Kewei Tu


2021

pdf bib
Unsupervised Natural Language Parsing (Introductory Tutorial)
Kewei Tu | Yong Jiang | Wenjuan Han | Yanpeng Zhao
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts

Unsupervised parsing learns a syntactic parser from training sentences without parse tree annotations. Recently, there has been a resurgence of interest in unsupervised parsing, which can be attributed to the combination of two trends in the NLP community: a general trend towards unsupervised training or pre-training, and an emerging trend towards finding or modeling linguistic structures in neural models. In this tutorial, we will introduce to the general audience what unsupervised parsing does and how it can be useful for and beyond syntactic parsing. We will then provide a systematic overview of major classes of approaches to unsupervised parsing, namely generative and discriminative approaches, and analyze their relative strengths and weaknesses. We will cover both decade-old statistical approaches and more recent neural approaches to give the audience a sense of the historical and recent development of the field. We will also discuss emerging research topics such as BERT-based approaches and visually grounded learning.

pdf bib
Generalized Supervised Attention for Text Generation
Yixian Liu | Liwen Zhang | Xinyu Zhang | Yong Jiang | Yue Zhang | Kewei Tu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
Songlin Yang | Yanpeng Zhao | Kewei Tu
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previous approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neural parameterization for the new form to improve unsupervised parsing performance. We evaluate our model across ten languages and empirically demonstrate the effectiveness of using more symbols.

pdf bib
Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
Xinyu Wang | Zixia Jia | Yong Jiang | Kewei Tu
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)

This paper describe the system used in our submission to the IWPT 2021 Shared Task. Our system is a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE). Because recent work found that better word representations can be obtained by concatenating different types of embeddings, we use ACE to automatically find the better concatenation of embeddings for the task of enhanced universal dependencies. According to official results averaged on 17 languages, our system rank 2nd over 9 teams.

pdf bib
Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
Xinyu Wang | Yong Jiang | Zhaohui Yan | Zixia Jia | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
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)

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the cross-entropy between the teacher and the student’s output distributions. However, for structured prediction problems, the output space is exponential in size; therefore, the cross-entropy objective becomes intractable to compute and optimize directly. In this paper, we derive a factorized form of the knowledge distillation objective for structured prediction, which is tractable for many typical choices of the teacher and student models. In particular, we show the tractability and empirical effectiveness of structural knowledge distillation between sequence labeling and dependency parsing models under four different scenarios: 1) the teacher and student share the same factorization form of the output structure scoring function; 2) the student factorization produces more fine-grained substructures than the teacher factorization; 3) the teacher factorization produces more fine-grained substructures than the student factorization; 4) the factorization forms from the teacher and the student are incompatible.

pdf bib
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
Xinyu Wang | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
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)

Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find external contexts of a sentence by retrieving and selecting a set of semantically relevant texts through a search engine, with the original sentence as the query. We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence. Furthermore, we can improve the model performance of both input views by Cooperative Learning, a training method that encourages the two input views to produce similar contextual representations or output label distributions. Experiments show that our approach can achieve new state-of-the-art performance on 8 NER data sets across 5 domains.

pdf bib
Automated Concatenation of Embeddings for Structured Prediction
Xinyu Wang | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
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)

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the selection of embeddings to form the best concatenated representation usually varies depending on the task and the collection of candidate embeddings, and the ever-increasing number of embedding types makes it a more difficult problem. In this paper, we propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks, based on a formulation inspired by recent progress on neural architecture search. Specifically, a controller alternately samples a concatenation of embeddings, according to its current belief of the effectiveness of individual embedding types in consideration for a task, and updates the belief based on a reward. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model, which is fed with the sampled concatenation as input and trained on a task dataset. Empirical results on 6 tasks and 21 datasets show that our approach outperforms strong baselines and achieves state-of-the-art performance with fine-tuned embeddings in all the evaluations.

pdf bib
Multi-View Cross-Lingual Structured Prediction with Minimum Supervision
Zechuan Hu | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
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)

In structured prediction problems, cross-lingual transfer learning is an efficient way to train quality models for low-resource languages, and further improvement can be obtained by learning from multiple source languages. However, not all source models are created equal and some may hurt performance on the target language. Previous work has explored the similarity between source and target sentences as an approximate measure of strength for different source models. In this paper, we propose a multi-view framework, by leveraging a small number of labeled target sentences, to effectively combine multiple source models into an aggregated source view at different granularity levels (language, sentence, or sub-structure), and transfer it to a target view based on a task-specific model. By encouraging the two views to interact with each other, our framework can dynamically adjust the confidence level of each source model and improve the performance of both views during training. Experiments for three structured prediction tasks on sixteen data sets show that our framework achieves significant improvement over all existing approaches, including these with access to additional source language data.

pdf bib
Neural Bi-Lexicalized PCFG Induction
Songlin Yang | Yanpeng Zhao | Kewei Tu
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)

Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction. However, to reduce computational complexity, they make a strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. In this paper, we propose an approach to parameterize L-PCFGs without making implausible independence assumptions. Our approach directly models bilexical dependencies and meanwhile reduces both learning and representation complexities of L-PCFGs. Experimental results on the English WSJ dataset confirm the effectiveness of our approach in improving both running speed and unsupervised parsing performance.

pdf bib
Risk Minimization for Zero-shot Sequence Labeling
Zechuan Hu | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
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)

Zero-shot sequence labeling aims to build a sequence labeler without human-annotated datasets. One straightforward approach is utilizing existing systems (source models) to generate pseudo-labeled datasets and train a target sequence labeler accordingly. However, due to the gap between the source and the target languages/domains, this approach may fail to recover the true labels. In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels. By making the risk function trainable, we draw a connection between minimum risk training and latent variable model learning. We propose a unified learning algorithm based on the expectation maximization (EM) algorithm. We extensively evaluate our proposed approaches on cross-lingual/domain sequence labeling tasks over twenty-one datasets. The results show that our approaches outperform state-of-the-art baseline systems.

pdf bib
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing
Liwen Zhang | Ge Wang | Wenjuan Han | Kewei Tu
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)

One of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, but there is so far little research in unsupervised discourse dependency parsing. Fortunately, unsupervised syntactic dependency parsing has been studied by decades, which could potentially be adapted for discourse parsing. In this paper, we propose a simple yet effective method to adapt unsupervised syntactic dependency parsing methodology for unsupervised discourse dependency parsing. We apply the method to adapt two state-of-the-art unsupervised syntactic dependency parsing methods. Experimental results demonstrate that our adaptation is effective. Moreover, we extend the adapted methods to the semi-supervised and supervised setting and surprisingly, we find that they outperform previous methods specially designed for supervised discourse parsing. Further analysis shows our adaptations result in superiority not only in parsing accuracy but also in time and space efficiency.

pdf bib
Neuralizing Regular Expressions for Slot Filling
Chengyue Jiang | Zijian Jin | Kewei Tu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Neural models and symbolic rules such as regular expressions have their respective merits and weaknesses. In this paper, we study the integration of the two approaches for the slot filling task by converting regular expressions into neural networks. Specifically, we first convert regular expressions into a special form of finite-state transducers, then unfold its approximate inference algorithm as a bidirectional recurrent neural model that performs slot filling via sequence labeling. Experimental results show that our model has superior zero-shot and few-shot performance and stays competitive when there are sufficient training data.

2020

pdf bib
Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
Xinyu Wang | Yong Jiang | Kewei Tu
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies

This paper presents the system used in our submission to the IWPT 2020 Shared Task. Our system is a graph-based parser with second-order inference. For the low-resource Tamil corpora, we specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil. Due to our misunderstanding of the submission requirements, we submitted graphs that are not connected, which makes our system only rank 6th over 10 teams. However, after we fixed this problem, our system is 0.6 ELAS higher than the team that ranked 1st in the official results.

pdf bib
Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training
Xinyu Wang | Kewei Tu
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

In this paper, we propose second-order graph-based neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding.

