation NMT +2

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models

no code implementations16 Jun 2024 Juseon-Do, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura

For this purpose, we created new evaluation datasets by transforming traditional sentence compression datasets into an instruction format.

Extractive Summarization Sentence +1

mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans

no code implementations6 Jun 2024 Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

Constructed dataset is a benchmark for cross-lingual language-transfer capabilities of multilingual LMs, and experimental results showed high language-transfer capabilities for questions that LMs could easily solve, but lower transfer capabilities for questions requiring deep knowledge or commonsense.

Common Sense Reasoning Natural Language Understanding

Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models

no code implementations3 May 2024 Zhiyu Guo, Hidetaka Kamigaito, Taro Wanatnabe

The rapid advancement in Large Language Models (LLMs) has markedly enhanced the capabilities of language understanding and generation.

Computational Efficiency Model Compression +1

Context-Aware Machine Translation with Source Coreference Explanation

1 code implementation30 Apr 2024 Huy Hien Vu, Hidetaka Kamigaito, Taro Watanabe

Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases.

Machine Translation Translation

Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair

no code implementations18 Apr 2024 Yusuke Sakai, Mana Makinae, Hidetaka Kamigaito, Taro Watanabe

In Simultaneous Machine Translation (SiMT) systems, training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency systems.

Machine Translation Speech-to-Text +1

Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences

no code implementations31 Mar 2024 Jesse Atuhurra, Hidetaka Kamigaito

NLP systems are on par or, in some cases, better than humans at accomplishing specific tasks.

Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models

no code implementations29 Mar 2024 Jesse Atuhurra, Iqra Ali, Tatsuya Hiraoka, Hidetaka Kamigaito, Tomoya Iwakura, Taro Watanabe

Our contribution is four-fold: 1) we introduced nine vision-and-language (VL) tasks (including object recognition, image-text matching, and more) and constructed multilingual visual-text datasets in four languages: English, Japanese, Swahili, and Urdu through utilizing templates containing \textit{questions} and prompting GPT4-V to generate the \textit{answers} and the \textit{rationales}, 2) introduced a new VL task named \textit{unrelatedness}, 3) introduced rationales to enable human understanding of the VLM reasoning process, and 4) employed human evaluation to measure the suitability of proposed datasets for VL tasks.

Image-text matching Object Recognition +1

Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili

no code implementations26 Mar 2024 Jesse Atuhurra, Hiroyuki Shindo, Hidetaka Kamigaito, Taro Watanabe

Tokenization is one such technique because it allows for the words to be split based on characters or subwords, creating word embeddings that best represent the structure of the language.

Multilingual NLP Text Generation +1

Cross-lingual Contextualized Phrase Retrieval

1 code implementation25 Mar 2024 Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.

Contrastive Learning Language Modelling +4

Distilling Named Entity Recognition Models for Endangered Species from Large Language Models

no code implementations13 Mar 2024 Jesse Atuhurra, Seiveright Cargill Dujohn, Hidetaka Kamigaito, Hiroyuki Shindo, Taro Watanabe

Natural language processing (NLP) practitioners are leveraging large language models (LLM) to create structured datasets from semi-structured and unstructured data sources such as patents, papers, and theses, without having domain-specific knowledge.

In-Context Learning Knowledge Distillation +5

Can we obtain significant success in RST discourse parsing by using Large Language Models?

1 code implementation8 Mar 2024 Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura

Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks.

Decoder Discourse Parsing

Artwork Explanation in Large-scale Vision Language Models

no code implementations29 Feb 2024 Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks.

Explanation Generation Text Generation

Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?

1 code implementation22 Feb 2024 Seiji Gobara, Hidetaka Kamigaito, Taro Watanabe

Experimental results on the Stack-Overflow dataset and the TSCC dataset, including multi-turn conversation show that LLMs can implicitly handle text difficulty between user input and its generated response.

Question Answering

IRR: Image Review Ranking Framework for Evaluating Vision-Language Models

no code implementations19 Feb 2024 Kazuki Hayashi, Kazuma Onishi, Toma Suzuki, Yusuke Ide, Seiji Gobara, Shigeki Saito, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

We validate it using a dataset of images from 15 categories, each with five critic review texts and annotated rankings in both English and Japanese, totaling over 2, 000 data instances.

Diversity Image Captioning

Centroid-Based Efficient Minimum Bayes Risk Decoding

1 code implementation17 Feb 2024 Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka, Masao Utiyama

Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.

de-en Translation

Generating Diverse Translation with Perturbed kNN-MT

no code implementations14 Feb 2024 Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe

Generating multiple translation candidates would enable users to choose the one that satisfies their needs.

Diversity Machine Translation +1

Model-based Subsampling for Knowledge Graph Completion

1 code implementation17 Sep 2023 Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets.

Knowledge Graph Completion Knowledge Graph Embedding +1

Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models

1 code implementation3 Jun 2023 Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

This task consists of two parts: the first is to generate a table containing knowledge about an entity and its related image, and the second is to generate an image from an entity with a caption and a table containing related knowledge of the entity.

Articles Image Generation

LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation

2 code implementations Journal of Natural Language Processing 2023 Thodsaporn Chay-intr, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

Our model employs the lattice structure to handle segmentation alternatives and utilizes graph neural networks along with an attention mechanism to attentively extract multi-granularity representation from the lattice for complementing character representations.

