Search Results for author: Wenting Zhao

Found 43 papers, 14 papers with code

Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning

no code implementations ICML 2020 Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John Gregoire, Carla Gomes

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with constraint reasoning for solving pattern de-mixing problems, typically in an unsupervised or very-weakly-supervised setting.

Commit0: Library Generation from Scratch

1 code implementation2 Dec 2024 Wenting Zhao, Nan Jiang, Celine Lee, Justin T Chiu, Claire Cardie, Matthias Gallé, Alexander M Rush

As a benchmark, Commit0 is designed to move beyond static one-shot code generation towards agents that must process long-form natural language specifications, adapt to multi-stage feedback, and generate code with complex dependencies.

Benchmarking Code Generation

Are Triggers Needed for Document-Level Event Extraction?

no code implementations13 Nov 2024 Shaden Shaar, Wayne Chen, Maitreyi Chatterjee, Barry Wang, Wenting Zhao, Claire Cardie

Our research shows that trigger effectiveness varies based on the extraction task's characteristics and data quality, with basic, automatically-generated triggers serving as a viable alternative to human-annotated ones.

Document-level Event Extraction Event Extraction +1

A Controlled Study on Long Context Extension and Generalization in LLMs

1 code implementation18 Sep 2024 Yi Lu, Jing Nathan Yan, Songlin Yang, Justin T. Chiu, Siyu Ren, Fei Yuan, Wenting Zhao, Zhiyong Wu, Alexander M. Rush

Broad textual understanding and in-context learning require language models that utilize full document contexts.

In-Context Learning

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild

no code implementations5 Sep 2024 Yuntian Deng, Wenting Zhao, Jack Hessel, Xiang Ren, Claire Cardie, Yejin Choi

The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions.

Chatbot

Great Memory, Shallow Reasoning: Limits of $k$NN-LMs

1 code implementation21 Aug 2024 Shangyi Geng, Wenting Zhao, Alexander M Rush

$K$-nearest neighbor language models ($k$NN-LMs), which integrate retrieval with next-word prediction, have demonstrated strong performance in language modeling as well as downstream NLP benchmarks.

Language Modelling Retrieval +2

WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries

no code implementations24 Jul 2024 Wenting Zhao, Tanya Goyal, Yu Ying Chiu, Liwei Jiang, Benjamin Newman, Abhilasha Ravichander, Khyathi Chandu, Ronan Le Bras, Claire Cardie, Yuntian Deng, Yejin Choi

While hallucinations of large language models (LLMs) prevail as a major challenge, existing evaluation benchmarks on factuality do not cover the diverse domains of knowledge that the real-world users of LLMs seek information about.

Chatbot Hallucination +1

I Could've Asked That: Reformulating Unanswerable Questions

1 code implementation24 Jul 2024 Wenting Zhao, Ge Gao, Claire Cardie, Alexander M. Rush

We curate CouldAsk, an evaluation benchmark composed of existing and new datasets for document-grounded question answering, specifically designed to study reformulating unanswerable questions.

Question Answering

WildChat: 1M ChatGPT Interaction Logs in the Wild

no code implementations2 May 2024 Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, Yuntian Deng

In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers.

Chatbot Instruction Following

kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning

no code implementations17 Dec 2023 Wenting Zhao, Ye Liu, Yao Wan, Yibo Wang, Qingyang Wu, Zhongfen Deng, Jiangshu Du, Shuaiqi Liu, Yunlong Xu, Philip S. Yu

Task-Oriented Parsing (TOP) enables conversational assistants to interpret user commands expressed in natural language, transforming them into structured outputs that combine elements of both natural language and intent/slot tags.

In-Context Learning Prompt Engineering +1

Language Model Inversion

2 code implementations22 Nov 2023 John X. Morris, Wenting Zhao, Justin T. Chiu, Vitaly Shmatikov, Alexander M. Rush

We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text.

Language Modelling

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations

no code implementations14 Nov 2023 Wenting Zhao, Justin T Chiu, Jena D. Hwang, Faeze Brahman, Jack Hessel, Sanjiban Choudhury, Yejin Choi, Xiang Lorraine Li, Alane Suhr

To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning.

Diversity Imitation Learning +1

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search

1 code implementation13 Nov 2023 Huihan Li, Yuting Ning, Zeyi Liao, Siyuan Wang, Xiang Lorraine Li, Ximing Lu, Wenting Zhao, Faeze Brahman, Yejin Choi, Xiang Ren

To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i. e. rare examples where models exhibit low confidence.

Language Modelling Natural Language Inference +1

JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction

1 code implementation7 Nov 2023 Zhongfen Deng, Hao Peng, Tao Zhang, Shuaiqi Liu, Wenting Zhao, Yibo Wang, Philip S. Yu

Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text.

Attribute Attribute Value Extraction +4

DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text

no code implementations31 Oct 2023 Wenting Zhao, Ye Liu, Tong Niu, Yao Wan, Philip S. Yu, Shafiq Joty, Yingbo Zhou, Semih Yavuz

Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e. g., knowledge base and text).

