Search Results for author:
Found 71 papers, 22 papers with code
Contrastive Learning for Context-aware Neural Machine Translation Using Coreference Information
Context-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation.
Modality Alignment between Deep Representations for Effective Video-and-Language Learning
Our method directly optimizes CKA to make an alignment between video and text embedding representations, hence it aids the cross-modality attention module to combine information over different modalities.
Learning to Select Question-Relevant Relations for Visual Question Answering
Previous existing visual question answering (VQA) systems commonly use graph neural networks(GNNs) to extract visual relationships such as semantic relations or spatial relations.
ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT
In this paper, we propose an evaluation metric for image captioning systems using both image and text information.
Improving Multiple Documents Grounded Goal-Oriented Dialog Systems via Diverse Knowledge Enhanced Pretrained Language Model
In this paper, we mainly discuss about our submission to MultiDoc2Dial task, which aims to model the goal-oriented dialogues grounded in multiple documents.
Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers.
SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models
To mitigate these challenges, we propose SWITCH (Studying WIth TeaCHer for Knowledge Distillation), a novel approach that strategically incorporates the teacher model during the student's sequence generation.
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
Lastly, we observe that although existing methods struggle to balance the reduction of object hallucinations with maintaining text quality, SGD demonstrates robustness in handling this challenge.
Guaranteed Generation from Large Language Models
These experiments show that GUARD achieves perfect constraint satisfaction while almost preserving the ideal distribution with highly improved inference efficiency.
A Character-Centric Creative Story Generation via Imagination
To address this, we introduce a novel story generation framework called CCI (Character-centric Creative story generation via Imagination).
Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
Then, Jekyll \& Hyde collects two potential solutions from role-playing and neutral prompts and selects a better solution using the LLM evaluator.
Fine-grained Gender Control in Machine Translation with Large Language Models
In this paper, we tackle controlled translation in a more realistic setting of inputs with multiple entities and propose Gender-of-Entity (GoE) prompting method for LLMs.
VLind-Bench: Measuring Language Priors in Large Vision-Language Models
To this end, we propose a new benchmark called VLind-Bench, which is the first benchmark specifically designed to measure the language priors, or blindness, of LVLMs.
Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models.
Skeleton: A New Framework for Accelerating Language Models via Task Neuron Localized Prompt Tuning
Prompt tuning methods have shown comparable performance to general training methods as parameter-efficient fine-tuning (PEFT) methods in various natural language understanding tasks.
AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
Therefore, we've completed a benchmark encompassing daily life questions, diverse corresponding responses, and majority vote ranking to train our helpfulness metric.
MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs
Through quantitative and qualitative experiments, we demonstrate MP2D's efficacy in generating dialogue with natural topic shifts.
Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to detect the toxicity in the generated text.
LongStory: Coherent, Complete and Length Controlled Long story Generation
A human author can write any length of story without losing coherence.
LifeTox: Unveiling Implicit Toxicity in Life Advice
As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial.
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
Furthermore, we propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings.
IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance
To address these challenges, we propose Iterative Conversational Query Reformulation (IterCQR), a methodology that conducts query reformulation without relying on human rewrites.
Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
To address the data scarcity issue in Conversational question answering (ConvQA), a dialog inpainting method, which utilizes documents to generate ConvQA datasets, has been proposed.
Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering
The problem of spurious programs is a longstanding challenge when training a semantic parser from weak supervision.
DPP-TTS: Diversifying prosodic features of speech via determinantal point processes
Second, the diversity among samples is neglected since the sampling procedure often focuses on a single speech sample rather than multiple ones.
MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
However, the existing VMR framework evaluates video moment retrieval performance, assuming that a video is given, which may not reveal whether the models exhibit overconfidence in the falsely given video.
Asking Clarification Questions to Handle Ambiguity in Open-Domain QA
We first present CAMBIGNQ, a dataset consisting of 5, 654 ambiguous questions, each with relevant passages, possible answers, and a clarification question.
Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation
In this paper, we specifically target the gender bias issue of multilingual machine translation models for unambiguous cases where there is a single correct translation, and propose a bias mitigation method based on a novel approach.
Multi-View Zero-Shot Open Intent Induction from Dialogues: Multi Domain Batch and Proxy Gradient Transfer
In Task Oriented Dialogue (TOD) system, detecting and inducing new intents are two main challenges to apply the system in the real world.
PR-MCS: Perturbation Robust Metric for MultiLingual Image Captioning
Vulnerability to lexical perturbation is a critical weakness of automatic evaluation metrics for image captioning.
Varianceflow: High-Quality and Controllable Text-to-Speech using Variance Information via Normalizing Flow
Also, the objective function of NF makes the model use the variance information and the text in a disentangled manner resulting in more precise variance control.
Critic-Guided Decoding for Controlled Text Generation
In this work, we propose a novel critic decoding method for controlled language generation (CriticControl) that combines the strengths of reinforcement learning and weighted decoding.
Multimodal Speech Emotion Recognition using Cross Attention with Aligned Audio and Text
Then, the attention weights of each modality are applied directly to the other modality in a crossed way, so that the CAN gathers the audio and text information from the same time steps based on each modality.
Task-specific Compression for Multi-task Language Models using Attribution-based Pruning
However, these language models utilize an unnecessarily large number of model parameters, even when used only for a specific task.
Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking
To this end, the latest approach is to train a factual consistency classifier on factually consistent and inconsistent summaries.
