Diyi Yang


2020

pdf bib
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
Jiaao Chen | Zichao Yang | Diyi Yang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data. By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks. The improvement is especially prominent when supervision is extremely limited. We have publicly released our code at https://github.com/GT-SALT/MixText.

pdf bib
Examining the Ordering of Rhetorical Strategies in Persuasive Requests
Omar Shaikh | Jiaao Chen | Jon Saad-Falcon | Polo Chau | Diyi Yang
Findings of the Association for Computational Linguistics: EMNLP 2020

Interpreting how persuasive language influences audiences has implications across many domains like advertising, argumentation, and propaganda. Persuasion relies on more than a message’s content. Arranging the order of the message itself (i.e., ordering specific rhetorical strategies) also plays an important role. To examine how strategy orderings contribute to persuasiveness, we first utilize a Variational Autoencoder model to disentangle content and rhetorical strategies in textual requests from a large-scale loan request corpus. We then visualize interplay between content and strategy through an attentional LSTM that predicts the success of textual requests. We find that specific (orderings of) strategies interact uniquely with a request’s content to impact success rate, and thus the persuasiveness of a request.

pdf bib
Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization
Kunal Chawla | Diyi Yang
Findings of the Association for Computational Linguistics: EMNLP 2020

Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal, which allows us to use maximization of token-level conditional probabilities for training. We further propose to maximize mutual information between source and target styles as our training objective instead of maximizing the regular likelihood that often leads to repetitive and trivial generated responses. Experiments showed that our model outperformed previous state-of-the-art baselines significantly in terms of both automated metrics and human judgement. We further generalized our model to unsupervised text style transfer task, and achieved significant improvements on two benchmark sentiment style transfer datasets.

pdf bib
ToTTo: A Controlled Table-To-Text Generation Dataset
Ankur Parikh | Xuezhi Wang | Sebastian Gehrmann | Manaal Faruqui | Bhuwan Dhingra | Diyi Yang | Dipanjan Das
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation.

pdf bib
Local Additivity Based Data Augmentation for Semi-supervised NER
Jiaao Chen | Zhenghui Wang | Ran Tian | Zichao Yang | Diyi Yang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Named Entity Recognition (NER) is one of the first stages in deep language understanding yet current NER models heavily rely on human-annotated data. In this work, to alleviate the dependence on labeled data, we propose a Local Additivity based Data Augmentation (LADA) method for semi-supervised NER, in which we create virtual samples by interpolating sequences close to each other. Our approach has two variations: Intra-LADA and Inter-LADA, where Intra-LADA performs interpolations among tokens within one sentence, and Inter-LADA samples different sentences to interpolate. Through linear additions between sampled training data, LADA creates an infinite amount of labeled data and improves both entity and context learning. We further extend LADA to the semi-supervised setting by designing a novel consistency loss for unlabeled data. Experiments conducted on two NER benchmarks demonstrate the effectiveness of our methods over several strong baselines. We have publicly released our code at https://github.com/GT-SALT/LADA

pdf bib
Planning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection
Jingfeng Yang | Diyi Yang | Zhaoran Ma
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Existing approaches to disfluency detection heavily depend on human-annotated data. Numbers of data augmentation methods have been proposed to alleviate the dependence on labeled data. However, current augmentation approaches such as random insertion or repetition fail to resemble training corpus well and usually resulted in unnatural and limited types of disfluencies. In this work, we propose a simple Planner-Generator based disfluency generation model to generate natural and diverse disfluent texts as augmented data, where the Planner decides on where to insert disfluent segments and the Generator follows the prediction to generate corresponding disfluent segments. We further utilize this augmented data for pretraining and leverage it for the task of disfluency detection. Experiments demonstrated that our two-stage disfluency generation model outperforms existing baselines; those disfluent sentences generated significantly aided the task of disfluency detection and led to state-of-the-art performance on Switchboard corpus.

pdf bib
Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization
Jiaao Chen | Diyi Yang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Text summarization is one of the most challenging and interesting problems in NLP. Although much attention has been paid to summarizing structured text like news reports or encyclopedia articles, summarizing conversations—an essential part of human-human/machine interaction where most important pieces of information are scattered across various utterances of different speakers—remains relatively under-investigated. This work proposes a multi-view sequence-to-sequence model by first extracting conversational structures of unstructured daily chats from different views to represent conversations and then utilizing a multi-view decoder to incorporate different views to generate dialogue summaries. Experiments on a large-scale dialogue summarization corpus demonstrated that our methods significantly outperformed previous state-of-the-art models via both automatic evaluations and human judgment. We also discussed specific challenges that current approaches faced with this task. We have publicly released our code at https://github.com/GT-SALT/Multi-View-Seq2Seq.

