Papers by Wei-Yun Ma

11 papers
Automatic Construction of a Chinese Review Dataset for Aspect Sentiment Triplet Extraction via Iterative Weak Supervision (2024.lrec-main)

Copied to clipboard

Challenge: Aspect Sentiment Triplet Extraction (ASTE) is a task that involves the extraction of three key elements: target aspects, descriptive opinion spans, and their corresponding sentiment polarity.
Approach: They propose a framework that facilitates automatic construction of Aspect Sentiment Triplet Extraction (ASTE) by iterative weak supervision and a discriminator to weed out subpar samples.
Outcome: The proposed framework automates the construction of Aspect Sentiment Triplet Extraction tasks in Chinese by using iterative weak supervision.
iComposer: An Automatic Songwriting System for Chinese Popular Music (N19-4)

Copied to clipboard

Challenge: iComposer is an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production.
Approach: They propose a web-based songwriting system that automatically generates melody from text . they use sequence-to-sequence models to predict melody, rhythm, and lyrics .
Outcome: The proposed system can write pleasing melodies and meaningful lyrics similar to humans.
CA-EHN: Commonsense Analogy from E-HowNet (2020.lrec-1)

Copied to clipboard

Challenge: Existing word analogy datasets rely on handcrafted words with only dozens of predefined relations.
Approach: They present a commonsense word analogy dataset with 90,505 analogies . they use an ontology that annotates 88K Chinese words with their structured sense definitions and English translations.
Outcome: The proposed dataset shows that word representations embed commonsense knowledge.
Headword-Oriented Entity Linking: A Special Entity Linking Task with Dataset and Baseline (2020.lrec-1)

Copied to clipboard

Challenge: specialized entity linking problem involves linking only headwords of entities to knowledge bases . full product names are rarely written in context, instead abbreviated to shorter, irregular versions .
Approach: They propose a specialized entity linking problem where only the headwords of entities are to be linked to knowledge bases.
Outcome: The proposed model provides a strong benchmark performance on the special task.
Generating Attractive and Authentic Copywriting from Customer Reviews (2024.naacl-long)

Copied to clipboard

Challenge: Typical approaches to copywriting focus on product attributes, leading to dull and repetitive content.
Approach: They propose to generate copywriting based on customer reviews as they provide firsthand practical experiences with products, offering a richer source of information than just product attributes.
Outcome: The proposed framework outperforms baseline and zero-shot large language models in terms of both attractiveness and faithfulness.
Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese (L18-1)

Copied to clipboard

Challenge: Existing evaluation sets for word embeddings in English are limited.
Approach: They propose to translate existing evaluation sets from English to Chinese to evaluate Chinese word embeddings.
Outcome: The proposed evaluation sets are based on translations of popular evaluation sets from English to Chinese and human rating from Amazon Mechanical Turk workers.
Plug-in Language Model: Controlling Text Generation with a Simple Regression Model (2024.findings-naacl)

Copied to clipboard

Challenge: Large-scale pre-trained language models have demonstrated unrivaled capacity in generating text that closely resembles human-written content.
Approach: They propose a plug-in language model that leverages reinforcement learning to adjust latent states to control text generation.
Outcome: The proposed model outperforms existing methods that rely on gradient-based, weighted decoding, or prompt-based methods.
Speed Reading: Learning to Read ForBackward via Shuttle (D18-1)

Copied to clipboard

Challenge: LSTM-Shuttle uses human speed reading techniques to perform natural language processing tasks.
Approach: They propose a model which uses human speed reading techniques to perform natural language processing tasks for accurate and efficient comprehension.
Outcome: The proposed model predicts on IMDB, Rotten Tomatoes, AG, and Children’s Book Test datasets and goes backwards.
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction (P19-1)

Copied to clipboard

Challenge: GraphRel is an end-to-end relation extraction model that uses graph convolutional networks to learn named entities and relations.
Approach: They propose a graph-based relation extraction model which uses graph convolutional networks to jointly learn named entities and relations.
Outcome: The proposed model outperforms previous models on two public datasets: NYT and WebNLG.
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Existing work on distant supervision denoising introduces false-positive (FP) and falsenegative (FN) training instances to the generated datasets.
Approach: They propose a hierarchical false-negative denoising framework for distant supervision relation extraction that denoises false-positive and false- negative training instances.
Outcome: The proposed framework can revise FN instances correctly and maintain high F1 scores even when 50% of instances have been turned into negatives.
Extended HowNet 2.0 – An Entity-Relation Common-Sense Representation Model (L18-1)

Copied to clipboard

Challenge: Extended HowNet 2.0 is a common-sense representation model for lexical senses .
Approach: They propose Extended HowNet 2.0 -an entity-relation common-sense representation model . a query system is being developed for flexibly clustering concepts .
Outcome: The proposed model can bring significant benefits to the community of lexical semantics and natural language understanding.

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