William Yang Wang
21 papers in the PaperMetrix corpus
Papers by this author
-
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
2017 · arXiv (Cornell University)
We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous …
-
Few-Shot NLG with Pre-Trained Language Model
2019 · arXiv (Cornell University)
Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task of \textit{few-shot …
-
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
2019 · arXiv (Cornell University)
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo …
-
Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection
2018
Jing Qian, Mai ElSherief, Elizabeth Belding, William Yang Wang. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.
-
HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing
2020 · arXiv (Cornell University)
Computation-intensive pretrained models have been taking the lead of many natural language processing benchmarks such as GLUE. However, energy efficiency in the process of model training and inference becomes a critical bottleneck. We introduce HULK, …
-
KETOD: Knowledge-Enriched Task-Oriented Dialogue
2022 · Findings of the Association for Computational Linguistics: NAACL 2022
Existing studies in dialogue system research mostly treat task-oriented dialogue and chitchat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a dialogue …
-
HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data
2022 · arXiv (Cornell University)
A pressing challenge in current dialogue systems is to successfully converse with users on topics with information distributed across different modalities. Previous work in multiturn dialogue systems has primarily focused on either text or table …
-
ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models
2023
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various settings in which a user …
-
Extraction of Unstructured Electronic Health Records to Evaluate Glioblastoma Treatment Patterns
2024 · JCO Clinical Cancer Informatics
PURPOSE: Data on lines of therapy (LOTs) for cancer treatment are important for clinical oncology research, but LOTs are not explicitly recorded in electronic health records (EHRs). We present an efficient approach for clinical data …
-
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding
2024 · arXiv (Cornell University)
Scientific figure interpretation is a crucial capability for AI-driven scientific assistants built on advanced Large Vision Language Models. However, current datasets and benchmarks primarily focus on simple charts or other relatively straightforward figures from limited …
-
Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models
2024
This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions.Specifically, we focus on addressing known-unknown questions, characterized by high uncertainty due to the absence …
-
Disentangling Memory and Reasoning Ability in Large Language Models
2024 · arXiv (Cornell University)
Large Language Models (LLMs) have demonstrated strong performance in handling complex tasks requiring both extensive knowledge and reasoning abilities. However, the existing LLM inference pipeline operates as an opaque process without explicit separation between knowledge …
-
REALM: A Dataset of Real-World LLM Use Cases
2025
Large Language Models (LLMs), such as the GPT series, have driven significant industrial applications, leading to economic and societal transformations.However, a comprehensive understanding of their real-world applications remains limited.To address this, we introduce REALM, a …
-
WikiHow: A Large Scale Text Summarization Dataset
2018 · arXiv (Cornell University)
Sequence-to-sequence models have recently gained the state of the art performance in summarization. However, not too many large-scale high-quality datasets are available and almost all the available ones are mainly news articles with specific writing …
-
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
2019
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is …
-
Mitigating Gender Bias in Natural Language Processing: Literature Review
2019
Tony Sun, Andrew Gaut, Shirlyn Tang, Yuxin Huang, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, William Yang Wang. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.
-
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
2018
Distant supervision has become the standard method for relation extraction. However, even though it is an efficient method, it does not come at no cost-The resulted distantly-supervised training samples are often very noisy. To combat …
-
MojiTalk: Generating Emotional Responses at Scale
2018
Generating emotional language is a key step towards building empathetic natural language processing agents. However, a major challenge for this line of research is the lack of large-scale labeled training data, and previous studies are …
-
Sentence Embedding Alignment for Lifelong Relation Extraction
2019
Hong Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long …
-
Fine-tune Bert for DocRED with Two-step Process
2019 · arXiv (Cornell University)
Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction. Current baselines for this task …
-
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language\n Model
2019 · arXiv (Cornell University)
Recent breakthroughs of pretrained language models have shown the\neffectiveness of self-supervised learning for a wide range of natural language\nprocessing (NLP) tasks. In addition to standard syntactic and semantic NLP\ntasks, pretrained models achieve strong improvements on …