Search Results for author:
Found 114 papers, 33 papers with code
Predicting Antonyms in Context using BERT
We address the task of antonym prediction in a context, which is a fill-in-the-blanks problem.
Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks
We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for MLMs, and find that there exists only a weak correlation between these two types of evaluation measures.
OpenKorPOS: Democratizing Korean Tokenization with Voting-Based Open Corpus Annotation
As this problem originates from the conventional scheme used when creating a POS tagging corpus, we propose an improvement to the existing scheme, which makes it friendlier to generative tasks.
Field Experiments of Real Time Foreign News Distribution Powered by MT
The second technology is machine translation (MT), which enables users to read foreign news articles in their mother language.
PatchBERT: Just-in-Time, Out-of-Vocabulary Patching
Large scale pre-trained language models have shown groundbreaking performance improvements for transfer learning in the domain of natural language processing.
IMPARA: Impact-Based Metric for GEC Using Parallel Data
Correlations between IMPARA and human scores indicate that IMPARA is comparable or better than existing evaluation methods.
Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks
We adopt table representations to model the entities and relations, casting the entity and relation extraction as a table-labeling problem.
Word-level Perturbation Considering Word Length and Compositional Subwords
We present two simple modifications for word-level perturbation: Word Replacement considering Length (WR-L) and Compositional Word Replacement (CWR). In conventional word replacement, a word in an input is replaced with a word sampled from the entire vocabulary, regardless of the length and context of the target word. WR-L considers the length of a target word by sampling words from the Poisson distribution. CWR considers the compositional candidates by restricting the source of sampling to related words that appear in subword regularization. Experimental results showed that the combination of WR-L and CWR improved the performance of text classification and machine translation.
Distributional Properties of Subword Regularization
Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training.
HMoE: Heterogeneous Mixture of Experts for Language Modeling
To address the imbalance in expert activation, we propose a novel training objective that encourages the frequent activation of smaller experts, enhancing computational efficiency and parameter utilization.
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).
Social Bias Evaluation for Large Language Models Requires Prompt Variations
In this paper, we investigate the sensitivity of LLMs when changing prompt variations (task instruction and prompt, few-shot examples, debias-prompt) by analyzing task performance and social bias of LLMs.
Building a Large Japanese Web Corpus for Large Language Models
Open Japanese large language models (LLMs) have been trained on the Japanese portions of corpora such as CC-100, mC4, and OSCAR.
Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities
The results showed that the efficiency gained through vocabulary expansion had no negative impact on performance, except for the summarization task, and that the combined use of parallel corpora enhanced translation ability.
Building a Japanese Document-Level Relation Extraction Dataset Assisted by Cross-Lingual Transfer
In our proposal, annotators edit relation predictions from a model trained on the transferred dataset.
Sampling-based Pseudo-Likelihood for Membership Inference Attacks
In this study, we propose a Sampling-based Pseudo-Likelihood (\textbf{SPL}) method for MIA (\textbf{SaMIA}) that calculates SPL using only the text generated by an LLM to detect leaks.
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords.
Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction
Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical.
Likelihood-based Mitigation of Evaluation Bias in Large Language Models
In this paper, we investigate the presence and impact of likelihood bias in LLM-based evaluators.
Two Counterexamples to Tokenization and the Noiseless Channel
In Tokenization and the Noiseless Channel (Zouhar et al., 2023a), R\'enyi efficiency is suggested as an intrinsic mechanism for evaluating a tokenizer: for NLP tasks, the tokenizer which leads to the highest R\'enyi efficiency of the unigram distribution should be chosen.
Knowledge of Pretrained Language Models on Surface Information of Tokens
Do pretrained language models have knowledge regarding the surface information of tokens?
Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting
In this study, we examine the impact of LLMs' step-by-step predictions on gender bias in unscalable tasks.
SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks
Large Language Models (LLMs) can justify or critique their predictions through discussions with other models or humans, thereby enriching their intrinsic understanding of instances.
How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection
Finally, our analysis indicates that the high instruction-following ability of LLMs fosters the large impact of such constraints on detection performance.
Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering
Besides, diverse interpretations of the input lead to various modes of answer generation, highlighting the role of causal reasoning between interpreting and answering steps in VQA.
Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction
Generating explanations for GEC corrections involves aligning input and output tokens, identifying correction points, and presenting corresponding explanations consistently.
Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels
In Natural Language Inference (NLI), existing bias evaluation methods have focused on the prediction results of one specific label out of three labels, such as neutral.