pdf bib
Adversarial Attack and Defense of Structured Prediction Models
Wenjuan Han | Liwen Zhang | Yong Jiang | Kewei Tu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on classification problems. In this paper, we investigate attacks and defenses for structured prediction tasks in NLP. Besides the difficulty of perturbing discrete words and the sentence fluency problem faced by attackers in any NLP tasks, there is a specific challenge to attackers of structured prediction models: the structured output of structured prediction models is sensitive to small perturbations in the input. To address these problems, we propose a novel and unified framework that learns to attack a structured prediction model using a sequence-to-sequence model with feedbacks from multiple reference models of the same structured prediction task. Based on the proposed attack, we further reinforce the victim model with adversarial training, making its prediction more robust and accurate. We evaluate the proposed framework in dependency parsing and part-of-speech tagging. Automatic and human evaluations show that our proposed framework succeeds in both attacking state-of-the-art structured prediction models and boosting them with adversarial training.

pdf bib
Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks
Chengyue Jiang | Yinggong Zhao | Shanbo Chu | Libin Shen | Kewei Tu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Neural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable. On the other hand, symbolic rules such as regular expressions are interpretable, require no training, and often achieve decent accuracy; but rules cannot benefit from labeled data when available and hence underperform neural networks in rich-resource scenarios. In this paper, we propose a type of recurrent neural networks called FA-RNNs that combine the advantages of neural networks and regular expression rules. An FA-RNN can be converted from regular expressions and deployed in zero-shot and cold-start scenarios. It can also utilize labeled data for training to achieve improved prediction accuracy. After training, an FA-RNN often remains interpretable and can be converted back into regular expressions. We apply FA-RNNs to text classification and observe that FA-RNNs significantly outperform previous neural approaches in both zero-shot and low-resource settings and remain very competitive in rich-resource settings.

pdf bib
AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
Xinyu Wang | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forward-backward and Viterbi algorithms are typically applied in training and prediction stages of the CRF model. However, these algorithms require sequential computation that makes parallelization impossible. In this paper, we propose to employ a parallelizable approximate variational inference algorithm for the CRF model. Based on this algorithm, we design an approximate inference network that can be connected with the encoder of the neural CRF model to form an end-to-end network, which is amenable to parallelization for faster training and prediction. The empirical results show that our proposed approaches achieve a 12.7-fold improvement in decoding speed with long sentences and a competitive accuracy compared with the traditional CRF approach.

pdf bib
Unsupervised Cross-Lingual Adaptation of Dependency Parsers Using CRF Autoencoders
Zhao Li | Kewei Tu
Findings of the Association for Computational Linguistics: EMNLP 2020

We consider the task of cross-lingual adaptation of dependency parsers without annotated target corpora and parallel corpora. Previous work either directly applies a discriminative source parser to the target language, ignoring unannotated target corpora, or employs an unsupervised generative parser that can leverage unannotated target data but has weaker representational power than discriminative parsers. In this paper, we propose to utilize unsupervised discriminative parsers based on the CRF autoencoder framework for this task. We train a source parser and use it to initialize and regularize a target parser that is trained on unannotated target data. We conduct experiments that transfer an English parser to 20 target languages. The results show that our method significantly outperforms previous methods.

pdf bib
Learning Numeral Embedding
Chengyue Jiang | Zhonglin Nian | Kaihao Guo | Shanbo Chu | Yinggong Zhao | Libin Shen | Kewei Tu
Findings of the Association for Computational Linguistics: EMNLP 2020

Word embedding is an essential building block for deep learning methods for natural language processing. Although word embedding has been extensively studied over the years, the problem of how to effectively embed numerals, a special subset of words, is still underexplored. Existing word embedding methods do not learn numeral embeddings well because there are an infinite number of numerals and their individual appearances in training corpora are highly scarce. In this paper, we propose two novel numeral embedding methods that can handle the out-of-vocabulary (OOV) problem for numerals. We first induce a finite set of prototype numerals using either a self-organizing map or a Gaussian mixture model. We then represent the embedding of a numeral as a weighted average of the prototype number embeddings. Numeral embeddings represented in this manner can be plugged into existing word embedding learning approaches such as skip-gram for training. We evaluated our methods and showed its effectiveness on four intrinsic and extrinsic tasks: word similarity, embedding numeracy, numeral prediction, and sequence labeling.

