Papers by Gary Geunbae Lee

8 papers
Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling (2024.lrec-main)

Copied to clipboard

Challenge: Existing models that generate complex questions do not explain reasoning process behind generated multi-hop questions.
Approach: They propose an end-to-end question rewriting model that increases question complexity through sequential rewrite.
Outcome: The proposed model generates complex questions that require multi-step reasoning over multiple documents.
Out-of-domain Detection based on Generative Adversarial Network (D18-1)

Copied to clipboard

Challenge: Existing methods for out-of-domain (OOD) detection require huge effort to collect OOD sentences.
Approach: They propose to use only in-domain (IND) sentences to build a generative adversarial network (GAN) of which the discriminator generates low scores for OOD sentences.
Outcome: The proposed method is most accurate compared to existing methods on multi-domain dialog systems.
Conversational QA Dataset Generation with Answer Revision (2022.coling-1)

Copied to clipboard

Challenge: Existing frameworks for conversational question-answer generation generate a large-scale dataset based on input passages.
Approach: They propose a conversational question-answer generation framework that extracts question-worthy phrases from passages and generates corresponding questions considering previous conversations.
Outcome: The proposed framework improves the quality of synthetic data and can be used for domain adaptation of conversational question answering.
Leveraging the Interplay between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation (2024.lrec-main)

Copied to clipboard

Challenge: despite recent advances in speech synthesis, the focus of research has been on high-resource languages like English.
Approach: They propose a framework that incorporates modeling of syntactic and acoustic cues associated with pausing patterns.
Outcome: The proposed framework generates natural speech even for longer and intricate out-of-domain sentences, despite training on short audio clips.
Denoising Table-Text Retrieval for Open-Domain Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies in table-text open-domain question answering have problems with false-positive labels in training datasets.
Approach: They propose a denoised table-text retriever that discards false positives from training datasets . they integrate table-level ranking information into the retriever to assist in finding evidence .
Outcome: The proposed method outperforms baselines on retrieval recall and QA tasks.
Schema Encoding for Transferable Dialogue State Tracking (2022.coling-1)

Copied to clipboard

Challenge: Recent work has focused on deep neural models for task-oriented dialogue systems . however, the neural models require a large dataset for training and a new dataset to be trained on another domain.
Approach: They propose a schema encoder for transferable dialogue state tracking to new domains . they aim to transfer the model to new datasets by encoding new schemas based on the dataset .
Outcome: The proposed method improves the accuracy of the proposed model on multi-domain settings.
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring (2023.findings-acl)

Copied to clipboard

Challenge: Existing systems assume to grade essays on same prompt as used in training and assign only a holistic score.
Approach: They propose a prompt- and trait relation-aware cross-prompt essay trait scorer that encodes prompt-awful essay representation by essay-promotion attention and utilizing the topic-coherence feature extracted by the topic model.
Outcome: The proposed model shows state-of-the-art results for all prompts and traits.
Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions (2022.aacl-short)

Copied to clipboard

Challenge: Conversational question answering (CQA) aims to answer a question based on a given passage and previous conversation.
Approach: They propose a method to synthesize data for CQA with various question types . they propose 'hierarchical answerability classification' module that improves quality of synthetic data while acquiring unanswerable questions.
Outcome: The proposed framework improves quality of synthetic data while acquiring unanswerable questions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations