Models, code, and papers for "Caiming Xiong":

Entropy Penalty: Towards Generalization Beyond the IID Assumption

Oct 01, 2019
Devansh Arpit, Caiming Xiong, Richard Socher

It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art performance on such test sets, they achieve poor generalization on out of distribution (OOD) samples where the IID (independent, identical distribution) assumption breaks and the distribution of non-robust features shifts. Through theoretical and empirical analysis, we show that this happens because maximum likelihood training (without appropriate regularization) leads the model to depend on all the correlations (including spurious ones) present between inputs and targets in the dataset. We then show evidence that the information bottleneck (IB) principle can address this problem. To do so, we propose a regularization approach based on IB, called Entropy Penalty, that reduces the model's dependence on spurious features-- features corresponding to such spurious correlations. This allows deep networks trained with Entropy Penalty to generalize well even under distribution shift of spurious features. As a controlled test-bed for evaluating our claim, we train deep networks with Entropy Penalty on a colored MNIST (C-MNIST) dataset and show that it is able to generalize well on vanilla MNIST, MNIST-M and SVHN datasets in addition to an OOD version of C-MNIST itself. The baseline regularization methods we compare against fail to generalize on this test-bed. Our code is available at https://github.com/salesforce/EntropyPenalty.


  Click for Model/Code and Paper
Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression

Sep 07, 2019
Tong Niu, Caiming Xiong, Richard Socher

Text compression has diverse applications such as Summarization, Reading Comprehension and Text Editing. However, almost all existing approaches require either hand-crafted features, syntactic labels or parallel data. Even for one that achieves this task in an unsupervised setting, its architecture necessitates a task-specific autoencoder. Moreover, these models only generate one compressed sentence for each source input, so that adapting to different style requirements (e.g. length) for the final output usually implies retraining the model from scratch. In this work, we propose a fully unsupervised model, Deleter, that is able to discover an "optimal deletion path" for an arbitrary sentence, where each intermediate sequence along the path is a coherent subsequence of the previous one. This approach relies exclusively on a pretrained bidirectional language model (BERT) to score each candidate deletion based on the average Perplexity of the resulting sentence and performs progressive greedy lookahead search to select the best deletion for each step. We apply Deleter to the task of extractive Sentence Compression, and found that our model is competitive with state-of-the-art supervised models trained on 1.02 million in-domain examples with similar compression ratio. Qualitative analysis, as well as automatic and human evaluations both verify that our model produces high-quality compression.

* 5 pages, 1 figure (presented @ WeCNLP) 

  Click for Model/Code and Paper
Global-Locally Self-Attentive Dialogue State Tracker

Sep 06, 2018
Victor Zhong, Caiming Xiong, Richard Socher

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achieves state-of-the-art performance on the WoZ and DSTC2 state tracking tasks. GLAD obtains 88.1% joint goal accuracy and 97.1% request accuracy on WoZ, outperforming prior work by 3.7% and 5.5%. On DSTC2, our model obtains 74.5% joint goal accuracy and 97.5% request accuracy, outperforming prior work by 1.1% and 1.0%.

* ACL 2018. 10 pages, 5 figures. Source code: https://github.com/salesforce/glad 

  Click for Model/Code and Paper
Dynamic Coattention Networks For Question Answering

Mar 06, 2018
Caiming Xiong, Victor Zhong, Richard Socher

Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both. Then a dynamic pointing decoder iterates over potential answer spans. This iterative procedure enables the model to recover from initial local maxima corresponding to incorrect answers. On the Stanford question answering dataset, a single DCN model improves the previous state of the art from 71.0% F1 to 75.9%, while a DCN ensemble obtains 80.4% F1.

* 14 pages, 7 figures, International Conference on Learning Representations 2017 

  Click for Model/Code and Paper
Interpretable Counting for Visual Question Answering

Mar 02, 2018
Alexander Trott, Caiming Xiong, Richard Socher

Questions that require counting a variety of objects in images remain a major challenge in visual question answering (VQA). The most common approaches to VQA involve either classifying answers based on fixed length representations of both the image and question or summing fractional counts estimated from each section of the image. In contrast, we treat counting as a sequential decision process and force our model to make discrete choices of what to count. Specifically, the model sequentially selects from detected objects and learns interactions between objects that influence subsequent selections. A distinction of our approach is its intuitive and interpretable output, as discrete counts are automatically grounded in the image. Furthermore, our method outperforms the state of the art architecture for VQA on multiple metrics that evaluate counting.