pdf bib
An Investigation of Potential Function Designs for Neural CRF
Zechuan Hu | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
Findings of the Association for Computational Linguistics: EMNLP 2020

The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling. In this paper, we investigate a series of increasingly expressive potential functions for neural CRF models, which not only integrate the emission and transition functions, but also explicitly take the representations of the contextual words as input. Our extensive experiments show that the decomposed quadrilinear potential function based on the vector representations of two neighboring labels and two neighboring words consistently achieves the best performance.

pdf bib
More Embeddings, Better Sequence Labelers?
Xinyu Wang | Yong Jiang | Nguyen Bach | Tao Wang | Zhongqiang Huang | Fei Huang | Kewei Tu
Findings of the Association for Computational Linguistics: EMNLP 2020

Recent work proposes a family of contextual embeddings that significantly improves the accuracy of sequence labelers over non-contextual embeddings. However, there is no definite conclusion on whether we can build better sequence labelers by combining different kinds of embeddings in various settings. In this paper, we conduct extensive experiments on 3 tasks over 18 datasets and 8 languages to study the accuracy of sequence labeling with various embedding concatenations and make three observations: (1) concatenating more embedding variants leads to better accuracy in rich-resource and cross-domain settings and some conditions of low-resource settings; (2) concatenating contextual sub-word embeddings with contextual character embeddings hurts the accuracy in extremely low-resource settings; (3) based on the conclusion of (1), concatenating additional similar contextual embeddings cannot lead to further improvements. We hope these conclusions can help people build stronger sequence labelers in various settings.

pdf bib
Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding
Ge Wang | Kewei Tu
Proceedings of the 28th International Conference on Computational Linguistics

Mannual annotation for dependency parsing is both labourious and time costly, resulting in the difficulty to learn practical dependency parsers for many languages due to the lack of labelled training corpora. To compensate for the scarcity of labelled data, semi-supervised dependency parsing methods are developed to utilize unlabelled data in the training procedure of dependency parsers. In previous work, the autoencoder framework is a prevalent approach for the utilization of unlabelled data. In this framework, training sentences are reconstructed from a decoder conditioned on dependency trees predicted by an encoder. The tree structure requirement brings challenges for both the encoder and the decoder. Sophisticated techniques are employed to tackle these challenges at the expense of model complexity and approximations in encoding and decoding. In this paper, we propose a model based on the variational autoencoder framework. By relaxing the tree constraint in both the encoder and the decoder during training, we make the learning of our model fully arc-factored and thus circumvent the challenges brought by the tree constraint. We evaluate our model on datasets across several languages and the results demonstrate the advantage of our model over previous approaches in both parsing accuracy and speed.

pdf bib
A Survey of Unsupervised Dependency Parsing
Wenjuan Han | Yong Jiang | Hwee Tou Ng | Kewei Tu
Proceedings of the 28th International Conference on Computational Linguistics

Syntactic dependency parsing is an important task in natural language processing. Unsupervised dependency parsing aims to learn a dependency parser from sentences that have no annotation of their correct parse trees. Despite its difficulty, unsupervised parsing is an interesting research direction because of its capability of utilizing almost unlimited unannotated text data. It also serves as the basis for other research in low-resource parsing. In this paper, we survey existing approaches to unsupervised dependency parsing, identify two major classes of approaches, and discuss recent trends. We hope that our survey can provide insights for researchers and facilitate future research on this topic.

pdf bib
Deep Inside-outside Recursive Autoencoder with All-span Objective
Ruyue Hong | Jiong Cai | Kewei Tu
Proceedings of the 28th International Conference on Computational Linguistics

Deep inside-outside recursive autoencoder (DIORA) is a neural-based model designed for unsupervised constituency parsing. During its forward computation, it provides phrase and contextual representations for all spans in the input sentence. By utilizing the contextual representation of each leaf-level span, the span of length 1, to reconstruct the word inside the span, the model is trained without labeled data. In this work, we extend the training objective of DIORA by making use of all spans instead of only leaf-level spans. We test our new training objective on datasets of two languages: English and Japanese, and empirically show that our method achieves improvement in parsing accuracy over the original DIORA.

pdf bib
Second-Order Unsupervised Neural Dependency Parsing
Songlin Yang | Yong Jiang | Wenjuan Han | Kewei Tu
Proceedings of the 28th International Conference on Computational Linguistics

Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose a novel design of the neural parameterization and optimization methods of the dependency models. In second-order models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set.

pdf bib
An Empirical Comparison of Unsupervised Constituency Parsing Methods
Jun Li | Yifan Cao | Jiong Cai | Yong Jiang | Kewei Tu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Unsupervised constituency parsing aims to learn a constituency parser from a training corpus without parse tree annotations. While many methods have been proposed to tackle the problem, including statistical and neural methods, their experimental results are often not directly comparable due to discrepancies in datasets, data preprocessing, lexicalization, and evaluation metrics. In this paper, we first examine experimental settings used in previous work and propose to standardize the settings for better comparability between methods. We then empirically compare several existing methods, including decade-old and newly proposed ones, under the standardized settings on English and Japanese, two languages with different branching tendencies. We find that recent models do not show a clear advantage over decade-old models in our experiments. We hope our work can provide new insights into existing methods and facilitate future empirical evaluation of unsupervised constituency parsing.

pdf bib
Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
Xinyu Wang | Yong Jiang | Nguyen Bach | Tao Wang | Fei Huang | Kewei Tu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Multilingual sequence labeling is a task of predicting label sequences using a single unified model for multiple languages. Compared with relying on multiple monolingual models, using a multilingual model has the benefit of a smaller model size, easier in online serving, and generalizability to low-resource languages. However, current multilingual models still underperform individual monolingual models significantly due to model capacity limitations. In this paper, we propose to reduce the gap between monolingual models and the unified multilingual model by distilling the structural knowledge of several monolingual models (teachers) to the unified multilingual model (student). We propose two novel KD methods based on structure-level information: (1) approximately minimizes the distance between the student’s and the teachers’ structure-level probability distributions, (2) aggregates the structure-level knowledge to local distributions and minimizes the distance between two local probability distributions. Our experiments on 4 multilingual tasks with 25 datasets show that our approaches outperform several strong baselines and have stronger zero-shot generalizability than both the baseline model and teacher models.

pdf bib
Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation
Bo Pang | Erik Nijkamp | Wenjuan Han | Linqi Zhou | Yixian Liu | Kewei Tu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Open-domain dialogue generation has gained increasing attention in Natural Language Processing. Its evaluation requires a holistic means. Human ratings are deemed as the gold standard. As human evaluation is inefficient and costly, an automated substitute is highly desirable. In this paper, we propose holistic evaluation metrics that capture different aspects of open-domain dialogues. Our metrics consist of (1) GPT-2 based context coherence between sentences in a dialogue, (2) GPT-2 based fluency in phrasing, (3) n-gram based diversity in responses to augmented queries, and (4) textual-entailment-inference based logical self-consistency. The empirical validity of our metrics is demonstrated by strong correlations with human judgments. We open source the code and relevant materials.

pdf bib
Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders
Zixia Jia | Youmi Ma | Jiong Cai | Kewei Tu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Semantic dependency parsing, which aims to find rich bi-lexical relationships, allows words to have multiple dependency heads, resulting in graph-structured representations. We propose an approach to semi-supervised learning of semantic dependency parsers based on the CRF autoencoder framework. Our encoder is a discriminative neural semantic dependency parser that predicts the latent parse graph of the input sentence. Our decoder is a generative neural model that reconstructs the input sentence conditioned on the latent parse graph. Our model is arc-factored and therefore parsing and learning are both tractable. Experiments show our model achieves significant and consistent improvement over the supervised baseline.

