Papers by Yutao Zeng

11 papers
Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking (2022.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks for dialogue state tracking with domain-slot-value labels are expensive . current models are limited due to high cost of data annotation and lack of data in some domains .
Approach: They propose a framework based on domain-slot related description to tackle the challenge of few-shot cross-domain DST.
Outcome: The proposed framework outperforms existing methods on MultiWOZ and gains strong slot accuracy compared to existing models.
Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing Temporal Knowledge Graphs (TKGs) only contain their core entities and form them as quadruples.
Approach: They propose to describe a temporal fact more accurately as an n-tuple . they propose to use a neural network to learn evolutional representations of entities .
Outcome: The proposed model oversimplifies and causes information loss on two datasets.
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning (2022.acl-short)

Copied to clipboard

Challenge: Existing methods to find out out-of-domain (OOD) intents do not take prior knowledge of in-domain data into account.
Approach: They propose a disentangled knowledge transfer method to bridge the gap between IND pre-training and OOD clustering by using a unified multi-head contrastive learning framework.
Outcome: The proposed method is able to group new unknown intents into different clusters, enabling future development of the system.
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach: They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome: The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.
KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Copied to clipboard

Challenge: Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach: They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome: The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.
Value type: the bridge to a better DST model (2023.findings-acl)

Copied to clipboard

Challenge: Value type of the slots can provide lots of useful information for DST tasks. however, it has been ignored in most previous works.
Approach: They propose a new framework for DST task based on slot value type . they propose to extract the type of token from each turn and train a Ner model to extract corresponding type-entity from each conversation according to the token.
Outcome: The proposed framework is effective on two multi-domain task-oriented conversation datasets.
Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for event coreference resolution do not identify paraphrase relations between events.
Approach: They propose a new event-specific paraphrase and argument-aware semantic Embedding model for event coreference resolution based on event-related paraphrases and argument embeddings . EPASE recognizes deep paraphrase relations in an event- specific context of sentences and can cover event paraphrase of more situations .
Outcome: Experiments on within- and cross-document event coreference show it is superior compared to existing methods.
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for generalized intent discovery lack pseudo label disambiguation and representation learning.
Approach: They propose a prototype learning framework to decouple pseudo label disambiguation and representation learning.
Outcome: The proposed method can decouple pseudo label disambiguation and representation learning.
Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively.
Approach: They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions.
Outcome: The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions.
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for OOD detection are overconfident for OD samples . lack of labeled OOD examples leads to poor prior knowledge about these unknown intents, making it challenging to detect OOD samples.
Approach: They propose a Bayesian OOD detection framework to calibrate distribution uncertainty using Monte-Carlo Dropout.
Outcome: The proposed framework gains 33.33% OOD F1 improvements with increasing only 0.41% inference time compared to previous methods.

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