Zheng Zhang


2022

pdf bib
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Ying Xu | Dakuo Wang | Mo Yu | Daniel Ritchie | Bingsheng Yao | Tongshuang Wu | Zheng Zhang | Toby Li | Nora Bradford | Branda Sun | Tran Hoang | Yisi Sang | Yufang Hou | Xiaojuan Ma | Diyi Yang | Nanyun Peng | Zhou Yu | Mark Warschauer
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity of high-quality QA datasets carefully designed to serve this purpose. In particular, existing datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. Drawing on the reading education research, we introduce FairytaleQA, a dataset focusing on narrative comprehension of kindergarten to eighth-grade students. Generated by educational experts based on an evidence-based theoretical framework, FairytaleQA consists of 10,580 explicit and implicit questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. Our dataset is valuable in two folds: First, we ran existing QA models on our dataset and confirmed that this annotation helps assess models’ fine-grained learning skills. Second, the dataset supports question generation (QG) task in the education domain. Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.

pdf bib
It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books
Bingsheng Yao | Dakuo Wang | Tongshuang Wu | Zheng Zhang | Toby Li | Mo Yu | Ying Xu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student’s comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.

pdf bib
SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis
Zheng Zhang | Zili Zhou | Yanna Wang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Aspect-based Sentiment Analysis (ABSA) aims to predict the sentiment polarity towards a particular aspect in a sentence. Recently, graph neural networks based on dependency tree convey rich structural information which is proven to be utility for ABSA. However, how to effectively harness the semantic and syntactic structure information from the dependency tree remains a challenging research question. In this paper, we propose a novel Syntactic and Semantic Enhanced Graph Convolutional Network (SSEGCN) model for ABSA task. Specifically, we propose an aspect-aware attention mechanism combined with self-attention to obtain attention score matrices of a sentence, which can not only learn the aspect-related semantic correlations, but also learn the global semantics of the sentence. In order to obtain comprehensive syntactic structure information, we construct syntactic mask matrices of the sentence according to the different syntactic distances between words. Furthermore, to combine syntactic structure and semantic information, we equip the attention score matrices by syntactic mask matrices. Finally, we enhance the node representations with graph convolutional network over attention score matrices for ABSA. Experimental results on benchmark datasets illustrate that our proposed model outperforms state-of-the-art methods.

2021

pdf bib
Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
Ruiqi Zhong | Kristy Lee | Zheng Zhang | Dan Klein
Findings of the Association for Computational Linguistics: EMNLP 2021

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can “prompt” the LM with the review and the label description “Does the user like this movie?”, and ask whether the next word is “yes” or “no”. However, the next word prediction training objective is still misaligned with the target zero-shot learning objective. To address this weakness, we propose meta-tuning, which directly optimizes the zero-shot learning objective by fine-tuning pre-trained language models on a collection of datasets. We focus on classification tasks, and construct the meta-dataset by aggregating 43 existing datasets and annotating 441 label descriptions in a question-answering (QA) format. When evaluated on unseen tasks, meta-tuned models outperform a same-sized QA model and the previous SOTA zero-shot learning system based on natural language inference. Additionally, increasing parameter count from 220M to 770M improves AUC-ROC scores by 6.3%, and we forecast that even larger models would perform better. Therefore, measuring zero-shot learning performance on language models out-of-the-box might underestimate their true potential, and community-wide efforts on aggregating datasets and unifying their formats can help build models that answer prompts better.

pdf bib
A Unified Generative Framework for Aspect-based Sentiment Analysis
Hang Yan | Junqi Dai | Tuo Ji | Xipeng Qiu | Zheng Zhang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which leads to various complicated ABSA models while hard to solve these subtasks in a unified framework. In this paper, we redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexes, which converts all ABSA subtasks into a unified generative formulation. Based on the unified formulation, we exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an end-to-end framework. Extensive experiments on four ABSA datasets for seven subtasks demonstrate that our framework achieves substantial performance gain and provides a real unified end-to-end solution for the whole ABSA subtasks, which could benefit multiple tasks.

pdf bib
A Unified Generative Framework for Various NER Subtasks
Hang Yan | Tao Gui | Junqi Dai | Qipeng Guo | Zheng Zhang | Xipeng Qiu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Named Entity Recognition (NER) is the task of identifying spans that represent entities in sentences. Whether the entity spans are nested or discontinuous, the NER task can be categorized into the flat NER, nested NER, and discontinuous NER subtasks. These subtasks have been mainly solved by the token-level sequence labelling or span-level classification. However, these solutions can hardly tackle the three kinds of NER subtasks concurrently. To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework. Based on our unified framework, we can leverage the pre-trained Seq2Seq model to solve all three kinds of NER subtasks without the special design of the tagging schema or ways to enumerate spans. We exploit three types of entity representations to linearize entities into a sequence. Our proposed framework is easy-to-implement and achieves state-of-the-art (SoTA) or near SoTA performance on eight English NER datasets, including two flat NER datasets, three nested NER datasets, and three discontinuous NER datasets.