2019

pdf bib
Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
Xinyu Wang | Jingxian Huang | Kewei Tu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Semantic dependency parsing aims to identify semantic relationships between words in a sentence that form a graph. In this paper, we propose a second-order semantic dependency parser, which takes into consideration not only individual dependency edges but also interactions between pairs of edges. We show that second-order parsing can be approximated using mean field (MF) variational inference or loopy belief propagation (LBP). We can unfold both algorithms as recurrent layers of a neural network and therefore can train the parser in an end-to-end manner. Our experiments show that our approach achieves state-of-the-art performance.

pdf bib
Latent Variable Sentiment Grammar
Liwen Zhang | Kewei Tu | Yue Zhang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Neural models have been investigated for sentiment classification over constituent trees. They learn phrase composition automatically by encoding tree structures but do not explicitly model sentiment composition, which requires to encode sentiment class labels. To this end, we investigate two formalisms with deep sentiment representations that capture sentiment subtype expressions by latent variables and Gaussian mixture vectors, respectively. Experiments on Stanford Sentiment Treebank (SST) show the effectiveness of sentiment grammar over vanilla neural encoders. Using ELMo embeddings, our method gives the best results on this benchmark.

pdf bib
Enhancing Unsupervised Generative Dependency Parser with Contextual Information
Wenjuan Han | Yong Jiang | Kewei Tu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Most of the unsupervised dependency parsers are based on probabilistic generative models that learn the joint distribution of the given sentence and its parse. Probabilistic generative models usually explicit decompose the desired dependency tree into factorized grammar rules, which lack the global features of the entire sentence. In this paper, we propose a novel probabilistic model called discriminative neural dependency model with valence (D-NDMV) that generates a sentence and its parse from a continuous latent representation, which encodes global contextual information of the generated sentence. We propose two approaches to model the latent representation: the first deterministically summarizes the representation from the sentence and the second probabilistically models the representation conditioned on the sentence. Our approach can be regarded as a new type of autoencoder model to unsupervised dependency parsing that combines the benefits of both generative and discriminative techniques. In particular, our approach breaks the context-free independence assumption in previous generative approaches and therefore becomes more expressive. Our extensive experimental results on seventeen datasets from various sources show that our approach achieves competitive accuracy compared with both generative and discriminative state-of-the-art unsupervised dependency parsers.

pdf bib
ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing
Xinyu Wang | Yixian Liu | Zixia Jia | Chengyue Jiang | Kewei Tu
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning

This paper presents the system used in our submission to the CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes and a second-order mean field variational inference module that predicts edges. Our system achieved 1st and 2nd place for the DM and PSD frameworks respectively on the in-framework ranks and achieved 3rd place for the DM framework on the cross-framework ranks.

pdf bib
A Regularization-based Framework for Bilingual Grammar Induction
Yong Jiang | Wenjuan Han | Kewei Tu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Grammar induction aims to discover syntactic structures from unannotated sentences. In this paper, we propose a framework in which the learning process of the grammar model of one language is influenced by knowledge from the model of another language. Unlike previous work on multilingual grammar induction, our approach does not rely on any external resource, such as parallel corpora, word alignments or linguistic phylogenetic trees. We propose three regularization methods that encourage similarity between model parameters, dependency edge scores, and parse trees respectively. We deploy our methods on a state-of-the-art unsupervised discriminative parser and evaluate it on both transfer grammar induction and bilingual grammar induction. Empirical results on multiple languages show that our methods outperform strong baselines.

pdf bib
Multilingual Grammar Induction with Continuous Language Identification
Wenjuan Han | Ge Wang | Yong Jiang | Kewei Tu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

The key to multilingual grammar induction is to couple grammar parameters of different languages together by exploiting the similarity between languages. Previous work relies on linguistic phylogenetic knowledge to specify similarity between languages. In this work, we propose a novel universal grammar induction approach that represents language identities with continuous vectors and employs a neural network to predict grammar parameters based on the representation. Without any prior linguistic phylogenetic knowledge, we automatically capture similarity between languages with the vector representations and softly tie the grammar parameters of different languages. In our experiments, we apply our approach to 15 languages across 8 language families and subfamilies in the Universal Dependency Treebank dataset, and we observe substantial performance gain on average over monolingual and multilingual baselines.

