Papers by Shuyan Yang

6 papers
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities (2022.acl-long)

Copied to clipboard

Challenge: Existing evaluation methods for transfer learning are limited in speech research . authors show that pre-trained models transfer well across multiple tasks .
Approach: They propose a benchmark to evaluate pre-trained models by increasing task diversity and difficulty over SUPERB.
Outcome: The proposed benchmark increases task diversity and difficulty over SUPERB-SG.
Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on abductive and long-context reasoning reports that current models still lack self-awareness of missing premises.
Approach: They propose a reasoning framework that introduces self-awareness of missing premises before making the final decision.
Outcome: SABA achieves best performance on all three difficulty splits of detective puzzle benchmark . a small early mistake can remain uncorrected and can guide later reasoning .
Causal Reasoning of Entities and Events in Procedural Texts (2023.findings-eacl)

Copied to clipboard

Challenge: Existing work on entity state tracking or event reasoning is limited to procedural texts.
Approach: They propose a benchmark for causal reasoning of event plausibility and entity states . they represent entities as programming languages while prompting language models .
Outcome: The proposed model outperforms existing models on human reasoning and event reasoning.
Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data (2022.acl-long)

Copied to clipboard

Challenge: Existing work has treated procedures as shallow structures without modeling the parent-child relation.
Approach: They propose to construct an open-domain hierarchical knowledge-base (KB) of procedures based on wikiHow . they link steps in an article to other articles with similar goals, recursively building the KB .
Outcome: The proposed method significantly outperforms baselines according to automatic evaluation, human judgment, and application to downstream tasks such as instructional video retrieval.
Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Copied to clipboard

Challenge: In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach: They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome: The proposed approach outperforms the baseline model on multiple domain evaluations.
Language Models of Code are Few-Shot Commonsense Learners (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate graphs using pre-trained language models hinder their ability to generate them correctly.
Approach: They propose to frame structured commonsense reasoning tasks as code generation tasks instead of serializing the output graph as a flat list of nodes and edges.
Outcome: The proposed approach outperforms natural-language LMs in three natural language tasks even when the downstream task does not involve source code at all.

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