Papers by Zhiyang Teng

13 papers
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation (2020.emnlp-main)

Copied to clipboard

Challenge: AMR-to-text generation is used to transduce Abstract Meaning Representation structures (AMRs) Graph Convolution Networks (GCNs) are not able to capture non-local information and follow a local (first-order) information aggregation scheme.
Approach: They propose a dynamic fusion mechanism that captures richer non-local interactions . they propose weight tied convolutions and group graph convolution to reduce memory usage .
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets with significantly fewer parameters while maintaining the model capacity.
G-Transformer for Document-Level Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Existing work extends translation unit from single sentence to multiple sentences.
Approach: They propose to introduce locality assumption as an inductive bias into Transformer and reduce the hypothesis space of attention from target to source.
Outcome: The proposed model achieves state-of-the-art BLEU scores on three benchmark datasets.
Two Local Models for Neural Constituent Parsing (C18-1)

Copied to clipboard

Challenge: Non-local features have been shown crucial for statistical parsing, but local models can give highly competitive accuracies thanks to the power of dense neural input representations.
Approach: They propose to use local neural models for constituent parsing to capture dependencies between sub output structures and to exploit non-local features.
Outcome: The proposed model achieves labeled bracketing F1 scores of 92.4% on PTB and 87.3% on CTB 5.1.
YATO: Yet Another deep learning based Text analysis Open toolkit (2023.emnlp-demo)

Copied to clipboard

Challenge: YATO is an open-source toolkit for text analysis with deep learning . it supports free combinations of three types of widely used features .
Approach: They introduce YATO, an open-source toolkit for text analysis with deep learning.
Outcome: YATO is an open-source toolkit for text analysis with deep learning . the toolkit supports free combinations of three types of widely used features .
Non-Autoregressive Document-Level Machine Translation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing non-autoregressive translation models struggle with document context and handling discourse phenomena.
Approach: They propose a simple but effective design of sentence alignment between source and target to improve their performance on document-level machine translation.
Outcome: The proposed model achieves high acceleration on documents and sentence alignment significantly enhances their performance.
Exploring Self-supervised Logic-enhanced Training for Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Traditional attempts to enhance the logical reasoning abilities of language models often rely on supervised fine-tuning, limiting their generalization to new tasks or domains.
Approach: They propose a framework for integrating logical reasoning capabilities into LLMs and activating them via in-context learning.
Outcome: The proposed framework achieves comparable results to existing models on three language understanding benchmarks.
Inducing Target-Specific Latent Structures for Aspect Sentiment Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Aspect-level sentiment analysis aims to classify the sentiment polarity of an aspect or a target in a comment . graph convolutional networks can be used to classifice aspect terms in syllables .
Approach: They propose to combine word dependency graphs and latent graphs to create latent models . they propose to model the interaction between the aspect and its surrounding contexts .
Outcome: The proposed model can complement syntactic features with latent semantic dependencies.
Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis (2022.acl-long)

Copied to clipboard

Challenge: Dependency trees are used for aspect-based sentiment classification but are not optimized for aspect classification.
Approach: They propose an aspect-specific and language-agnostic discrete latent opinion tree model as an alternative structure to explicit dependency trees.
Outcome: The proposed model can achieve competitive performance and interpretability on six English benchmarks and one Chinese dataset.
How Well Do Text Embedding Models Understand Syntax? (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing text embedding models have not addressed syntactic understanding challenges, highlighting ineffectiveness and enhancing generalization ability.
Approach: They propose to examine the ability of text embedding models to generalize across syntactic contexts.
Outcome: The proposed models exhibit high similarity socres at this simple task.
Solving Aspect Category Sentiment Analysis as a Text Generation Task (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for Aspect category sentiment analysis use pre-trained language models to learn aspect category-specific representations.
Approach: They propose to make use of pre-trained language models by casting the ACSA tasks into natural language generation tasks, using natural language sentences to represent the output.
Outcome: The proposed method gives the best reported results, having large advantages in few-shot and zero-shot settings.
LogiCoT: Logical Chain-of-Thought Instruction Tuning (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent work on self-instruction tuning has focused on enhancing the general proficiency of models.
Approach: They propose a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4 that harvests instructions for prompting GPT to generate chain-of thought rationales.
Outcome: The proposed dataset enables the model to generate chain-of-thought rationales with GPT-4.
Target-Side Augmentation for Document-Level Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data.
Approach: They propose a document-level machine translation model that generates many potential translations for each source document and smoothes the distribution.
Outcome: The proposed method outperforms the previous best system by 2.30 s-BLEU on News and achieves new state-of-the-art on News .
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis (2023.acl-short)

Copied to clipboard

Challenge: Existing retrieval-augmented approaches focus on modeling the retrieved textual knowledge but this may not be able to accurately identify complex relations.
Approach: They propose to retrieve multimodal relation extraction information based on object, sentence, and whole image . they propose to synthesize the object-level, image-level and sentence-level information .
Outcome: The proposed method outperforms state-of-the-art models on multimodal relation extraction.

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