arXiv subjects

Alexander M. Rush

Publications and source records attributed to Alexander M. Rush.

At least 73 records · Page 4Linked to original sources

arXiv2020

Sequence-Level Mixed Sample Data Augmentation

Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for sequence-to-sequence problems. Our approach, SeqMix, creates new synthetic examples by softly combining input/output sequences from the training set. We connect this approach to existing techniques such as SwitchOut and word dropout, and show that these techniques are all approximating variants of a single objective. SeqMix consistently yields approximately 1.0 BLEU improvement on five different translation datasets over strong Transformer baselines. On tasks that require strong compositional generalization such as SCAN and semantic parsing, SeqMix also offers further improvements.

cs.CL↗

arXiv2020

Scaling Hidden Markov Language Models

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure. However, this separation makes it difficult to fit HMMs to large datasets in modern NLP, and they have fallen out of use due to very poor performance compared to fully observed models. This work revisits the challenge of scaling HMMs to language modeling datasets, taking ideas from recent approaches to neural modeling. We propose methods for scaling HMMs to massive state spaces while maintaining efficient exact inference, a compact parameterization, and effective regularization. Experiments show that this approach leads to models that are more accurate than previous HMM and n-gram-based methods, making progress towards the performance of state-of-the-art neural models.

cs.CL↗

arXiv2020

Adversarial Semantic Collisions

We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks which rely on analyzing the meaning and similarity of texts-- including paraphrase identification, document retrieval, response suggestion, and extractive summarization-- are vulnerable to semantic collisions. For example, given a target query, inserting a crafted collision into an irrelevant document can shift its retrieval rank from 1000 to top 3. We show how to generate semantic collisions that evade perplexity-based filtering and discuss other potential mitigations. Our code is available at https://github.com/csong27/collision-bert.

cs.CL↗

arXiv2020

Pre-trained Summarization Distillation

Recent state-of-the-art approaches to summarization utilize large pre-trained Transformer models. Distilling these models to smaller student models has become critically important for practical use; however there are many different distillation methods proposed by the NLP literature. Recent work on distilling BERT for classification and regression tasks shows strong performance using direct knowledge distillation. Alternatively, machine translation practitioners distill using pseudo-labeling, where a small model is trained on the translations of a larger model. A third, simpler approach is to 'shrink and fine-tune' (SFT), which avoids any explicit distillation by copying parameters to a smaller student model and then fine-tuning. We compare these three approaches for distillation of Pegasus and BART, the current and former state of the art, pre-trained summarization models, and find that SFT outperforms knowledge distillation and pseudo-labeling on the CNN/DailyMail dataset, but under-performs pseudo-labeling on the more abstractive XSUM dataset. PyTorch Code and checkpoints of different sizes are available through Hugging Face transformers here http://tiny.cc/4iy0tz.

cs.CL↗

arXiv2020

Movement Pruning: Adaptive Sparsity by Fine-Tuning

Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning shows significant improvements in high-sparsity regimes. When combined with distillation, the approach achieves minimal accuracy loss with down to only 3% of the model parameters.

cs.CL↗

arXiv2020

HuggingFace's Transformers: State-of-the-art Natural Language Processing

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks. \textit{Transformers} is an open-source library with the goal of opening up these advances to the wider machine learning community. The library consists of carefully engineered state-of-the art Transformer architectures under a unified API. Backing this library is a curated collection of pretrained models made by and available for the community. \textit{Transformers} is designed to be extensible by researchers, simple for practitioners, and fast and robust in industrial deployments. The library is available at \url{https://github.com/huggingface/transformers}.

cs.CL↗

arXiv2020

MiniConf -- A Virtual Conference Framework

MiniConf is a framework for hosting virtual academic conferences motivated by the sudden inability for these events to be hosted globally. The framework is designed to be global and asynchronous, interactive, and to promote browsing and discovery. We developed the system to be sustainable and maintainable, in particular ensuring that it is open-source, easy to setup, and scalable on minimal hardware. In this technical report, we discuss design decisions, provide technical detail, and show examples of a case study deployment.

cs.HC↗

arXiv2020

What is Learned in Visually Grounded Neural Syntax Acquisition

Visual features are a promising signal for learning bootstrap textual models. However, blackbox learning models make it difficult to isolate the specific contribution of visual components. In this analysis, we consider the case study of the Visually Grounded Neural Syntax Learner (Shi et al., 2019), a recent approach for learning syntax from a visual training signal. By constructing simplified versions of the model, we isolate the core factors that yield the model's strong performance. Contrary to what the model might be capable of learning, we find significantly less expressive versions produce similar predictions and perform just as well, or even better. We also find that a simple lexical signal of noun concreteness plays the main role in the model's predictions as opposed to more complex syntactic reasoning.

cs.CL↗

arXiv2020

Posterior Control of Blackbox Generation

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.

cs.CL↗

arXiv2020

Compound Probabilistic Context-Free Grammars for Grammar Induction

We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our grammar's rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginalized out with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods when evaluated on unsupervised parsing.

