b'Yangfeng Ji'

research

∙ 06/16/2023

Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values

Although Shapley values have been shown to be highly effective for ident...

0 Stephanie Schoch, et al. ∙

research

∙ 03/28/2023

Pre-training Transformers for Knowledge Graph Completion

Learning transferable representation of knowledge graphs (KGs) is challe...

0 Sanxing Chen, et al. ∙

research

∙ 02/03/2023

Improving Interpretability via Explicit Word Interaction Graph Layer

Recent NLP literature has seen growing interest in improving model inter...

0 Arshdeep Sekhon, et al. ∙

research

∙ 12/10/2022

Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification

Some recent works observed the instability of post-hoc explanations when...

0 Ruixuan Tang, et al. ∙

research

∙ 11/13/2022

CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification

Data valuation, or the valuation of individual datum contributions, has ...

0 Stephanie Schoch, et al. ∙

research

∙ 10/20/2022

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

Traditional (fickle) adversarial examples involve finding a small pertur...

7 Hannah Chen, et al. ∙

research

∙ 10/20/2022

Pre-trained Sentence Embeddings for Implicit Discourse Relation Classification

Implicit discourse relations bind smaller linguistic units into coherent...

0 Murali Raghu Babu Balusu, et al. ∙

research

∙ 07/28/2022

Efficient Model Finetuning for Text Classification via Data Filtering

As model finetuning is central to the modern NLP, we set to maximize its...

0 Xu Ouyang, et al. ∙

research

∙ 05/24/2022

PLAtE: A Large-scale Dataset for List Page Web Extraction

Recently, neural models have been leveraged to significantly improve the...

0 Aidan San, et al. ∙

research

∙ 05/19/2022

Self-augmented Data Selection for Few-shot Dialogue Generation

The natural language generation (NLG) module in task-oriented dialogue s...

0 Wanyu Du, et al. ∙

research

∙ 05/10/2022

White-box Testing of NLP models with Mask Neuron Coverage

Recent literature has seen growing interest in using black-box strategie...

0 Arshdeep Sekhon, et al. ∙

research

∙ 04/17/2022

Pathologies of Pre-trained Language Models in Few-shot Fine-tuning

Although adapting pre-trained language models with few examples has show...

0 Hanjie Chen, et al. ∙

research

∙ 04/04/2022

Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors

Generating high quality texts with high diversity is important for many ...

0 Wanyu Du, et al. ∙

research

∙ 03/23/2022

Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation

Neural language models show vulnerability to adversarial examples which ...

0 Hanjie Chen, et al. ∙

research

∙ 02/14/2022

FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows

Despite recent progress in open-domain dialogue evaluation, how to devel...

0 Jianqiao Zhao, et al. ∙

research

∙ 01/11/2022

Explaining Prediction Uncertainty of Pre-trained Language Models by Detecting Uncertain Words in Inputs

Estimating the predictive uncertainty of pre-trained language models is ...

0 Hanjie Chen, et al. ∙

research

∙ 12/15/2021

Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings

Large pre-trained language models are often trained on large volumes of ...

0 Andrew Wang, et al. ∙

research

∙ 09/05/2021

SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks

Transformer-based pre-trained language models boost the performance of o...

0 Wanyu Du, et al. ∙

research

∙ 08/17/2021

Contextualizing Variation in Text Style Transfer Datasets

Text style transfer involves rewriting the content of a source sentence ...

0 Stephanie Schoch, et al. ∙

research

∙ 08/11/2021

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing

Interpretability methods like Integrated Gradient and LIME are popular c...

0 Sanchit Sinha, et al. ∙

research

∙ 04/09/2021

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

Explaining neural network models is important for increasing their trust...

8 Hanjie Chen, et al. ∙

research

∙ 02/02/2021

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

We introduce GEM, a living benchmark for natural language Generation (NL...

5 Sebastian Gehrmann, et al. ∙

research

∙ 11/03/2020

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory

Most NLP datasets are manually labeled, so suffer from inconsistent labe...

8 Hannah Chen, et al. ∙

research

∙ 10/01/2020

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers

To build an interpretable neural text classifier, most of the prior work...

0 Hanjie Chen, et al. ∙

research

∙ 09/30/2020

A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing

In Text-to-SQL semantic parsing, selecting the correct entities (tables ...

0 Sanxing Chen, et al. ∙

research

∙ 08/28/2020

HittER: Hierarchical Transformers for Knowledge Graph Embeddings

This paper examines the challenging problem of learning representations ...

0 Sanxing Chen, et al. ∙

research

∙ 05/25/2020

Pointwise Paraphrase Appraisal is Potentially Problematic

The prevailing approach for training and evaluating paraphrase identific...

0 Hannah Chen, et al. ∙

research

∙ 04/25/2020

Reevaluating Adversarial Examples in Natural Language

State-of-the-art attacks on NLP models have different definitions of wha...

7 John X. Morris, et al. ∙

research

∙ 04/04/2020

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection

Generating explanations for neural networks has become crucial for their...

0 Hanjie Chen, et al. ∙

research

∙ 09/10/2019

Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation

Recent progress of neural network models has achieved remarkable perform...

0 Hanjie Chen, et al. ∙

research

∙ 08/28/2019

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Generating paraphrases from given sentences involves decoding words step...

0 Wanyu Du, et al. ∙

research

∙ 08/02/2017

Dynamic Entity Representations in Neural Language Models

Understanding a long document requires tracking how entities are introdu...

0 Yangfeng Ji, et al. ∙

research

∙ 02/07/2017

Neural Discourse Structure for Text Categorization

We show that discourse structure, as defined by Rhetorical Structure The...

0 Yangfeng Ji, et al. ∙

research

∙ 01/15/2017

DyNet: The Dynamic Neural Network Toolkit

We describe DyNet, a toolkit for implementing neural network models base...

0 Graham Neubig, et al. ∙

research

∙ 03/31/2016

LSTM based Conversation Models

In this paper, we present a conversational model that incorporates both ...

0 Yi Luan, et al. ∙

research

∙ 03/07/2016

A Latent Variable Recurrent Neural Network for Discourse Relation Language Models

This paper presents a novel latent variable recurrent neural network arc...

0 Yangfeng Ji, et al. ∙

research

∙ 11/12/2015

Document Context Language Models

Text documents are structured on multiple levels of detail: individual w...

0 Yangfeng Ji, et al. ∙

research

∙ 09/04/2015

Better Document-level Sentiment Analysis from RST Discourse Parsing

Discourse structure is the hidden link between surface features and docu...

0 Parminder Bhatia, et al. ∙

research

∙ 06/23/2015

deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrins...

0 Michel Galley, et al. ∙

research

∙ 06/22/2015

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

We present a novel response generation system that can be trained end to...

0 Alessandro Sordoni, et al. ∙

research

∙ 12/17/2014

Entity-Augmented Distributional Semantics for Discourse Relations

Discourse relations bind smaller linguistic elements into coherent texts...

0 Yangfeng Ji, et al. ∙

research

∙ 11/25/2014

One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations

Discourse relations bind smaller linguistic units into coherent texts. H...

0 Yangfeng Ji, et al. ∙

Yangfeng Ji

Featured Co-authors