* ICLR 2018 

  Click for Model/Code and Paper
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning

Dec 20, 2017
Tianmin Shu, Caiming Xiong, Richard Socher

Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for efficient multi-task reinforcement learning. Our framework trains agents to employ hierarchical policies that decide when to use a previously learned policy and when to learn a new skill. This enables agents to continually acquire new skills during different stages of training. Each learned task corresponds to a human language description. Because agents can only access previously learned skills through these descriptions, the agent can always provide a human-interpretable description of its choices. In order to help the agent learn the complex temporal dependencies necessary for the hierarchical policy, we provide it with a stochastic temporal grammar that modulates when to rely on previously learned skills and when to execute new skills. We validate our approach on Minecraft games designed to explicitly test the ability to reuse previously learned skills while simultaneously learning new skills.

* 14 pages, 6 figures 

  Click for Model/Code and Paper
Improved Regularization Techniques for End-to-End Speech Recognition

Dec 19, 2017
Yingbo Zhou, Caiming Xiong, Richard Socher

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are relatively under explored for end-to-end speech models. Therefore, we investigate the effectiveness of both methods for end-to-end trainable, deep speech recognition models. We augment audio data through random perturbations of tempo, pitch, volume, temporal alignment, and adding random noise.We further investigate the effect of dropout when applied to the inputs of all layers of the network. We show that the combination of data augmentation and dropout give a relative performance improvement on both Wall Street Journal (WSJ) and LibriSpeech dataset of over 20%. Our model performance is also competitive with other end-to-end speech models on both datasets.


  Click for Model/Code and Paper
Improving End-to-End Speech Recognition with Policy Learning

Dec 19, 2017
Yingbo Zhou, Caiming Xiong, Richard Socher

Connectionist temporal classification (CTC) is widely used for maximum likelihood learning in end-to-end speech recognition models. However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e.g., word error rate (WER). This results in a mismatch between the objective function and metric during training. We show that the above problem can be mitigated by jointly training with maximum likelihood and policy gradient. In particular, with policy learning we are able to directly optimize on the (otherwise non-differentiable) performance metric. We show that joint training improves relative performance by 4% to 13% for our end-to-end model as compared to the same model learned through maximum likelihood. The model achieves 5.53% WER on Wall Street Journal dataset, and 5.42% and 14.70% on Librispeech test-clean and test-other set, respectively.


  Click for Model/Code and Paper
A Deep Reinforced Model for Abstractive Summarization

Nov 13, 2017
Romain Paulus, Caiming Xiong, Richard Socher

Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent phrases. We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL). Models trained only with supervised learning often exhibit "exposure bias" - they assume ground truth is provided at each step during training. However, when standard word prediction is combined with the global sequence prediction training of RL the resulting summaries become more readable. We evaluate this model on the CNN/Daily Mail and New York Times datasets. Our model obtains a 41.16 ROUGE-1 score on the CNN/Daily Mail dataset, an improvement over previous state-of-the-art models. Human evaluation also shows that our model produces higher quality summaries.


  Click for Model/Code and Paper
DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

Nov 10, 2017
Caiming Xiong, Victor Zhong, Richard Socher

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that combines cross entropy loss with self-critical policy learning. The objective uses rewards derived from word overlap to solve the misalignment between evaluation metric and optimization objective. In addition to the mixed objective, we improve dynamic coattention networks (DCN) with a deep residual coattention encoder that is inspired by recent work in deep self-attention and residual networks. Our proposals improve model performance across question types and input lengths, especially for long questions that requires the ability to capture long-term dependencies. On the Stanford Question Answering Dataset, our model achieves state-of-the-art results with 75.1% exact match accuracy and 83.1% F1, while the ensemble obtains 78.9% exact match accuracy and 86.0% F1.