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated
In this study, we compare the impact of debiasing on performance across multiple downstream tasks using a wide-range of benchmark datasets that containing female, male, and stereotypical words.
OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples
Experiments in the domain of student essays show that the proposed detector improves the detection performance on the attacker-generated texts by up to +41. 3 points F1-score.
Generative Data Augmentation for Aspect Sentiment Quad Prediction
Aspect sentiment quad prediction (ASQP) analyzes the aspect terms, opinion terms, sentiment polarity, and aspect categories in a text.
Ranked #3 on
Aspect-Based Sentiment Analysis (ABSA)
on ASQP
SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning
Automating figure caption generation helps move model understandings of scientific documents beyond text and will help authors write informative captions that facilitate communicating scientific findings.
Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods
Large-scale pre-trained language models such as GPT-3 have shown remarkable performance across various natural language processing tasks.
Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach
Humans work together to solve common problems by having discussions, explaining, and agreeing or disagreeing with each other.
Reducing Sequence Length by Predicting Edit Operations with Large Language Models
Experiments show that the proposed method achieves comparable performance to the baseline in four tasks, paraphrasing, formality style transfer, GEC, and text simplification, despite reducing the length of the target text by as small as 21%.
Semantic Specialization for Knowledge-based Word Sense Disambiguation
A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a target word in a given sentence.
DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction
First, we propose DREEAM, a memory-efficient approach that adopts evidence information as the supervisory signal, thereby guiding the attention modules of the DocRE system to assign high weights to evidence.
Ranked #1 on
Relation Extraction
on ReDocRED
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples
Prior works have relied on human annotated examples to compare existing intrinsic bias evaluation measures.
Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps
We conducted experiments using our method on datasets with a large vocabulary gap from a source domain.
Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks
We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists only a weak correlation between these two types of evaluation measures.
Nearest Neighbor Non-autoregressive Text Generation
In addition, the proposed method outperforms an NAR baseline on the WMT'14 En-De dataset.
Are Neighbors Enough? Multi-Head Neural n-gram can be Alternative to Self-attention
Impressive performance of Transformer has been attributed to self-attention, where dependencies between entire input in a sequence are considered at every position.
PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation
However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data.
Gender Bias in Meta-Embeddings
Different methods have been proposed to develop meta-embeddings from a given set of source embeddings.
Gender Bias in Masked Language Models for Multiple Languages
Unfortunately, it was reported that MLMs also learn discriminative biases regarding attributes such as gender and race.
Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation
Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models.
Semi-Supervised Formality Style Transfer with Consistency Training
In this work, we propose a simple yet effective semi-supervised framework to better utilize source-side unlabeled sentences based on consistency training.
Ranked #1 on
Formality Style Transfer
on GYAFC
(using extra training data)
Interpretability for Language Learners Using Example-Based Grammatical Error Correction
In this study, we introduce an Example-Based GEC (EB-GEC) that presents examples to language learners as a basis for a correction result.
Learning How to Translate North Korean through South Korean
Training a model using North Korean data is the most straightforward approach to solving this problem, but there is insufficient data to train NMT models.
ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization
Through experiments, we show that ExtraPhrase improves the performance of abstractive summarization tasks by more than 0. 50 points in ROUGE scores compared to the setting without data augmentation.
Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation
We further introduce logical form generation (LG), a dual task of Logic2text that requires generating a valid logical form based on a text description of a table.
Transformer-based Lexically Constrained Headline Generation
We also consider a new headline generation strategy that takes advantage of the controllable generation order of Transformer.
Behavioral Testing of Knowledge Graph Embedding Models for Link Prediction
With an extensive set of experiments, we perform and analyze these tests for several KGE models.
Joint Optimization of Tokenization and Downstream Model
Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the performance.
You May Like This Hotel Because ...: Identifying Evidence for Explainable Recommendations
To tackle the challenge, this paper proposes a novel and practical task to explain evidences in recommending hotels given vague requests expressed freely in natural language.
TextLearner at SemEval-2020 Task 10: A Contextualized Ranking System in Solving Emphasis Selection in Text
This paper describes the emphasis selection system of the team TextLearner for SemEval 2020 Task 10: Emphasis Selection For Written Text in Visual Media.
Image Caption Generation for News Articles
In this paper, we address the task of news-image captioning, which generates a description of an image given the image and its article body as input.
SWAGex at SemEval-2020 Task 4: Commonsense Explanation as Next Event Prediction
We describe the system submitted by the SWAGex team to the SemEval-2020 Commonsense Validation and Explanation Task.
Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs
Large-scale pretraining and task-specific fine-tuning is now the standard methodology for many tasks in computer vision and natural language processing.
Optimizing Word Segmentation for Downstream Task
In traditional NLP, we tokenize a given sentence as a preprocessing, and thus the tokenization is unrelated to a target downstream task.
Multi-Task Learning for Cross-Lingual Abstractive Summarization
Experimental results indicate that Transum improves the performance from the strong baseline, Transformer, in Chinese-English, Arabic-English, and English-Japanese translation datasets.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+4
Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations
In this study, a novel method for extracting named entities and relations from unstructured text based on the table representation is presented.
Ranked #3 on
Relation Extraction
on CoNLL04
(NER Micro F1 metric)
Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020
Video-guided machine translation as one of multimodal neural machine translation tasks targeting on generating high-quality text translation by tangibly engaging both video and text.
It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
The performance of neural machine translation systems is commonly evaluated in terms of BLEU.
Improving Truthfulness of Headline Generation
Building a binary classifier that predicts an entailment relation between an article and its headline, we filter out untruthful instances from the supervision data.
Evaluation Dataset for Zero Pronoun in Japanese to English Translation
Therefore, we present a hand-crafted dataset to evaluate whether translation models can resolve the zero pronoun problems in Japanese to English translations.
Jamo Pair Encoding: Subcharacter Representation-based Extreme Korean Vocabulary Compression for Efficient Subword Tokenization
In the context of multilingual language model pre-training, vocabulary size for languages with a broad set of potential characters is an unsolved problem.
Neural Question Generation using Interrogative Phrases
One of the key requirements of QG is to generate a question such that it results in a target answer.
Enhancing Machine Translation with Dependency-Aware Self-Attention
Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism.
Learning to Select, Track, and Generate for Data-to-Text
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
TokyoTech\_NLP at SemEval-2019 Task 3: Emotion-related Symbols in Emotion Detection
This paper presents our contextual emotion detection system in approaching the SemEval2019 shared task 3: EmoContext: Contextual Emotion Detection in Text.
Positional Encoding to Control Output Sequence Length
Neural encoder-decoder models have been successful in natural language generation tasks.
Ranked #2 on
Text Summarization
on DUC 2004 Task 1
A Large-Scale Multi-Length Headline Corpus for Analyzing Length-Constrained Headline Generation Model Evaluation
However, because there is no corpus of headlines of multiple lengths for a given article, previous research on controlling output length in headline generation has not discussed whether the system outputs could be adequately evaluated without multiple references of different lengths.
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.
Investigating the Challenges of Temporal Relation Extraction from Clinical Text
Temporal reasoning remains as an unsolved task for Natural Language Processing (NLP), particularly demonstrated in the clinical domain.
Predicting Stances from Social Media Posts using Factorization Machines
This paper presents an approach to detect the stance of a user toward a topic based on their stances toward other topics and the social media posts of the user.
Source-side Prediction for Neural Headline Generation
The encoder-decoder model is widely used in natural language generation tasks.
A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations
Our coverage result of 74. 6% indicates that argumentative relations can reasonably be explained by our small pattern set.
Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction
This paper explores the idea of robot editors, automated proofreaders that enable journalists to improve the quality of their articles.
A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models.
Analyzing the Revision Logs of a Japanese Newspaper for Article Quality Assessment
We address the issue of the quality of journalism and analyze daily article revision logs from a Japanese newspaper company.
Composing Distributed Representations of Relational Patterns
Learning distributed representations for relation instances is a central technique in downstream NLP applications.
Other Topics You May Also Agree or Disagree: Modeling Inter-Topic Preferences using Tweets and Matrix Factorization
We present in this paper our approach for modeling inter-topic preferences of Twitter users: for example, those who agree with the Trans-Pacific Partnership (TPP) also agree with free trade.
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
Automatic video description generation has recently been getting attention after rapid advancement in image caption generation.
Modeling Discourse Segments in Lyrics Using Repeated Patterns
This study proposes a computational model of the discourse segments in lyrics to understand and to model the structure of lyrics.
Modeling Context-sensitive Selectional Preference with Distributed Representations
This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP).
Learning Semantically and Additively Compositional Distributional Representations
This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS).
The Mechanism of Additive Composition
Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitchell and Lapata, 2010) is a widely used method for computing meanings of phrases, which takes the average of vector representations of the constituent words.