 Ranked #1 on Chinese Word Segmentation on CTB6 (using extra training data)

Chinese Word Segmentation Japanese Word Segmentation +2

Bidirectional Transformer Reranker for Grammatical Error Correction

1 code implementation22 May 2023 Ying Zhang, Hidetaka Kamigaito, Manabu Okumura

Pre-trained seq2seq models have achieved state-of-the-art results in the grammatical error correction task.

Decoder Grammatical Error Correction +5

A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing

1 code implementation15 Oct 2022 Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results.

Discourse Parsing

Subsampling for Knowledge Graph Embedding Explained

no code implementations13 Sep 2022 Hidetaka Kamigaito, Katsuhiko Hayashi

In this article, we explain the recent advance of subsampling methods in knowledge graph embedding (KGE) starting from the original one used in word2vec.

Knowledge Graph Embedding

Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning

1 code implementation21 Jun 2022 Hidetaka Kamigaito, Katsuhiko Hayashi

To solve this problem, we theoretically analyzed NS loss to assist hyperparameter tuning and understand the better use of the NS loss in KGE learning.

Knowledge Graph Embedding

Aspect-based Analysis of Advertising Appeals for Search Engine Advertising

no code implementations NAACL (ACL) 2022 Soichiro Murakami, Peinan Zhang, Sho Hoshino, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

Writing an ad text that attracts people and persuades them to click or act is essential for the success of search engine advertising.

Why does Negative Sampling not Work Well? Analysis of Convexity in Negative Sampling

no code implementations29 Sep 2021 Hidetaka Kamigaito, Katsuhiko Hayashi

On the other hand, properties of the NS loss function that are considered important for learning, such as the relationship between the noise distribution and the number of negative samples, have not been investigated theoretically.

Computational Efficiency Knowledge Graph Embedding

Towards Table-to-Text Generation with Numerical Reasoning

1 code implementation ACL 2021 Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, Hiroya Takamura

In summary, our contributions are (1) a new dataset for numerical table-to-text generation using pairs of a table and a paragraph of a table description with richer inference from scientific papers, and (2) a table-to-text generation framework enriched with numerical reasoning.

Descriptive Table-to-Text Generation

Improving Neural RST Parsing Model with Silver Agreement Subtrees

no code implementations NAACL 2021 Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

We then pre-train a neural RST parser with the obtained silver data and fine-tune it on the RST-DT.

 Ranked #1 on Discourse Parsing on RST-DT (RST-Parseval (Relation) metric, using extra training data)

Discourse Parsing Relation

An Empirical Study of Generating Texts for Search Engine Advertising

no code implementations NAACL 2021 Hidetaka Kamigaito, Peinan Zhang, Hiroya Takamura, Manabu Okumura

Although there are many studies on neural language generation (NLG), few trials are put into the real world, especially in the advertising domain.

Text Generation

A New Surprise Measure for Extracting Interesting Relationships between Persons

no code implementations EACL 2021 Hidetaka Kamigaito, Jingun Kwon, Young-In Song, Manabu Okumura

We therefore propose a method for extracting interesting relationships between persons from natural language texts by focusing on their surprisingness.

Articles

Generating Weather Comments from Meteorological Simulations

1 code implementation EACL 2021 Soichiro Murakami, Sora Tanaka, Masatsugu Hangyo, Hidetaka Kamigaito, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura

The task of generating weather-forecast comments from meteorological simulations has the following requirements: (i) the changes in numerical values for various physical quantities need to be considered, (ii) the weather comments should be dependent on delivery time and area information, and (iii) the comments should provide useful information for users.

Informativeness

Top-Down RST Parsing Utilizing Granularity Levels in Documents

1 code implementation3 Apr 2020 Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures.

Ranked #3 on Discourse Parsing on RST-DT (RST-Parseval (Span) metric)

Discourse Parsing Relation

Syntactically Look-Ahead Attention Network for Sentence Compression

1 code implementation4 Feb 2020 Hidetaka Kamigaito, Manabu Okumura

Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words.

Decoder Informativeness +2

Split or Merge: Which is Better for Unsupervised RST Parsing?

no code implementations IJCNLP 2019 Naoki Kobayashi, Tsutomu Hirao, Kengo Nakamura, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones.

Context-aware Neural Machine Translation with Coreference Information

no code implementations WS 2019 Takumi Ohtani, Hidetaka Kamigaito, Masaaki Nagata, Manabu Okumura

We present neural machine translation models for translating a sentence in a text by using a graph-based encoder which can consider coreference relations provided within the text explicitly.

Machine Translation Sentence +1

Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization

no code implementations RANLP 2019 Tatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

To incorporate the information of a discourse tree structure into the neural network-based summarizers, we propose a discourse-aware neural extractive summarizer which can explicitly take into account the discourse dependency tree structure of the source document.

Document Summarization Sentence

Higher-Order Syntactic Attention Network for Longer Sentence Compression

no code implementations NAACL 2018 Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Masaaki Nagata

To solve this problem, we propose a higher-order syntactic attention network (HiSAN) that can handle higher-order dependency features as an attention distribution on LSTM hidden states.

Informativeness Machine Translation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.