Many common sequential data sources, such as source code and natural language, have a natural tree-structured representation. These trees can be generated by fitting a sequence to a grammar, yielding a hierarchical ordering of the tokens in the sequence. This structure encodes a high degree of syntactic information, making it ideal for problems such as grammar correction. However, little work has been done to develop neural networks that can operate on and exploit tree-structured data. In this paper we present the Tree-Transformer \textemdash{} a novel neural network architecture designed to translate between arbitrary input and output trees. We applied this architecture to correction tasks in both the source code and natural language domains. On source code, our model achieved an improvement of $25\%$ $\text{F}0.5$ over the best sequential method. On natural language, we achieved comparable results to the most complex state of the art systems, obtaining a $10\%$ improvement in recall on the CoNLL 2014 benchmark and the highest to date $\text{F}0.5$ score on the AESW benchmark of $50.43$.
New York University（纽约大学）；University of Virginia（弗吉尼亚大学）
Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks to learn tree structures that are important for tree transduction problems. We first analyze the theoretical capability of the standard Transformer architecture to learn tree structures given enumeration of all possible tree backbones, which we define as trees without labels. We then prove that two linear layers with ReLU activation function can recover any …
Tree-structured neural networks encode a particular tree geometry for a sentence in the network design. However, these models have at best only slightly outperformed simpler sequence-based models. We hypothesize that neural sequence models like LSTMs are in fact able to discover and implicitly use recursive compositional structure, at least for tasks with clear cues to that structure in the data. We demonstrate this possibility using an artificial data task for which recursive compositional structure is crucial, and find an LSTM-based sequence model can indeed learn to exploit the underlying t…
Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by attention heads seems not to match human intuitions about hierarchical structures. This paper proposes Tree Transformer, which adds an extra constraint to attention heads of the bidirectional Transformer encoder in order to encourage the attention heads to follow tree structures. The tree structures can be automatically induced from raw texts by our proposed "Con…
Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a Contrastive Predictive Coding (CPC) …
Dipartimento di Informatica - Università di Pisa（比萨大学信息学系）
The paper introduces two new aggregation functions to encode structural knowledge from tree-structured data. They leverage the Canonical and Tensor-Train decompositions to yield expressive context aggregation while limiting the number of model parameters. Finally, we define two novel neural recursive models for trees leveraging such aggregation functions, and we test them on two tree classification tasks, showing the advantage of proposed models when tree outdegree increases.
Facebook AI Research（Facebook人工智能研究（FAIR））；LORIA（洛林研究所（法国国家信息与自动化研究所洛林分部））
Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of parameters, necessitating a large amount of computation and making them prone to overfitting. In this work, we explore LayerDrop, a form of structured dropout, which has a regularization effect during training and allows for efficient pruning at inference time. In particular, we show that it is possible to select sub-networks of any depth from one large net…
Nanjing University（南京大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Squirrel AI Learning（松鼠AI智适应教育）
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented grap…
University of Pennsylvania（宾夕法尼亚大学）；University of California, San Francisco（加利福尼亚大学旧金山分校）；University of Maryland Medical Center（马里兰大学医学中心）
Additive models, such as produced by gradient boosting, and full interaction models, such as classification and regression trees (CART), are widely used algorithms that have been investigated largely in isolation. We show that these models exist along a spectrum, revealing never-before-known connections between these two approaches. This paper introduces a novel technique called tree-structured boosting for creating a single decision tree, and shows that this method can produce models equivalent to CART or gradient boosted stumps at the extremes by varying a single parameter. Although tree-str…
Relationship extraction and named entity recognition have always been considered as two distinct tasks that require different input data, labels, and models. However, both are essential for structured sentiment analysis. We believe that both tasks can be combined into a single stacked model with the same input data. We performed different experiments to find the best model to extract multiple opinion tuples from a single sentence. The opinion tuples will consist of holders, targets, and expressions. With the opinion tuples, we will be able to extract the relationship we need.