* 10 pages, 6 figures 

  Click for Model/Code and Paper
Dynamic Memory Networks for Visual and Textual Question Answering

Mar 04, 2016
Caiming Xiong, Stephen Merity, Richard Socher

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering. One such architecture, the dynamic memory network (DMN), obtained high accuracy on a variety of language tasks. However, it was not shown whether the architecture achieves strong results for question answering when supporting facts are not marked during training or whether it could be applied to other modalities such as images. Based on an analysis of the DMN, we propose several improvements to its memory and input modules. Together with these changes we introduce a novel input module for images in order to be able to answer visual questions. Our new DMN+ model improves the state of the art on both the Visual Question Answering dataset and the \babi-10k text question-answering dataset without supporting fact supervision.


  Click for Model/Code and Paper
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue

Jan 15, 2019
Chien-Sheng Wu, Richard Socher, Caiming Xiong

End-to-end task-oriented dialogue is challenging since knowledge bases are usually large, dynamic and hard to incorporate into a learning framework. We propose the global-to-local memory pointer (GLMP) networks to address this issue. In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge. The encoder encodes dialogue history, modifies global contextual representation, and generates a global memory pointer. The decoder first generates a sketch response with unfilled slots. Next, it passes the global memory pointer to filter the external knowledge for relevant information, then instantiates the slots via the local memory pointers. We empirically show that our model can improve copy accuracy and mitigate the common out-of-vocabulary problem. As a result, GLMP is able to improve over the previous state-of-the-art models in both simulated bAbI Dialogue dataset and human-human Stanford Multi-domain Dialogue dataset on automatic and human evaluation.

* ICLR 2019 

  Click for Model/Code and Paper
Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Sep 11, 2018
Xi Victoria Lin, Richard Socher, Caiming Xiong

Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the correct answer. We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.

* Accepted to EMNLP 2018, 12 pages 

  Click for Model/Code and Paper
Action Understanding with Multiple Classes of Actors

Apr 27, 2017
Chenliang Xu, Caiming Xiong, Jason J. Corso

Despite the rapid progress, existing works on action understanding focus strictly on one type of action agent, which we call actor---a human adult, ignoring the diversity of actions performed by other actors. To overcome this narrow viewpoint, our paper marks the first effort in the computer vision community to jointly consider algorithmic understanding of various types of actors undergoing various actions. To begin with, we collect a large annotated Actor-Action Dataset (A2D) that consists of 3782 short videos and 31 temporally untrimmed long videos. We formulate the general actor-action understanding problem and instantiate it at various granularities: video-level single- and multiple-label actor-action recognition, and pixel-level actor-action segmentation. We propose and examine a comprehensive set of graphical models that consider the various types of interplay among actors and actions. Our findings have led us to conclusive evidence that the joint modeling of actor and action improves performance over modeling each of them independently, and further improvement can be obtained by considering the multi-scale natural in video understanding. Hence, our paper concludes the argument of the value of explicit consideration of various actors in comprehensive action understanding and provides a dataset and a benchmark for later works exploring this new problem.


  Click for Model/Code and Paper
Active Clustering with Model-Based Uncertainty Reduction

Feb 14, 2014
Caiming Xiong, David Johnson, Jason J. Corso

Semi-supervised clustering seeks to augment traditional clustering methods by incorporating side information provided via human expertise in order to increase the semantic meaningfulness of the resulting clusters. However, most current methods are \emph{passive} in the sense that the side information is provided beforehand and selected randomly. This may require a large number of constraints, some of which could be redundant, unnecessary, or even detrimental to the clustering results. Thus in order to scale such semi-supervised algorithms to larger problems it is desirable to pursue an \emph{active} clustering method---i.e. an algorithm that maximizes the effectiveness of the available human labor by only requesting human input where it will have the greatest impact. Here, we propose a novel online framework for active semi-supervised spectral clustering that selects pairwise constraints as clustering proceeds, based on the principle of uncertainty reduction. Using a first-order Taylor expansion, we decompose the expected uncertainty reduction problem into a gradient and a step-scale, computed via an application of matrix perturbation theory and cluster-assignment entropy, respectively. The resulting model is used to estimate the uncertainty reduction potential of each sample in the dataset. We then present the human user with pairwise queries with respect to only the best candidate sample. We evaluate our method using three different image datasets (faces, leaves and dogs), a set of common UCI machine learning datasets and a gene dataset. The results validate our decomposition formulation and show that our method is consistently superior to existing state-of-the-art techniques, as well as being robust to noise and to unknown numbers of clusters.