Knowledge Graphs Open-Domain Question Answering +2

Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

1 code implementation20 Sep 2023 Yibo Wang, Wenting Zhao, Yao Wan, Zhongfen Deng, Philip S. Yu

In this paper, we propose to incorporate the label dependencies among entity types into a multi-task learning framework for better MRC-based NER.

Machine Reading Comprehension Multi-Task Learning +3

Self-Calibrated Cross Attention Network for Few-Shot Segmentation

1 code implementation ICCV 2023 Qianxiong Xu, Wenting Zhao, Guosheng Lin, Cheng Long

Moreover, when calculating SCCA, we design a scaled-cosine mechanism to better utilize the support features for similarity calculation.

Few-Shot Semantic Segmentation

Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce

no code implementations29 Jul 2023 Yibo Wang, Yanbing Xue, Bo Liu, Musen Wen, Wenting Zhao, Stephen Guo, Philip S. Yu

Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems.

Position

Structure-Sensitive Graph Dictionary Embedding for Graph Classification

no code implementations18 Jun 2023 Guangbu Liu, Tong Zhang, Xudong Wang, Wenting Zhao, Chuanwei Zhou, Zhen Cui

Instead of a plain use of a base graph dictionary, we propose the variational graph dictionary adaptation (VGDA) to generate a personalized dictionary (named adapted graph dictionary) for catering to each input graph.

Graph Classification Variational Inference

Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations

no code implementations24 May 2023 Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context.

HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision

no code implementations23 May 2023 Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers.

Multi-hop Question Answering Question Answering

Serenity: Library Based Python Code Analysis for Code Completion and Automated Machine Learning

no code implementations5 Jan 2023 Wenting Zhao, Ibrahim Abdelaziz, Julian Dolby, Kavitha Srinivas, Mossad Helali, Essam Mansour

We demonstrate the efficiency and usefulness of Serenity's analysis in two applications: code completion and automated machine learning.

Code Completion

Compositional Task-Oriented Parsing as Abstractive Question Answering

1 code implementation NAACL 2022 Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie

Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm.

abstractive question answering Question Answering +1

Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots

1 code implementation Findings (EMNLP) 2021 Wenting Zhao, Ye Liu, Yao Wan, Philip S. Yu

Few-shot table-to-text generation is a task of composing fluent and faithful sentences to convey table content using limited data.

Table-to-Text Generation

Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors

1 code implementation Findings (ACL) 2022 Yang Wu, Yanyan Zhao, Hao Yang, Song Chen, Bing Qin, Xiaohuan Cao, Wenting Zhao

Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment models directly.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning

no code implementations21 Aug 2021 Di Chen, Yiwei Bai, Sebastian Ament, Wenting Zhao, Dan Guevarra, Lan Zhou, Bart Selman, R. Bruce van Dover, John M. Gregoire, Carla P. Gomes

DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization.

Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation

no code implementations EACL 2021 Ye Liu, Yao Wan, JianGuo Zhang, Wenting Zhao, Philip Yu

In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance.

Machine Translation Translation

HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders

no code implementations9 Mar 2021 Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, Carla Gomes

This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels?

Multi-Label Classification

Evaluating Multi-label Classifiers with Noisy Labels

no code implementations16 Feb 2021 Wenting Zhao, Carla Gomes

In the real world, it is more common to deal with noisy datasets than clean datasets, given how modern datasets are labeled by a large group of annotators on crowdsourcing platforms, but little attention has been given to evaluating multi-label classifiers with noisy labels.

Multi-Label Classification

Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems

no code implementations5 Feb 2021 Yiwei Bai, Wenting Zhao, Carla P. Gomes

There has been an increasing interest in harnessing deep learning to tackle combinatorial optimization (CO) problems in recent years.

BIG-bench Machine Learning Combinatorial Optimization +3

Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation

no code implementations22 Jan 2021 Ye Liu, Yao Wan, Jian-Guo Zhang, Wenting Zhao, Philip S. Yu

In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance.

Machine Translation Translation

Graph Deformer Network

no code implementations1 Jan 2021 Wenting Zhao, Yuan Fang, Zhen Cui, Tong Zhang, Jian Yang, Wei Liu

In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.

Isomorphism Testing

Dual-Attention Graph Convolutional Network

no code implementations28 Nov 2019 Xueya Zhang, Tong Zhang, Wenting Zhao, Zhen Cui, Jian Yang

Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification.

Diversity text-classification +1

Deep Reasoning Networks: Thinking Fast and Slow, for Pattern De-mixing

no code implementations25 Sep 2019 Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John M. Gregoire, Carla P. Gomes

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving pattern de-mixing problems, typically in an unsupervised or weakly-supervised setting.

scientific discovery

Deep Reasoning Networks: Thinking Fast and Slow

no code implementations3 Jun 2019 Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John M. Gregoire, Carla P. Gomes

At a high level, DRNets encode a structured latent space of the input data, which is constrained to adhere to prior knowledge by a reasoning module.

Decoder scientific discovery

When Work Matters: Transforming Classical Network Structures to Graph CNN

no code implementations7 Jul 2018 Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhen-Yu Zhang, Jian Yang

In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem.

Graph Classification Video Understanding

Cannot find the paper you are looking for? You can Submit a new open access paper.