Search Results for author:
Found 69 papers, 25 papers with code
Scene-Text Aware Image and Text Retrieval with Dual-Encoder
We tackle the tasks of image and text retrieval using a dual-encoder model in which images and text are encoded independently.
SHAPE : Shifted Absolute Position Embedding for Transformers
Position representation is crucial for building position-aware representations in Transformers.
Seeing the World through Text: Evaluating Image Descriptions for Commonsense Reasoning in Machine Reading Comprehension
Despite recent achievements in natural language understanding, reasoning over commonsense knowledge still represents a big challenge to AI systems.
Tohoku-AIP-NTT at WMT 2020 News Translation Task
In this paper, we describe the submission of Tohoku-AIP-NTT to the WMT’20 news translation task.
ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper
In this year, we mainly build our systems based on Transformer architectures in all tasks and focus on the end-to-end speech translation (E2E-ST).
Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems
Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems.
Domain Adaptation of Machine Translation with Crowdworkers
With the collected parallel data, we can quickly adapt a machine translation model to the target domain.
Target-Guided Open-Domain Conversation Planning
Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning.
N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models
In this scenario, the quality of the n-best list considerably affects the occurrence of contradictions because the final response is chosen from this n-best list.
Balancing Cost and Quality: An Exploration of Human-in-the-loop Frameworks for Automated Short Answer Scoring
Towards guaranteeing high-quality predictions, we present the first study of exploring the use of human-in-the-loop framework for minimizing the grading cost while guaranteeing the grading quality by allowing a SAS model to share the grading task with a human grader.
On Layer Normalizations and Residual Connections in Transformers
In the perspective of a layer normalization (LN) position, the architecture of Transformers can be categorized into two types: Post-LN and Pre-LN.
Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
Ensembling is a popular method used to improve performance as a last resort.
Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond
Natural language processing technology has rapidly improved automated grammatical error correction tasks, and the community begins to explore document-level revision as one of the next challenges.
JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus
Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora.
Instance-Based Neural Dependency Parsing
Interpretable rationales for model predictions are crucial in practical applications.
SHAPE: Shifted Absolute Position Embedding for Transformers
Position representation is crucial for building position-aware representations in Transformers.
Context-aware Neural Machine Translation with Mini-batch Embedding
It is crucial to provide an inter-sentence context in Neural Machine Translation (NMT) models for higher-quality translation.
An Investigation Between Schema Linking and Text-to-SQL Performance
Text-to-SQL is a crucial task toward developing methods for understanding natural language by computers.
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
Quantum-state estimation problem via optimal design of experiments
We then extend a classical result in the design problem, the Kiefer-Wolfowitz theorem, to a qubit system showing the D-optimal design is equivalent to a certain type of the A-optimal design.
Quantum Physics
Efficient Estimation of Influence of a Training Instance
Understanding the influence of a training instance on a neural network model leads to improving interpretability.
PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents
Neural Machine Translation (NMT) has shown drastic improvement in its quality when translating clean input, such as text from the news domain.
Langsmith: An Interactive Academic Text Revision System
Despite the current diversity and inclusion initiatives in the academic community, researchers with a non-native command of English still face significant obstacles when writing papers in English.
A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction
Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets.
Preventing Critical Scoring Errors in Short Answer Scoring with Confidence Estimation
We introduce a new task formulation of SAS that matches the actual usage.
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition
In general, the labels used in sequence labeling consist of different types of elements.
Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction
The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC.
Ranked #2 on
Grammatical Error Correction
on JFLEG
Single Model Ensemble using Pseudo-Tags and Distinct Vectors
Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort.
Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese
We examine a methodology using neural language models (LMs) for analyzing the word order of language.
Word Rotator's Distance
Accordingly, we propose a method that first decouples word vectors into their norm and direction, and then computes alignment-based similarity using earth mover's distance (i. e., optimal transport cost), which we refer to as word rotator's distance.
Evaluating Dialogue Generation Systems via Response Selection
Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation.
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
Interpretable rationales for model predictions play a critical role in practical applications.
Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
Large-scale dialogue datasets have recently become available for training neural dialogue agents.
JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus
We constructed a parallel corpus for English-Japanese, for which the amount of publicly available parallel corpora is still limited.
NTT Neural Machine Translation Systems at WAT 2019
In this paper, we describe our systems that were submitted to the translation shared tasks at WAT 2019.
Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis
In transductive learning, an unlabeled test set is used for model training.
Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance
The writing process consists of several stages such as drafting, revising, editing, and proofreading.
Select and Attend: Towards Controllable Content Selection in Text Generation
As a result, the content to be described in the text cannot be explicitly controlled.
TEASPN: Framework and Protocol for Integrated Writing Assistance Environments
Language technologies play a key role in assisting people with their writing.
An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction
The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models.
The AIP-Tohoku System at the BEA-2019 Shared Task
We introduce the AIP-Tohoku grammatical error correction (GEC) system for the BEA-2019 shared task in Track 1 (Restricted Track) and Track 2 (Unrestricted Track) using the same system architecture.
Effective Adversarial Regularization for Neural Machine Translation
A regularization technique based on adversarial perturbation, which was initially developed in the field of image processing, has been successfully applied to text classification tasks and has yielded attractive improvements.
An Empirical Study of Span Representations in Argumentation Structure Parsing
For several natural language processing (NLP) tasks, span representation design is attracting considerable attention as a promising new technique; a common basis for an effective design has been established.
Character n-gram Embeddings to Improve RNN Language Models
This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information.
Subword-based Compact Reconstruction of Word Embeddings
The idea of subword-based word embeddings has been proposed in the literature, mainly for solving the out-of-vocabulary (OOV) word problem observed in standard word-based word embeddings.
Annotating with Pros and Cons of Technologies in Computer Science Papers
Specifically, we show how to adapt the targeted sentiment analysis task for pros/cons extraction in computer science papers and conduct an annotation study.
The Sally Smedley Hyperpartisan News Detector at SemEval-2019 Task 4
Our system achieved 80. 9{\%} accuracy on the test set for the formal run and got the 3rd place out of 42 teams.
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models
Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor.
Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework
We also demonstrate that our method has the more data, better performance property with promising scalability to the amount of unlabeled data.
NTT's Neural Machine Translation Systems for WMT 2018
This paper describes NTT{'}s neural machine translation systems submitted to the WMT 2018 English-German and German-English news translation tasks.
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC).
Direct Output Connection for a High-Rank Language Model
This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also from middle layers.
Ranked #8 on
Language Modelling
on Penn Treebank (Word Level)
Improving Neural Machine Translation by Incorporating Hierarchical Subword Features
We hypothesize that in the NMT model, the appropriate subword units for the following three modules (layers) can differ: (1) the encoder embedding layer, (2) the decoder embedding layer, and (3) the decoder output layer.
An Empirical Study of Building a Strong Baseline for Constituency Parsing
This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing.
Ranked #16 on
Constituency Parsing
on Penn Treebank
Interpretable Adversarial Perturbation in Input Embedding Space for Text
This paper restores interpretability to such methods by restricting the directions of perturbations toward the existing words in the input embedding space.
Source-side Prediction for Neural Headline Generation
The encoder-decoder model is widely used in natural language generation tasks.
NTT Neural Machine Translation Systems at WAT 2017
In this year, we participated in four translation subtasks at WAT 2017.
Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models.
Input-to-Output Gate to Improve RNN Language Models
This paper proposes a reinforcing method that refines the output layers of existing Recurrent Neural Network (RNN) language models.
Enumeration of Extractive Oracle Summaries
To analyze the limitations and the future directions of the extractive summarization paradigm, this paper proposes an Integer Linear Programming (ILP) formulation to obtain extractive oracle summaries in terms of ROUGE-N. We also propose an algorithm that enumerates all of the oracle summaries for a set of reference summaries to exploit F-measures that evaluate which system summaries contain how many sentences that are extracted as an oracle summary.
Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models.
Ranked #4 on
Text Summarization
on DUC 2004 Task 1
