Papers by Hongliang Fei

6 papers
Denoising Enhanced Distantly Supervised Ultrafine Entity Typing (2023.findings-acl)

Copied to clipboard

Challenge: Recent work on distantly supervised (DS) ultra-fine entity typing has received significant attention . however, DS data is noisy and often suffers from missing or wrong labeling issues resulting in low precision and low recall.
Approach: They propose a noise model to estimate unknown labeling noise distribution over input contexts and noisy type labels and a model to train on denoised data.
Outcome: The proposed model outperforms baseline methods on the Ultra-Fine entity typing dataset and OntoNotes dataset.
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in disentanglement work on coarse levels in the disenanglement of closely related properties, such as syntax and semantics in human languages.
Approach: They propose a deep decomposable model based on VAE to disentangle syntax and semantics by using total correlation penalties on KL divergences.
Outcome: The proposed model significantly improves the disentanglement quality between syntactic and semantic representations for semantic similarity tasks and syntaktic similarity task.
End-to-end Deep Reinforcement Learning Based Coreference Resolution (P19-1)

Copied to clipboard

Challenge: Recent neural network models for coreference resolution are usually trained with heuristic loss functions that are computed over a sequence of local decisions.
Approach: They propose an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics.
Outcome: The proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.
PromptGen: Automatically Generate Prompts using Generative Models (2022.findings-naacl)

Copied to clipboard

Challenge: Recent prompt learning has received significant attention, where downstream tasks are reformulated to the mask-filling task with the help of a textual prompt.
Approach: They propose a model PromptGen which can automatically generate prompts conditional on the input sentence.
Outcome: The proposed model outperforms baseline models on the knowledge probing LAMA benchmark.
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval (2021.naacl-main)

Copied to clipboard

Challenge: Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English.
Approach: They propose a new approach to learn cross-lingual cross-modal representations for matching images and captions in multiple languages using an annotated corpus.
Outcome: The proposed model achieves impressive performance on two multimodal multilingual image caption benchmarks: Multi30k with German captions and MSCOCO with Japanese captions.
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning (2020.acl-main)

Copied to clipboard

Challenge: Recent neural network models have achieved impressive performance on sentiment classification in English and other languages.
Approach: They propose an unsupervised sentiment classification model that leverages an uncontrolled machine translation system and a language discriminator to learn a shared representation.
Outcome: The proposed model outperforms other models on five language pairs.

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