University of Chinese Academy of Sciences（中国科学院大学）；Department of Computer Science, University of California Santa Barbara（加州大学圣塔芭芭拉分校计算机科学系）；WeChat Search Application Department, Tencent（腾讯微信搜索应用部）
Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sente…
Bayesian optimization (BO) is a sample-efficient global optimization algorithm for black-box functions which are expensive to evaluate. Existing literature on model based optimization in conditional parameter spaces are usually built on trees. In this work, we generalize the additive assumption to tree-structured functions and propose an additive tree-structured covariance function, showing improved sample-efficiency, wider applicability and greater flexibility. Furthermore, by incorporating the structure information of parameter spaces and the additive assumption in the BO loop, we develop a …
Semantic parsing is the task of transducing natural language (NL) utterances into formal meaning representations (MRs), commonly represented as tree structures. Annotating NL utterances with their corresponding MRs is expensive and time-consuming, and thus the limited availability of labeled data often becomes the bottleneck of data-driven, supervised models. We introduce StructVAE, a variational auto-encoding model for semisupervised semantic parsing, which learns both from limited amounts of parallel data, and readily-available unlabeled NL utterances. StructVAE models latent MRs not observe…
We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities. In this paper, we focus on the problem of robust estimation of tree-structured Ising models. Without any additional assumption of side information, this is an open problem. We first prove that this problem is unidentifiable, however, this unidentifiability is limited to a small equivalence class of trees formed by leaf nodes exchanging positions with their neighbors. Next, we propose an algorithm to solve the above problem with logar…
Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that carries no position at all. But as set processors, transformers are at a disadvantage in reasoning over more general graph-structured data where nodes represent entities and edges represent relations between entities. To address this shortcoming, we generalize transformer attention to consider and update edge vectors in each transformer layer. We evaluate thi…
Ant Financial Services Group（蚂蚁金融服务集团）；Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
Human language understanding operates at multiple levels of granularity (e.g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined. However, existing deep models with stacked layers do not explicitly model any sort of hierarchical process. This paper proposes a recursive Transformer model based on differentiable CKY style binary trees to emulate the composition process. We extend the bidirectional language model pre-training objective to this architecture, attempting to predict each word given its left and right abstraction nodes. To scale u…
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LST…
Bayesian optimization (BO) is a sample-efficient global optimization algorithm for black-box functions which are expensive to evaluate. Existing literature on model based optimization in conditional parameter spaces are usually built on trees. In this work, we generalize the additive assumption to tree-structured functions and propose an additive tree-structured covariance function, showing improved sample-efficiency, wider applicability and greater flexibility. Furthermore, by incorporating the structure information of parameter spaces and the additive assumption in the BO loop, we develop a …
Consider jointly Gaussian random variables whose conditional independence structure is specified by a graphical model. If we observe realizations of the variables, we can compute the covariance matrix, and it is well known that the support of the inverse covariance matrix corresponds to the edges of the graphical model. Instead, suppose we only have noisy observations. If the noise at each node is independent, we can compute the sum of the covariance matrix and an unknown diagonal. The inverse of this sum is (in general) dense. We ask: can the original independence structure be recovered? We a…
Czech Technical University in Prague（捷克理工大学）；Cisco Systems, Inc.（思科系统公司）；Charles University（查理大学）
This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a decade old results on mean-map embedding of probability measures in reproducing kernel Hilbert spaces. The work has wide practical consequences for multi-instance learning, where it theoretically justifies some recently proposed constructions. The result is then extended to Cartesian products, yielding universal approximation theorem for tree-structured domains,…
In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central machine is then responsible for learning the structure based on received messages from the other nodes. We present a set of communication efficient strategies, which are theoretically proved to convey sufficient information for reliable learning of the structure. In particular, our analyses show that even if each machine sends only the signs of its local da…
Beihang University（北京航空航天大学）；University of Technology Sydney（悉尼科技大学）；Meituan Inc.（美团公司）
Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path planning, which, however, has rarely been studied before in literature. In this article, we propose a Target-Driven Structured Transformer Planner (TD-STP) for long-horizon goal-guided and room layout-aware navigation. Specifically, we devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unex…
Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-of-the-art (SOTA) sequence-based models like the Transformer struggle to encode such structures inherently. On the other hand, dedicated models like the Tree-LSTM, while explicitly modeling hierarchical structures, do not perform as efficiently as the Transformer. In this paper, we attempt to bridge this gap with "Hierarchical Accumulation" to encode parse tree structures into self-attention at constant time complexi…
It has been of increasing interest in the field to develop automatic machineries to facilitate the design process. In this paper, we focus on assisting graphical user interface (UI) layout design, a crucial task in app development. Given a partial layout, which a designer has entered, our model learns to complete the layout by predicting the remaining UI elements with a correct position and dimension as well as the hierarchical structures. Such automation will significantly ease the effort of UI designers and developers. While we focus on interface layout prediction, our model can be generally…
Shiraz University（设拉子大学）；Shiraz University of Medical Sciences（设拉子医科大学）
Since radiology reports needed for clinical practice and research are written and stored in free-text narrations, extraction of relative information for further analysis is difficult. In these circumstances, natural language processing (NLP) techniques can facilitate automatic information extraction and transformation of free-text formats to structured data. In recent years, deep learning (DL)-based models have been adapted for NLP experiments with promising results. Despite the significant potential of DL models based on artificial neural networks (ANN) and convolutional neural networks (CNN)…
Department of Computer Science, The University of Manchester（曼彻斯特大学计算机科学系）
While learning models are typically studied for inputs in the form of a fixed dimensional feature vector, real world data is rarely found in this form. In order to meet the basic requirement of traditional learning models, structural data generally have to be converted into fix-length vectors in a handcrafted manner, which is tedious and may even incur information loss. A common form of structured data is what we term "semantic tree-structures", corresponding to data where rich semantic information is encoded in a compositional manner, such as those expressed in JavaScript Object Notation (JSO…
University College London（伦敦大学学院）；King’s College London（伦敦国王学院）；Northeastern University（东北大学）
We propose a model for tagging unstructured texts with an arbitrary number of terms drawn from a tree-structured vocabulary (i.e., an ontology). We treat this as a special case of sequence-to-sequence learning in which the decoder begins at the root node of an ontological tree and recursively elects to expand child nodes as a function of the input text, the current node, and the latent decoder state. In our experiments the proposed method outperforms state-of-the-art approaches on the important task of automatically assigning MeSH terms to biomedical abstracts.
Dynamic trees are mixtures of tree structured belief networks. They solve some of the problems of fixed tree networks at the cost of making exact inference intractable. For this reason approximate methods such as sampling or mean field approaches have been used. However, mean field approximations assume a factorized distribution over node states. Such a distribution seems unlickely in the posterior, as nodes are highly correlated in the prior. Here a structured variational approach is used, where the posterior distribution over the non-evidential nodes is itself approximated by a dynamic tree.…
Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g., abstract syntax tree (AST) and concrete syntax tree (CST). However, most neural architectures either fail to capture long-range dependencies which are ubiquitous in programs, or cannot learn effective representations for syntax tree nodes, making them incapable of performing the node-level prediction tasks, e.g., bug localization. In this paper, we propose Tre…
Monash University（莫纳什大学）；University of Melbourne（墨尔本大学）
Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions. We propose a novel hierarchical model for structured prediction over sequences and trees which exploits global context by conditioning each generation decision on an unbounded context of prior decisions. This builds on the success of Markov models but without imposing a fixed bound in order to better represent global phenomena. To facilitate learning of this large and unbounded model, we use a hierarchica…
Institut de Matemàtiques de la UPC-BarcelonaTech (IMTech)（加泰罗尼亚理工大学巴塞罗那技术学院数学研究所（IMTech））；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Centre de Recerca Matemàtica（数学研究中心）；Universitat Pompeu Fabra（庞培法布拉大学）
Consider the problem of learning undirected graphical models on trees from corrupted data. Recently Katiyar et al. showed that it is possible to recover trees from noisy binary data up to a small equivalence class of possible trees. Their other paper on the Gaussian case follows a similar pattern. By framing this as a special phylogenetic recovery problem we largely generalize these two settings. Using the framework of linear latent tree models we discuss tree identifiability for binary data under a continuous corruption model. For the Ising and the Gaussian tree model we also provide a charac…
Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional inputs. However, there is an ongoing debate about how and when transformers can acquire highly structured behavior and achieve systematic generalization. Here, we explore how well a causal transformer can perform a set of algorithmic tasks, including copying, sorting, and hierarchical compositions of these operations. We demonstrate strong generalization to seq…
