Search Results for author:
Found 37 papers, 9 papers with code
DIRECT: Direct and Indirect Responses in Conversational Text Corpus
We create a large-scale dialogue corpus that provides pragmatic paraphrases to advance technology for understanding the underlying intentions of users.
Distilling Word Meaning in Context from Pre-trained Language Models
The results confirm that our representations exhibited a competitive performance compared to that of the state-of-the-art method transforming contextualised representations for the context-aware lexical semantic tasks and outperformed it for STS estimation.
JADE: Corpus for Japanese Definition Modelling
This study investigated and released the JADE, a corpus for Japanese definition modelling, which is a technique that automatically generates definitions of a given target word and phrase.
Fine-Grained Error Analysis on English-to-Japanese Machine Translation in the Medical Domain
We performed a detailed error analysis in domain-specific neural machine translation (NMT) for the English and Japanese language pair with fine-grained manual annotation.
Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation
We propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation.
Compositional Phrase Alignment and Beyond
Most phrase alignments are compositional processes such that an alignment of a phrase pair is constructed based on the alignments of their child phrases.
Definition Modelling for Appropriate Specificity
Definition generation techniques aim to generate a definition of a target word or phrase given a context.
Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation
Experimental results on both quality estimation of machine translation and cross-lingual semantic textual similarity tasks reveal that our method consistently outperforms the strong baselines using the original multilingual embedding.
Cross-Lingual Semantic Textual Similarity
Machine Translation
+3
An In-depth Evaluation of GPT-4 in Sentence Simplification with Error-based Human Assessment
Second, current human evaluation approaches in sentence simplification often fall into two extremes: they are either too superficial, failing to offer a clear understanding of the models' performance, or overly detailed, making the annotation process complex and prone to inconsistency, which in turn affects the evaluation's reliability.
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters.
Unbalanced Optimal Transport for Unbalanced Word Alignment
Monolingual word alignment is crucial to model semantic interactions between sentences.
CEFR-Based Sentence Difficulty Annotation and Assessment
Controllable text simplification is a crucial assistive technique for language learning and teaching.
Edit Distance Based Curriculum Learning for Paraphrase Generation
Curriculum learning has improved the quality of neural machine translation, where only source-side features are considered in the metrics to determine the difficulty of translation.
Distinct Label Representations for Few-Shot Text Classification
Few-shot text classification aims to classify inputs whose label has only a few examples.
Text Simplification with Reinforcement Learning Using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity
We optimize rewards of reinforcement learning in text simplification using metrics that are highly correlated with human-perspectives.
Tiny Word Embeddings Using Globally Informed Reconstruction
We reduce the model size of pre-trained word embeddings by a factor of 200 while preserving its quality.
Consistent Response Generation with Controlled Specificity
To control the specificity of generated responses, we add the distant supervision based on the co-occurrence degree and a PMI-based word prediction mechanism to a sequence-to-sequence model.
A Corpus for English-Japanese Multimodal Neural Machine Translation with Comparable Sentences
Multimodal neural machine translation (NMT) has become an increasingly important area of research over the years because additional modalities, such as image data, can provide more context to textual data.
Lexically Cohesive Neural Machine Translation with Copy Mechanism
Lexically cohesive translations preserve consistency in word choices in document-level translation.
Text Classification with Negative Supervision
Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks.
Annotation of Adverse Drug Reactions in Patients' Weblogs
The dataset we present in this paper is unique for the richness of annotated information, including detailed descriptions of drug reactions with full context.
SAPPHIRE: Simple Aligner for Phrasal Paraphrase with Hierarchical Representation
To estimate the likelihood of phrase alignments, SAPPHIRE uses phrase embeddings that are hierarchically composed of word embeddings.
Natural Language Inference
Natural Language Understanding
+2
Contextualized context2vec
Herein we propose a method that combines these two approaches to contextualize word embeddings for lexical substitution.
Transfer Fine-Tuning: A BERT Case Study
It constitutes a set of tasks crucial for research on natural language understanding.
Relevant and Informative Response Generation using Pointwise Mutual Information
A sequence-to-sequence model tends to generate generic responses with little information for input utterances.
Responsive and Self-Expressive Dialogue Generation
Specifically, our model generates domain-aware and sentiment-rich responses.
Dialogue-Act Prediction of Future Responses Based on Conversation History
One significant drawback of such a neural network based approach is that the response generation process is a black-box, and how a specific response is generated is unclear.
Controllable Text Simplification with Lexical Constraint Loss
Our text simplification method succeeds in translating an input into a specific grade level by considering levels of both sentences and words.
Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation
Experiments show that the proposed method achieves comparable gain in translation quality to the state-of-the-art method but without a manual feature design.
Monolingual Phrase Alignment on Parse Forests
We propose an efficient method to conduct phrase alignment on parse forests for paraphrase detection.
