Papers by Yuanmeng Yan

14 papers
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System (2021.acl-long)

Copied to clipboard

Challenge: Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set.
Approach: They introduce a task, Novel Slot Detection, in the task-oriented dialogue system.
Outcome: The proposed task is based on two public NSD datasets and proposes strong baselines . it aims to identify a sequence of tokens and extract semantic constituents from user queries .
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for zero-shot cross-domain slot filling do not achieve effective knowledge transfer to the target domain.
Approach: They propose a novel approach based on prototypical contrastive learning and a dynamic label confusion strategy for zero-shot slot filling.
Outcome: The proposed model improves on unseen slots while setting new state-of-the-arts on slot filling task.
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to zero-shot slot filling ignore constraints in the latent space and lack robustness.
Approach: They propose a Contrastive Zero-Shot Learning with Adversarial Attack method for slot filling . they propose to map slot value contextual representations to slot description representations .
Outcome: The proposed method outperforms state-of-the-art models under zero-shot and few-shot settings.
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning (2021.acl-short)

Copied to clipboard

Challenge: Existing methods of OOD detection only focus on whether a sample is correctly classified . lack of real OOD examples leads to poor prior knowledge about these unknown intents .
Approach: They propose a supervised contrastive learning objective to minimize intra-class variance . they employ an adversarial augmentation mechanism to obtain pseudo diverse views .
Outcome: The proposed method minimizes intra-class variance by pulling together in-domain intents belonging to the same class and maximizes inter-class variation by pushing apart samples from different classes.
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021.acl-long)

Copied to clipboard

Challenge: Existing BERT-based pre-trained language models achieve high performance on many downstream tasks, but native derived sentence representations are collapsed and thus poor performance on semantic textual similarity (STS) tasks.
Approach: They propose a framework for self-supervised Sentence Representation Transfer that adopts contrastive learning to fine-tune BERT in an unsupervised way.
Outcome: The proposed framework improves on the BERT-derived representations by 8% on STS datasets and shows robustness in data scarcity scenarios.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges.
Approach: They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections.
Outcome: Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete.
Rethinking the Word-level Quality Estimation for Machine Translation from Human Judgement (2023.findings-acl)

Copied to clipboard

Challenge: Word-level Quality Estimation (QE) of Machine Translation aims to detect potential translation errors in the translated sentence without reference.
Approach: They propose to use a human-generated translation judgment to generate a word-level quality estimate (QE) using a translation error rate toolkit to detect translation errors without reference.
Outcome: The proposed dataset is more consistent with human judgment and confirms the effectiveness of the proposed tag-correcting strategies.
Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots (2020.emnlp-main)

Copied to clipboard

Challenge: Open-vocabulary slots degrade neural-based slot filling models because they can take on unlimited set of values and have no semantic restriction nor length limit.
Approach: They propose a model-agnostic slot filling method that explicitly decouples local semantics inherent in open-vocabulary slot words from the global context.
Outcome: The proposed method outperforms other models on open-vocabulary slots without deteriorating performance.
Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to learn representations from text often reflect social biases . previous methods rely on pre-specified direction or suffer from unstable training .
Approach: They propose an adversarial disentangled debiasing model to decouple social bias attributes from intermediate representations trained on the main task.
Outcome: The proposed model decouples social bias attributes from intermediate representations trained on the main task.
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for OOD detection are based on labeled in-domain data . detecting out-of-domain (OOD) or unknown intents is challenging .
Approach: They propose a novel reassigned contrastive learning method to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents.
Outcome: The proposed method is effective for both aspects of overconfidence issues.
Learning to Tag OOV Tokens by Integrating Contextual Representation and Background Knowledge (2020.acl-main)

Copied to clipboard

Challenge: Recent context-aware models for slot tagging have achieved state-of-the-art performance . however, the presence of OOV( out-of vocab) words significantly degrades the performance of these models.
Approach: They propose a knowledge-enhanced slot tagging model to integrate contextual representation of input text and large-scale lexical background knowledge.
Outcome: The proposed model achieves consistent improvements across settings with different sizes of training data on two public benchmark datasets.
Adversarial Self-Supervised Learning for Out-of-Domain Detection (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for detecting out-of-domain (OOD) intents are unsupervised and require extensive labeled data.
Approach: They propose a self-supervised contrastive learning framework to model discriminative semantic features from unlabeled data.
Outcome: The proposed framework outperforms baseline methods on two public benchmark datasets with a statistically significant margin.
A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: Abstractive summarization models have achieved impressive results on document summarizing tasks, but their performance on dialogue modeling is poor due to the crude and straight methods for dialogue encoding.
Approach: They propose a model that leverages Finer-grain universal Dialogue semantic Structures to model dialogue and generate better summaries.
Outcome: The proposed model outperforms various dialogue summarization approaches and achieves state-of-the-art (SOTA) ROUGE results on a SAMsum dataset.
A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for detecting out-of-domain (OOD) intents rely on manually labeled samples . a strong generative distance-based classifier can detect OOD samples in task-oriented dialog systems .
Approach: They propose a generative distance-based classifier to detect out-of-domain (OOD) intents . they use Gaussian discriminant analysis to avoid over-confidence problems .
Outcome: The proposed method outperforms baseline methods on four benchmark datasets.

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