2019

pdf bib
Proceedings of the 2019 Workshop on Widening NLP
Amittai Axelrod | Diyi Yang | Rossana Cunha | Samira Shaikh | Zeerak Waseem
Proceedings of the 2019 Workshop on Widening NLP

pdf bib
Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms
Diyi Yang | Jiaao Chen | Zichao Yang | Dan Jurafsky | Eduard Hovy
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Modeling what makes a request persuasive - eliciting the desired response from a reader - is critical to the study of propaganda, behavioral economics, and advertising. Yet current models can’t quantify the persuasiveness of requests or extract successful persuasive strategies. Building on theories of persuasion, we propose a neural network to quantify persuasiveness and identify the persuasive strategies in advocacy requests. Our semi-supervised hierarchical neural network model is supervised by the number of people persuaded to take actions and partially supervised at the sentence level with human-labeled rhetorical strategies. Our method outperforms several baselines, uncovers persuasive strategies - offering increased interpretability of persuasive speech - and has applications for other situations with document-level supervision but only partial sentence supervision.

2017

pdf bib
Identifying Semantic Edit Intentions from Revisions in Wikipedia
Diyi Yang | Aaron Halfaker | Robert Kraut | Eduard Hovy
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Most studies on human editing focus merely on syntactic revision operations, failing to capture the intentions behind revision changes, which are essential for facilitating the single and collaborative writing process. In this work, we develop in collaboration with Wikipedia editors a 13-category taxonomy of the semantic intention behind edits in Wikipedia articles. Using labeled article edits, we build a computational classifier of intentions that achieved a micro-averaged F1 score of 0.621. We use this model to investigate edit intention effectiveness: how different types of edits predict the retention of newcomers and changes in the quality of articles, two key concerns for Wikipedia today. Our analysis shows that the types of edits that users make in their first session predict their subsequent survival as Wikipedia editors, and articles in different stages need different types of edits.

2016

pdf bib
Edit Categories and Editor Role Identification in Wikipedia
Diyi Yang | Aaron Halfaker | Robert Kraut | Eduard Hovy
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

In this work, we introduced a corpus for categorizing edit types in Wikipedia. This fine-grained taxonomy of edit types enables us to differentiate editing actions and find editor roles in Wikipedia based on their low-level edit types. To do this, we first created an annotated corpus based on 1,996 edits obtained from 953 article revisions and built machine-learning models to automatically identify the edit categories associated with edits. Building on this automated measurement of edit types, we then applied a graphical model analogous to Latent Dirichlet Allocation to uncover the latent roles in editors’ edit histories. Applying this technique revealed eight different roles editors play, such as Social Networker, Substantive Expert, etc.

pdf bib
Hierarchical Attention Networks for Document Classification
Zichao Yang | Diyi Yang | Chris Dyer | Xiaodong He | Alex Smola | Eduard Hovy
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2015

pdf bib
Humor Recognition and Humor Anchor Extraction
Diyi Yang | Alon Lavie | Chris Dyer | Eduard Hovy
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets
William Yang Wang | Diyi Yang
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Incorporating Word Correlation Knowledge into Topic Modeling
Pengtao Xie | Diyi Yang | Eric Xing
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Weakly Supervised Role Identification in Teamwork Interactions
Diyi Yang | Miaomiao Wen | Carolyn Rosé
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Towards Identifying the Resolvability of Threads in MOOCs
Diyi Yang | Miaomiao Wen | Carolyn Rose
Proceedings of the EMNLP 2014 Workshop on Analysis of Large Scale Social Interaction in MOOCs