2020

pdf bib
TL-Explorer: A Digital Humanities Tool for Mapping and Analyzing Translated Literature
Alex Zhai | Zheng Zhang | Amel Fraisse | Ronald Jenn | Shelley Fisher Fishkin | Pierre Zweigenbaum
Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

TL-Explorer is a digital humanities tool for mapping and analyzing translated literature, encompassing the World Map and the Translation Dashboard. The World Map displays collected literature of different languages, locations, and cultures and establishes the foundation for further analysis. It comprises three global maps for spatial and temporal interpretation. A further investigation into an individual point on the map leads to the Translation Dashboard. Each point represents one edition or translation. Collected translations are processed in order to build multilingual parallel corpora for a large number of under-resourced languages as well as to highlight the transnational circulation of knowledge. Our first rendition of TL-Explorer was conducted on the well-traveled American novel, Adventures of Huckleberry Finn, by Mark Twain. The maps currently chronicle nearly 400 translations of this novel. And the dashboard supports over 30 collected translations. However, the TL-Explore is easily extended to other works of literature and is not limited to type of texts, such as academic manuscripts or constitutional documents to name a few.

pdf bib
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
Qi Zhu | Zheng Zhang | Yan Fang | Xiang Li | Ryuichi Takanobu | Jinchao Li | Baolin Peng | Jianfeng Gao | Xiaoyan Zhu | Minlie Huang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab, ConvLab-2 inherits ConvLab’s framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which facilitates error analysis and system improvement. The interactive tool provides an user interface that allows developers to diagnose an assembled dialogue system by interacting with the system and modifying the output of each system component.

pdf bib
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation
Zhijing Jin | Qipeng Guo | Xipeng Qiu | Zheng Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel versions of existing small supervised datasets, which largely constrain their potential. In this paper, we propose a large-scale, general-domain dataset, GenWiki. Our unsupervised dataset has 1.3M text and graph examples, respectively. With a human-annotated test set, we provide this new benchmark dataset for future research on unsupervised text generation from knowledge graphs.

pdf bib
CoLAKE: Contextualized Language and Knowledge Embedding
Tianxiang Sun | Yunfan Shao | Xipeng Qiu | Qipeng Guo | Yaru Hu | Xuanjing Huang | Zheng Zhang
Proceedings of the 28th International Conference on Computational Linguistics

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models. Few works explore the potential of deep contextualized knowledge representation when injecting knowledge. In this paper, we propose the Contextualized Language and Knowledge Embedding (CoLAKE), which jointly learns contextualized representation for both language and knowledge with the extended MLM objective. Instead of injecting only entity embeddings, CoLAKE extracts the knowledge context of an entity from large-scale knowledge bases. To handle the heterogeneity of knowledge context and language context, we integrate them in a unified data structure, word-knowledge graph (WK graph). CoLAKE is pre-trained on large-scale WK graphs with the modified Transformer encoder. We conduct experiments on knowledge-driven tasks, knowledge probing tasks, and language understanding tasks. Experimental results show that CoLAKE outperforms previous counterparts on most of the tasks. Besides, CoLAKE achieves surprisingly high performance on our synthetic task called word-knowledge graph completion, which shows the superiority of simultaneously contextualizing language and knowledge representation.

pdf bib
MovieChats: Chat like Humans in a Closed Domain
Hui Su | Xiaoyu Shen | Zhou Xiao | Zheng Zhang | Ernie Chang | Cheng Zhang | Cheng Niu | Jie Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Being able to perform in-depth chat with humans in a closed domain is a precondition before an open-domain chatbot can be ever claimed. In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots. We propose a unified, readily scalable neural approach which reconciles all subtasks like intent prediction and knowledge retrieval. The model is first pretrained on the huge general-domain data, then finetuned on our corpus. We show this simple neural approach trained on high-quality data is able to outperform commercial systems replying on complex rules. On both the static and interactive tests, we find responses generated by our system exhibits remarkably good engagement and sensibleness close to human-written ones. We further analyze the limits of our work and point out potential directions for future work

pdf bib
Learning Goal-oriented Dialogue Policy with opposite Agent Awareness
Zheng Zhang | Lizi Liao | Xiaoyan Zhu | Tat-Seng Chua | Zitao Liu | Yan Huang | Minlie Huang
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treats the opposite agent policy as part of the environment. While in real-world scenarios, the behavior of an opposite agent often exhibits certain patterns or underlies hidden policies, which can be inferred and utilized by the target agent to facilitate its own decision making. This strategy is common in human mental simulation by first imaging a specific action and the probable results before really acting it. We therefore propose an opposite behavior aware framework for policy learning in goal-oriented dialogues. We estimate the opposite agent’s policy from its behavior and use this estimation to improve the target agent by regarding it as part of the target policy. We evaluate our model on both cooperative and competitive dialogue tasks, showing superior performance over state-of-the-art baselines.

pdf bib
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Qi Zhu | Kaili Huang | Zheng Zhang | Xiaoyan Zhu | Minlie Huang
Transactions of the Association for Computational Linguistics, Volume 8

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts on both user and system sides. About 60% of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across domains in conversation. We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus. The large size and rich annotation of CrossWOZ make it suitable to investigate a variety of tasks in cross-domain dialogue modeling, such as dialogue state tracking, policy learning, user simulation, etc.

pdf bib
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Qipeng Guo | Zhijing Jin | Xipeng Qiu | Weinan Zhang | David Wipf | Zheng Zhang
Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)

Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-tograph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG 2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models for G2T and T2G suffer largely from scarce training data. We present CycleGT, an unsupervised training method that can bootstrap from fully non-parallel graph and text data, and iteratively back translate between the two forms. Experiments on WebNLG datasets show that our unsupervised model trained on the same number of data achieves performance on par with several fully supervised models. Further experiments on the non-parallel GenWiki dataset verify that our method performs the best among unsupervised baselines. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G.

pdf bib
𝒫2: A Plan-and-Pretrain Approach for Knowledge Graph-to-Text Generation
Qipeng Guo | Zhijing Jin | Ning Dai | Xipeng Qiu | Xiangyang Xue | David Wipf | Zheng Zhang
Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)

Text verbalization of knowledge graphs is an important problem with wide application to natural language generation (NLG) systems. It is challenging because the generated text not only needs to be grammatically correct (fluency), but also has to contain the given structured knowledge input (relevance) and meet some other criteria. We develop a plan-and-pretrain approach, 𝒫2, which consists of a relational graph convolutional network (RGCN) planner and the pretrained sequence-tosequence (Seq2Seq) model T5. Specifically, the R-GCN planner first generates an order of the knowledge graph triplets, corresponding to the order that they will be mentioned in text, and then T5 produces the surface realization of the given plan. In the WebNLG+ 2020 Challenge, our submission ranked in 1st place on all automatic and human evaluation criteria of the English RDF-to-text generation task.

2019

pdf bib
Star-Transformer
Qipeng Guo | Xipeng Qiu | Pengfei Liu | Yunfan Shao | Xiangyang Xue | Zheng Zhang
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)

Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data. In this paper, we present Star-Transformer, a lightweight alternative by careful sparsification. To reduce model complexity, we replace the fully-connected structure with a star-shaped topology, in which every two non-adjacent nodes are connected through a shared relay node. Thus, complexity is reduced from quadratic to linear, while preserving the capacity to capture both local composition and long-range dependency. The experiments on four tasks (22 datasets) show that Star-Transformer achieved significant improvements against the standard Transformer for the modestly sized datasets.

pdf bib
ConvLab: Multi-Domain End-to-End Dialog System Platform
Sungjin Lee | Qi Zhu | Ryuichi Takanobu | Zheng Zhang | Yaoqin Zhang | Xiang Li | Jinchao Li | Baolin Peng | Xiujun Li | Minlie Huang | Jianfeng Gao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.

2018

pdf bib
Efficient Generation and Processing of Word Co-occurrence Networks Using corpus2graph
Zheng Zhang | Pierre Zweigenbaum | Ruiqing Yin
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)

Corpus2graph is an open-source NLP-application-oriented tool that generates a word co-occurrence network from a large corpus. It not only contains different built-in methods to preprocess words, analyze sentences, extract word pairs and define edge weights, but also supports user-customized functions. By using parallelization techniques, it can generate a large word co-occurrence network of the whole English Wikipedia data within hours. And thanks to its nodes-edges-weight three-level progressive calculation design, rebuilding networks with different configurations is even faster as it does not need to start all over again. This tool also works with other graph libraries such as igraph, NetworkX and graph-tool as a front end providing data to boost network generation speed.

pdf bib
GNEG: Graph-Based Negative Sampling for word2vec
Zheng Zhang | Pierre Zweigenbaum
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5% and improves the performance on word similarity tasks by about 1% compared to the skip-gram negative sampling baseline.

2017

pdf bib
zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora
Zheng Zhang | Pierre Zweigenbaum
Proceedings of the 10th Workshop on Building and Using Comparable Corpora

This paper describes the zNLP system for the BUCC 2017 shared task. Our system identifies parallel sentence pairs in Chinese-English comparable corpora by translating word-by-word Chinese sentences into English, using the search engine Solr to select near-parallel sentences and then by using an SVM classifier to identify true parallel sentences from the previous results. It obtains an F1-score of 45% (resp. 32%) on the test (training) set.