Papers by Haoyue Shi

8 papers
On Tree-Based Neural Sentence Modeling (D18-1)

Copied to clipboard

Challenge: Existing tree-based sentence modeling approaches adopt syntactic parsing trees as the explicit structure prior.
Approach: They replace parsing trees with trivial trees to study their effectiveness . they found that tree-based sentence modeling gives better results when crucial words are closer to the final representation .
Outcome: The proposed tree-based sentences have shown better results on many downstream tasks.
Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for bilingual lexicon induction are linear and require simplifying assumptions.
Approach: They propose methods that combine unsupervised bitext mining and unsupervised word alignment to produce higher quality lexicons.
Outcome: The proposed method outperforms the state-of-the-art on the BUCC 2020 task by 14 F1 points . further analysis suggests they are comparable quality .
Visually Grounded Neural Syntax Acquisition (P19-1)

Copied to clipboard

Challenge: a visually grounded neural syntax learner is an approach for learning syntactic representations without any supervision.
Approach: They propose a visually grounded neural syntax learner that acquires syntax by looking at images and reading captions.
Outcome: The proposed model outperforms unsupervised approaches on the MSCOCO data set . it is more stable with choice of initialization and amount of training data, the authors show .
Constructing High Quality Sense-specific Corpus and Word Embedding via Unsupervised Elimination of Pseudo Multi-sense (L18-1)

Copied to clipboard

Challenge: Existing word embedding frameworks distinguish different senses of words by their contexts.
Approach: They propose a framework for unsupervised corpus sense tagging which trains multi-sense word embeddings on a given corpus.
Outcome: The proposed framework detects pseudo multi-senses without extra language resources without additional language resources.
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions .
Approach: They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts.
Outcome: The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts.
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples (C18-1)

Copied to clipboard

Challenge: Existing frameworks for grounding distributional representations of texts on the visual domain are limited . effective and efficient grounding of distributional embeddings remains challenging .
Approach: They propose to ground distributional representations of texts on the visual domain using visual-semantic embeddings.
Outcome: The proposed model improves on a diverse set of downstream tasks and defends known-type adversarial attacks.
On the Role of Supervision in Unsupervised Constituency Parsing (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work on unsupervised constituency parsing uses labeled examples for tuning . a few-shot parser with labeles can outperform other approaches by a significant margin .
Approach: They propose to use as few labeled examples as possible for model development . they propose to train existing models on the same labeles they access .
Outcome: The proposed model outperforms other models on the WSJ development set by a significant margin . the proposed model can be further improved by augmentation and self-training .
Substructure Substitution: Structured Data Augmentation for NLP (2021.findings-acl)

Copied to clipboard

Challenge: Existing work focuses on word-level manipulation or global sequence-to-sequence style generation.
Approach: They propose a family of data augmentation methods that generalize prior methods by substituting substructures with others having the same label.
Outcome: The proposed methods can be applied to many structured NLP tasks such as part-of-speech tagging and parsing.

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