Factual Error Correction for Abstractive Summaries Using Entity Retrieval
In this paper, we propose an efficient factual error correction system RFEC based on entities retrieval post-editing process.
CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models
Specifically, we employ a two-stage augmentation pipeline to generate new claims and evidences from existing samples.
Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information
We experimented with our method on common context-aware NMT models and two document-level translation tasks.
Self-Adapter at SemEval-2021 Task 10: Entropy-based Pseudo-Labeler for Source-free Domain Adaptation
Source-free domain adaptation is an emerging line of work in deep learning research since it is closely related to the real-world environment.
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
Also, we observe critical problems of the previous benchmark dataset (i. e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions.
Neural Sequence-to-grid Module for Learning Symbolic Rules
Logical reasoning tasks over symbols, such as learning arithmetic operations and computer program evaluations, have become challenges to deep learning.
Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech
Although early text-to-speech (TTS) models such as Tacotron 2 have succeeded in generating human-like speech, their autoregressive (AR) architectures have a limitation that they require a lot of time to generate a mel-spectrogram consisting of hundreds of steps.
Collaborative Training of GANs in Continuous and Discrete Spaces for Text Generation
Applying generative adversarial networks (GANs) to text-related tasks is challenging due to the discrete nature of language.
KPQA: A Metric for Generative Question Answering Using Keyphrase Weights
To evaluate our metric, we create high-quality human judgments of correctness on two GenQA datasets.
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language representations.
Drug-disease Graph: Predicting Adverse Drug Reaction Signals via Graph Neural Network with Clinical Data
In this study, we develop a novel graph-based framework for ADR signal detection using healthcare claims data.
BaitWatcher: A lightweight web interface for the detection of incongruent news headlines
In digital environments where substantial amounts of information are shared online, news headlines play essential roles in the selection and diffusion of news articles.
Attentive Modality Hopping Mechanism for Speech Emotion Recognition
In this work, we explore the impact of visual modality in addition to speech and text for improving the accuracy of the emotion detection system.
Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks
In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation.
Surf at MEDIQA 2019: Improving Performance of Natural Language Inference in the Clinical Domain by Adopting Pre-trained Language Model
While deep learning techniques have shown promising results in many natural language processing (NLP) tasks, it has not been widely applied to the clinical domain.
MILAB at SemEval-2019 Task 3: Multi-View Turn-by-Turn Model for Context-Aware Sentiment Analysis
This paper describes our system for SemEval-2019 Task 3: EmoContext, which aims to predict the emotion of the third utterance considering two preceding utterances in a dialogue.
A Compare-Aggregate Model with Latent Clustering for Answer Selection
In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing.
Ranked #8 on
Question Answering
on TrecQA
Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition
Recent studies have tried to use bidirectional LMs (biLMs) instead of conventional unidirectional LMs (uniLMs) for rescoring the $N$-best list decoded from the acoustic model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Speech Emotion Recognition Using Multi-hop Attention Mechanism
As opposed to using knowledge from both the modalities separately, we propose a framework to exploit acoustic information in tandem with lexical data.
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarchical Encoder
Some news headlines mislead readers with overrated or false information, and identifying them in advance will better assist readers in choosing proper news stories to consume.
Multimodal Speech Emotion Recognition Using Audio and Text
Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers.
Improving Neural Question Generation using Answer Separation
Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions.
Comparative Studies of Detecting Abusive Language on Twitter
However, this dataset has not been comprehensively studied to its potential.
Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks
We define the complexity and difficulty of a number sequence prediction task with the structure of the smallest automaton that can generate the sequence.
AttnConvnet at SemEval-2018 Task 1: Attention-based Convolutional Neural Networks for Multi-label Emotion Classification
In this paper, we propose an attention-based classifier that predicts multiple emotions of a given sentence.
Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering
In this paper, we propose a novel end-to-end neural architecture for ranking candidate answers, that adapts a hierarchical recurrent neural network and a latent topic clustering module.
Ranked #1 on
Answer Selection
on Ubuntu Dialogue (v1, Ranking)
Synonym Discovery with Etymology-based Word Embeddings
We test our model in the Chinese and Sino-Korean vocabularies.
Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network
In this paper, we propose an efficient transfer leaning methods for training a personalized language model using a recurrent neural network with long short-term memory architecture.
Partition-Merge: Distributed Inference and Modularity Optimization
This paper presents a novel meta algorithm, Partition-Merge (PM), which takes existing centralized algorithms for graph computation and makes them distributed and faster.
Efficient Energy Minimization for Enforcing Statistics
However, for many computer vision problems, the MAP solution under the model is not the ground truth solution.
Multi-dimensional Parametric Mincuts for Constrained MAP Inference
We show how this constrained discrete optimization problem can be formulated as a multi-dimensional parametric mincut problem via its Lagrangian dual, and prove that our algorithm isolates all constraint instances for which the problem can be solved exactly.
Local Rules for Global MAP: When Do They Work ?
We consider the question of computing Maximum A Posteriori (MAP) assignment in an arbitrary pair-wise Markov Random Field (MRF).
Local Algorithms for Approximate Inference in Minor-Excluded Graphs
We present a new local approximation algorithm for computing MAP and log-partition function for arbitrary exponential family distribution represented by a finite-valued pair-wise Markov random field (MRF), say G. Our algorithm is based on decomposing G into appropriately chosen small components; computing estimates locally in each of these components and then producing a good global solution.