cs.CL↗

arXiv2020

Automating Botnet Detection with Graph Neural Networks

Botnets are now a major source for many network attacks, such as DDoS attacks and spam. However, most traditional detection methods heavily rely on heuristically designed multi-stage detection criteria. In this paper, we consider the neural network design challenges of using modern deep learning techniques to learn policies for botnet detection automatically. To generate training data, we synthesize botnet connections with different underlying communication patterns overlaid on large-scale real networks as datasets. To capture the important hierarchical structure of centralized botnets and the fast-mixing structure for decentralized botnets, we tailor graph neural networks (GNN) to detect the properties of these structures. Experimental results show that GNNs are better able to capture botnet structure than previous non-learning methods when trained with appropriate data, and that deeper GNNs are crucial for learning difficult botnet topologies. We believe our data and studies can be useful for both the network security and graph learning communities.

cs.CR↗

arXiv2020

Torch-Struct: Deep Structured Prediction Library

The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at https://github.com/harvardnlp/pytorch-struct.

cs.CL↗

arXiv2020

LAN -- A materials notation for 2D layered assemblies

Two-dimensional (2D) layered materials offer intriguing possibilities for novel physics and applications. Before any attempt at exploring the materials space in a systematic fashion, or combining insights from theory, computation and experiment, a formal description of information about an assembly of arbitrary composition is required. Here, we introduce a domain-generic notation that is used to describe the space of 2D layered materials from monolayers to twisted assemblies of arbitrary composition, existent or not-yet-fabricated. The notation corresponds to a theoretical materials concept of stepwise assembly of layered structures using a sequence of rotation, vertical stacking, and other operations on individual 2D layers. Its scope is demonstrated with a number of example structures using common single-layer materials as building blocks. This work overall aims to contribute to the systematic codification, capture and transfer of materials knowledge in the area of 2D layered materials.

cond-mat.mtrl-sci↗

arXiv2019

A Hierarchy of Graph Neural Networks Based on Learnable Local Features

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNNs. As an example, we construct a simple architecture that exceeds the expressiveness of the Weisfeiler-Lehman graph isomorphism test. We empirically validate our theory on both synthetic and real-world benchmarks, and demonstrate our example's theoretical power translates to strong results on node classification, graph classification, and graph regression tasks.

cs.LG↗

arXiv2019

Encoder-Agnostic Adaptation for Conditional Language Generation

Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks. However it is an open-question how to use similar techniques for language generation. Early results in the encoder-agnostic setting have been mostly negative. In this work we explore methods for adapting a pretrained language model to arbitrary conditional input. We observe that pretrained transformer models are sensitive to large parameter changes during tuning. We therefore propose an adaptation that directly injects arbitrary conditioning into self attention, an approach we call pseudo self attention. Through experiments on four diverse conditional text generation tasks we show that this encoder-agnostic technique outperforms strong baselines, produces coherent generations, and is data efficient.

cs.CL↗

arXiv2019

Neural Linguistic Steganography

Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal. Language is a particularly pragmatic cover signal due to its benign occurrence and independence from any one medium. Traditionally, linguistic steganography systems encode secret messages in existing text via synonym substitution or word order rearrangements. Advances in neural language models enable previously impractical generation-based techniques. We propose a steganography technique based on arithmetic coding with large-scale neural language models. We find that our approach can generate realistic looking cover sentences as evaluated by humans, while at the same time preserving security by matching the cover message distribution with the language model distribution.

cs.CL↗

arXiv2019

Commonsense Knowledge Mining from Pretrained Models

Inferring commonsense knowledge is a key challenge in natural language processing, but due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on novel data. In this work, we develop a method for generating commonsense knowledge using a large, pre-trained bidirectional language model. By transforming relational triples into masked sentences, we can use this model to rank a triple's validity by the estimated pointwise mutual information between the two entities. Since we do not update the weights of the bidirectional model, our approach is not biased by the coverage of any one commonsense knowledge base. Though this method performs worse on a test set than models explicitly trained on a corresponding training set, it outperforms these methods when mining commonsense knowledge from new sources, suggesting that unsupervised techniques may generalize better than current supervised approaches.

cs.CL↗

arXiv2019

MASR: A Modular Accelerator for Sparse RNNs

Recurrent neural networks (RNNs) are becoming the de facto solution for speech recognition. RNNs exploit long-term temporal relationships in data by applying repeated, learned transformations. Unlike fully-connected (FC) layers with single vector matrix operations, RNN layers consist of hundreds of such operations chained over time. This poses challenges unique to RNNs that are not found in convolutional neural networks (CNNs) or FC models, namely large dynamic activation. In this paper we present MASR, a principled and modular architecture that accelerates bidirectional RNNs for on-chip ASR. MASR is designed to exploit sparsity in both dynamic activations and static weights. The architecture is enhanced by a series of dynamic activation optimizations that enable compact storage, ensure no energy is wasted computing null operations, and maintain high MAC utilization for highly parallel accelerator designs. In comparison to current state-of-the-art sparse neural network accelerators (e.g., EIE), MASR provides 2x area 3x energy, and 1.6x performance benefits. The modular nature of MASR enables designs that efficiently scale from resource-constrained low-power IoT applications to large-scale, highly parallel datacenter deployments.

eess.SP↗