* 14 pages, 8 figures, submitted to TPAMI (second version just fixes a missing reference and format) 

  Click for Model/Code and Paper
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards

Nov 04, 2019
Alexander Trott, Stephan Zheng, Caiming Xiong, Richard Socher

While using shaped rewards can be beneficial when solving sparse reward tasks, their successful application often requires careful engineering and is problem specific. For instance, in tasks where the agent must achieve some goal state, simple distance-to-goal reward shaping often fails, as it renders learning vulnerable to local optima. We introduce a simple and effective model-free method to learn from shaped distance-to-goal rewards on tasks where success depends on reaching a goal state. Our method introduces an auxiliary distance-based reward based on pairs of rollouts to encourage diverse exploration. This approach effectively prevents learning dynamics from stabilizing around local optima induced by the naive distance-to-goal reward shaping and enables policies to efficiently solve sparse reward tasks. Our augmented objective does not require any additional reward engineering or domain expertise to implement and converges to the original sparse objective as the agent learns to solve the task. We demonstrate that our method successfully solves a variety of hard-exploration tasks (including maze navigation and 3D construction in a Minecraft environment), where naive distance-based reward shaping otherwise fails, and intrinsic curiosity and reward relabeling strategies exhibit poor performance.

* NeurIPS 2019 

  Click for Model/Code and Paper
Evaluating the Factual Consistency of Abstractive Text Summarization

Oct 28, 2019
Wojciech Kryściński, Bryan McCann, Caiming Xiong, Richard Socher

Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents. We propose a weakly-supervised, model-based approach for verifying factual consistency and identifying conflicts between source documents and a generated summary. Training data is generated by applying a series of rule-based transformations to the sentences of source documents. The factual consistency model is then trained jointly for three tasks: 1) identify whether sentences remain factually consistent after transformation, 2) extract a span in the source documents to support the consistency prediction, 3) extract a span in the summary sentence that is inconsistent if one exists. Transferring this model to summaries generated by several state-of-the art models reveals that this highly scalable approach substantially outperforms previous models, including those trained with strong supervision using standard datasets for natural language inference and fact checking. Additionally, human evaluation shows that the auxiliary span extraction tasks provide useful assistance in the process of verifying factual consistency.

* 11 pages, 7 tables, 1 algorithm 

  Click for Model/Code and Paper
On the Generalization Gap in Reparameterizable Reinforcement Learning

May 29, 2019
Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher

Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the reparametrization trick. For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory. Through these relationships, we derive guarantees on the gap between the expected and empirical return for both intrinsic and external errors, based on Rademacher complexity as well as the PAC-Bayes bound. Our bound suggests the generalization capability of reparameterizable RL is related to multiple factors including "smoothness" of the environment transition, reward and agent policy function class. We also empirically verify the relationship between the generalization gap and these factors through simulations.

* Proceedings of the 36 th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019 

  Click for Model/Code and Paper
Competitive Experience Replay

Feb 17, 2019
Hao Liu, Alexander Trott, Richard Socher, Caiming Xiong

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully shape reward function to guide policy optimization. This limits the applicability of RL in the real world since both reinforcement learning and domain-specific knowledge are required. It is therefore of great practical importance to develop algorithms which can learn from a binary signal indicating successful task completion or other unshaped, sparse reward signals. We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents. Our method complements the recently proposed hindsight experience replay (HER) by inducing an automatic exploratory curriculum. We evaluate our approach on the tasks of reaching various goal locations in an ant maze and manipulating objects with a robotic arm. Each task provides only binary rewards indicating whether or not the goal is achieved. Our method asymmetrically augments these sparse rewards for a pair of agents each learning the same task, creating a competitive game designed to drive exploration. Extensive experiments demonstrate that this method leads to faster converge and improved task performance.

* Published as a conference paper at Seventh International Conference on Learning Representations(ICLR 2019) 

  Click for Model/Code and Paper