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine where to branch out for each task given a backbone model to optimize for both task accuracy and computation efficiency. To address the challenge, this paper proposes a recommender that, given a set of tasks and a convolutional neural network-based backbone model, automatically suggests tree-structured multi-task architectures that could achieve a high task performance while meeting a user-specified computation budge…
The University of Tokyo（东京大学）；RIKEN（理化学研究所）；University of Liverpool（利物浦大学）
This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys generic content, and the leaf sentences describe specific topics. Expe…
Identifying interactions between proteins is important to understand underlying biological processes. Extracting a protein-protein interaction (PPI) from the raw text is often very difficult. Previous supervised learning methods have used handcrafted features on human-annotated data sets. In this paper, we propose a novel tree recurrent neural network with structured attention architecture for doing PPI. Our architecture achieves state of the art results (precision, recall, and F1-score) on the AIMed and BioInfer benchmark data sets. Moreover, our models achieve a significant improvement over …
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need to be learned from data, the deficiencies of learned models have limited their utility for planning. To address these challenges, we propose TreeQN, a differentiable, recursive, tree-structured model that serves as a drop-in replacement for any value function network in deep RL wi…
Xi’an Jiaotong University（西安交通大学）；University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
Tree-structured data usually contain both topological and geometrical information, and are necessarily considered on manifold instead of Euclidean space for appropriate data parameterization and analysis. In this study, we propose a novel tree-structured data parameterization, called Topology-Attribute matrix (T-A matrix), so the data clustering task can be conducted on matrix manifold. We incorporate the structure constraints embedded in data into the negative matrix factorization method to determine meta-trees from the T-A matrix, and the signature vector of each single tree can then be extr…
Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians by Application of the Bayes Codes for Context Tree Models
Center for Data Science Waseda University（早稻田大学数据科学中心）
National Institute of Informatics（国立信息学研究所）；Keio University（庆应义塾大学）
Tree-structured LSTM is promising way to consider long-distance interaction over hierarchies. However, there have been few research efforts on the hyperparameter tuning of the construction and traversal of tree-structured LSTM. To name a few, hyperparamters such as the interval of state initialization, the number of batches for normalization have been left unexplored specifically in applying batch normalization for reducing training cost and parallelization. In this paper, we propose a novel recursive algorithm for traversing batch normalized tree-structured LSTM. In proposal method, we impose…
Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of information scattered across the long document, and (2) composing a cohesive text by reconstructing these salient facts into a shorter summary that faithfully reflects the complex relations connecting these facts. In this paper, we adapt TP-TRANSFORMER (Schlag et al., 2019), an architecture that enriches the original Transformer (Vaswani et al., 2017) with the explicitly compositional Tensor Product Representation (TPR), for…
National University of Singapore（新加坡国立大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Nebraska-Lincoln（内布拉斯加大学林肯分校）
We provide finite sample guarantees for the classical Chow-Liu algorithm (IEEE Trans.~Inform.~Theory, 1968) to learn a tree-structured graphical model of a distribution. For a distribution $P$ on $Σ^n$ and a tree $T$ on $n$ nodes, we say $T$ is an $\varepsilon$-approximate tree for $P$ if there is a $T$-structured distribution $Q$ such that $D(P\;||\;Q)$ is at most $\varepsilon$ more than the best possible tree-structured distribution for $P$. We show that if $P$ itself is tree-structured, then the Chow-Liu algorithm with the plug-in estimator for mutual information with $\widetilde{O}(|Σ|^3 n…
Peking University（北京大学）；University of Alberta（阿尔伯塔大学）
A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems. One is the long dependency problem, where a code element often depends on another far-away code element. A variable reference, for example, depends on its definition, which may appear quite a few lines before. The other problem is structure modeling, as programs contain rich structural information. In this paper, we propose a novel tree-based neural architect…
Program comprehension is a fundamental task in software development and maintenance processes. Software developers often need to understand a large amount of existing code before they can develop new features or fix bugs in existing programs. Being able to process programming language code automatically and provide summaries of code functionality accurately can significantly help developers to reduce time spent in code navigation and understanding, and thus increase productivity. Different from natural language articles, source code in programming languages often follows rigid syntactical stru…
SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
Cornell University（康奈尔大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tsinghua University（清华大学）；University of Washington（华盛顿大学）；ByteDance（字节跳动）