2018

pdf bib
Gaussian Mixture Latent Vector Grammars
Yanpeng Zhao | Liwen Zhang | Kewei Tu
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We introduce Latent Vector Grammars (LVeGs), a new framework that extends latent variable grammars such that each nonterminal symbol is associated with a continuous vector space representing the set of (infinitely many) subtypes of the nonterminal. We show that previous models such as latent variable grammars and compositional vector grammars can be interpreted as special cases of LVeGs. We then present Gaussian Mixture LVeGs (GM-LVeGs), a new special case of LVeGs that uses Gaussian mixtures to formulate the weights of production rules over subtypes of nonterminals. A major advantage of using Gaussian mixtures is that the partition function and the expectations of subtype rules can be computed using an extension of the inside-outside algorithm, which enables efficient inference and learning. We apply GM-LVeGs to part-of-speech tagging and constituency parsing and show that GM-LVeGs can achieve competitive accuracies.

2017

pdf bib
CRF Autoencoder for Unsupervised Dependency Parsing
Jiong Cai | Yong Jiang | Kewei Tu
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Unsupervised dependency parsing, which tries to discover linguistic dependency structures from unannotated data, is a very challenging task. Almost all previous work on this task focuses on learning generative models. In this paper, we develop an unsupervised dependency parsing model based on the CRF autoencoder. The encoder part of our model is discriminative and globally normalized which allows us to use rich features as well as universal linguistic priors. We propose an exact algorithm for parsing as well as a tractable learning algorithm. We evaluated the performance of our model on eight multilingual treebanks and found that our model achieved comparable performance with state-of-the-art approaches.

pdf bib
Dependency Grammar Induction with Neural Lexicalization and Big Training Data
Wenjuan Han | Yong Jiang | Kewei Tu
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We study the impact of big models (in terms of the degree of lexicalization) and big data (in terms of the training corpus size) on dependency grammar induction. We experimented with L-DMV, a lexicalized version of Dependency Model with Valence (Klein and Manning, 2004) and L-NDMV, our lexicalized extension of the Neural Dependency Model with Valence (Jiang et al., 2016). We find that L-DMV only benefits from very small degrees of lexicalization and moderate sizes of training corpora. L-NDMV can benefit from big training data and lexicalization of greater degrees, especially when enhanced with good model initialization, and it achieves a result that is competitive with the current state-of-the-art.

pdf bib
Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition
Yong Jiang | Wenjuan Han | Kewei Tu
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Unsupervised dependency parsing aims to learn a dependency parser from unannotated sentences. Existing work focuses on either learning generative models using the expectation-maximization algorithm and its variants, or learning discriminative models using the discriminative clustering algorithm. In this paper, we propose a new learning strategy that learns a generative model and a discriminative model jointly based on the dual decomposition method. Our method is simple and general, yet effective to capture the advantages of both models and improve their learning results. We tested our method on the UD treebank and achieved a state-of-the-art performance on thirty languages.

pdf bib
Semi-supervised Structured Prediction with Neural CRF Autoencoder
Xiao Zhang | Yong Jiang | Hao Peng | Kewei Tu | Dan Goldwasser
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model for semi-supervised learning of sequential structured prediction problems. Our NCRF-AE consists of two parts: an encoder which is a CRF model enhanced by deep neural networks, and a decoder which is a generative model trying to reconstruct the input. Our model has a unified structure with different loss functions for labeled and unlabeled data with shared parameters. We developed a variation of the EM algorithm for optimizing both the encoder and the decoder simultaneously by decoupling their parameters. Our Experimental results over the Part-of-Speech (POS) tagging task on eight different languages, show that our model can outperform competitive systems in both supervised and semi-supervised scenarios.

2016

pdf bib
Context-Dependent Sense Embedding
Lin Qiu | Kewei Tu | Yong Yu
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Unsupervised Neural Dependency Parsing
Yong Jiang | Wenjuan Han | Kewei Tu
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Modified Dirichlet Distribution: Allowing Negative Parameters to Induce Stronger Sparsity
Kewei Tu
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2012

pdf bib
Unambiguity Regularization for Unsupervised Learning of Probabilistic Grammars
Kewei Tu | Vasant Honavar
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
Combining the Sparsity and Unambiguity Biases for Grammar Induction
Kewei Tu
Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure