Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Tal Linzen, Grzegorz Chrupała, Afra Alishahi (Editors)


Anthology ID:
W18-54
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
URL:
https://aclanthology.org/W18-54
DOI:
Bib Export formats:
BibTeX
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/W18-54.pdf

pdf bib
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Tal Linzen | Grzegorz Chrupała | Afra Alishahi

pdf bib
When does deep multi-task learning work for loosely related document classification tasks?
Emma Kerinec | Chloé Braud | Anders Søgaard

This work aims to contribute to our understanding of when multi-task learning through parameter sharing in deep neural networks leads to improvements over single-task learning. We focus on the setting of learning from loosely related tasks, for which no theoretical guarantees exist. We therefore approach the question empirically, studying which properties of datasets and single-task learning characteristics correlate with improvements from multi-task learning. We are the first to study this in a text classification setting and across more than 500 different task pairs.

pdf bib
Analyzing Learned Representations of a Deep ASR Performance Prediction Model
Zied Elloumi | Laurent Besacier | Olivier Galibert | Benjamin Lecouteux

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text embeddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information at training time through multi-task learning. Our experiments show that this allows to train slightly more efficient ASR performance prediction systems that - in addition - simultaneously tag the analyzed utterances according to their speech style, accent and broadcast program origin.

pdf
Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures
Danilo Croce | Daniele Rossini | Roberto Basili

Nonlinear methods such as deep neural networks achieve state-of-the-art performances in several semantic NLP tasks. However epistemologically transparent decisions are not provided as for the limited interpretability of the underlying acquired neural models. In neural-based semantic inference tasks epistemological transparency corresponds to the ability of tracing back causal connections between the linguistic properties of a input instance and the produced classification output. In this paper, we propose the use of a methodology, called Layerwise Relevance Propagation, over linguistically motivated neural architectures, namely Kernel-based Deep Architectures (KDA), to guide argumentations and explanation inferences. In such a way, each decision provided by a KDA can be linked to real examples, linguistically related to the input instance: these can be used to motivate the network output. Quantitative analysis shows that richer explanations about the semantic and syntagmatic structures of the examples characterize more convincing arguments in two tasks, i.e. question classification and semantic role labeling.

pdf
Nightmare at test time: How punctuation prevents parsers from generalizing
Anders Søgaard | Miryam de Lhoneux | Isabelle Augenstein

Punctuation is a strong indicator of syntactic structure, and parsers trained on text with punctuation often rely heavily on this signal. Punctuation is a diversion, however, since human language processing does not rely on punctuation to the same extent, and in informal texts, we therefore often leave out punctuation. We also use punctuation ungrammatically for emphatic or creative purposes, or simply by mistake. We show that (a) dependency parsers are sensitive to both absence of punctuation and to alternative uses; (b) neural parsers tend to be more sensitive than vintage parsers; (c) training neural parsers without punctuation outperforms all out-of-the-box parsers across all scenarios where punctuation departs from standard punctuation. Our main experiments are on synthetically corrupted data to study the effect of punctuation in isolation and avoid potential confounds, but we also show effects on out-of-domain data.

pdf
Evaluating Textual Representations through Image Generation
Graham Spinks | Marie-Francine Moens

We present a methodology for determining the quality of textual representations through the ability to generate images from them. Continuous representations of textual input are ubiquitous in modern Natural Language Processing techniques either at the core of machine learning algorithms or as the by-product at any given layer of a neural network. While current techniques to evaluate such representations focus on their performance on particular tasks, they don’t provide a clear understanding of the level of informational detail that is stored within them, especially their ability to represent spatial information. The central premise of this paper is that visual inspection or analysis is the most convenient method to quickly and accurately determine information content. Through the use of text-to-image neural networks, we propose a new technique to compare the quality of textual representations by visualizing their information content. The method is illustrated on a medical dataset where the correct representation of spatial information and shorthands are of particular importance. For four different well-known textual representations, we show with a quantitative analysis that some representations are consistently able to deliver higher quality visualizations of the information content. Additionally, we show that the quantitative analysis technique correlates with the judgment of a human expert evaluator in terms of alignment.

pdf
On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis
Jose Camacho-Collados | Mohammad Taher Pilehvar

Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep learning literature. In this paper we investigate the impact of simple text preprocessing decisions (particularly tokenizing, lemmatizing, lowercasing and multiword grouping) on the performance of a standard neural text classifier. We perform an extensive evaluation on standard benchmarks from text categorization and sentiment analysis. While our experiments show that a simple tokenization of input text is generally adequate, they also highlight significant degrees of variability across preprocessing techniques. This reveals the importance of paying attention to this usually-overlooked step in the pipeline, particularly when comparing different models. Finally, our evaluation provides insights into the best preprocessing practices for training word embeddings.

pdf
Jump to better conclusions: SCAN both left and right
Jasmijn Bastings | Marco Baroni | Jason Weston | Kyunghyun Cho | Douwe Kiela

Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple commands paired with action sequences and is intended to test the strong generalization abilities of recurrent sequence-to-sequence models. Their initial experiments suggested that such models may fail because they lack the ability to extract systematic rules. Here, we take a closer look at SCAN and show that it does not always capture the kind of generalization that it was designed for. To mitigate this we propose a complementary dataset, which requires mapping actions back to the original commands, called NACS. We show that models that do well on SCAN do not necessarily do well on NACS, and that NACS exhibits properties more closely aligned with realistic use-cases for sequence-to-sequence models.

pdf
Understanding Convolutional Neural Networks for Text Classification
Alon Jacovi | Oren Sar Shalom | Yoav Goldberg

We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs remain a mystery. We aim to understand the method by which the networks process and classify text. We examine common hypotheses to this problem: that filters, accompanied by global max-pooling, serve as ngram detectors. We show that filters may capture several different semantic classes of ngrams by using different activation patterns, and that global max-pooling induces behavior which separates important ngrams from the rest. Finally, we show practical use cases derived from our findings in the form of model interpretability (explaining a trained model by deriving a concrete identity for each filter, bridging the gap between visualization tools in vision tasks and NLP) and prediction interpretability (explaining predictions).

pdf
Linguistic representations in multi-task neural networks for ellipsis resolution
Ola Rønning | Daniel Hardt | Anders Søgaard

Sluicing resolution is the task of identifying the antecedent to a question ellipsis. Antecedents are often sentential constituents, and previous work has therefore relied on syntactic parsing, together with complex linguistic features. A recent model instead used partial parsing as an auxiliary task in sequential neural network architectures to inject syntactic information. We explore the linguistic information being brought to bear by such networks, both by defining subsets of the data exhibiting relevant linguistic characteristics, and by examining the internal representations of the network. Both perspectives provide evidence for substantial linguistic knowledge being deployed by the neural networks.

pdf
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models
Shun Kiyono | Sho Takase | Jun Suzuki | Naoaki Okazaki | Kentaro Inui | Masaaki Nagata

Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor. Conventionally, many studies have used an attention matrix to interpret how Encoder-Decoder-based models translate a given source sentence to the corresponding target sentence. However, recent studies have empirically revealed that an attention matrix is not optimal for token-wise translation analyses. We propose a method that explicitly models the token-wise alignment between the source and target sequences to provide a better analysis. Experiments show that our method can acquire token-wise alignments that are superior to those of an attention mechanism.

pdf
Rule induction for global explanation of trained models
Madhumita Sushil | Simon Šuster | Walter Daelemans

Understanding the behavior of a trained network and finding explanations for its outputs is important for improving the network’s performance and generalization ability, and for ensuring trust in automated systems. Several approaches have previously been proposed to identify and visualize the most important features by analyzing a trained network. However, the relations between different features and classes are lost in most cases. We propose a technique to induce sets of if-then-else rules that capture these relations to globally explain the predictions of a network. We first calculate the importance of the features in the trained network. We then weigh the original inputs with these feature importance scores, simplify the transformed input space, and finally fit a rule induction model to explain the model predictions. We find that the output rule-sets can explain the predictions of a neural network trained for 4-class text classification from the 20 newsgroups dataset to a macro-averaged F-score of 0.80. We make the code available at https://github.com/clips/interpret_with_rules.

pdf
Can LSTM Learn to Capture Agreement? The Case of Basque
Shauli Ravfogel | Yoav Goldberg | Francis Tyers

Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical structures typical to human language, and what kind of grammatical phenomena can they acquire? We focus on the task of agreement prediction in Basque, as a case study for a task that requires implicit understanding of sentence structure and the acquisition of a complex but consistent morphological system. Analyzing experimental results from two syntactic prediction tasks – verb number prediction and suffix recovery – we find that sequential models perform worse on agreement prediction in Basque than one might expect on the basis of a previous agreement prediction work in English. Tentative findings based on diagnostic classifiers suggest the network makes use of local heuristics as a proxy for the hierarchical structure of the sentence. We propose the Basque agreement prediction task as challenging benchmark for models that attempt to learn regularities in human language.

pdf
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
João Loula | Marco Baroni | Brenden Lake

Systematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it’s seen as key to the human capacity for generalization in language. Recent work (Lake and Baroni, 2018) has studied systematic compositionality in modern seq2seq models using generalization to novel navigation instructions in a grounded environment as a probing tool. Lake and Baroni’s main experiment required the models to quickly bootstrap the meaning of new words. We extend this framework here to settings where the model needs only to recombine well-trained functional words (such as “around” and “right”) in novel contexts. Our findings confirm and strengthen the earlier ones: seq2seq models can be impressively good at generalizing to novel combinations of previously-seen input, but only when they receive extensive training on the specific pattern to be generalized (e.g., generalizing from many examples of “X around right” to “jump around right”), while failing when generalization requires novel application of compositional rules (e.g., inferring the meaning of “around right” from those of “right” and “around”).

pdf
Evaluating the Ability of LSTMs to Learn Context-Free Grammars
Luzi Sennhauser | Robert Berwick

While long short-term memory (LSTM) neural net architectures are designed to capture sequence information, human language is generally composed of hierarchical structures. This raises the question as to whether LSTMs can learn hierarchical structures. We explore this question with a well-formed bracket prediction task using two types of brackets modeled by an LSTM. Demonstrating that such a system is learnable by an LSTM is the first step in demonstrating that the entire class of CFLs is also learnable. We observe that the model requires exponential memory in terms of the number of characters and embedded depth, where a sub-linear memory should suffice. Still, the model does more than memorize the training input. It learns how to distinguish between relevant and irrelevant information. On the other hand, we also observe that the model does not generalize well. We conclude that LSTMs do not learn the relevant underlying context-free rules, suggesting the good overall performance is attained rather by an efficient way of evaluating nuisance variables. LSTMs are a way to quickly reach good results for many natural language tasks, but to understand and generate natural language one has to investigate other concepts that can make more direct use of natural language’s structural nature.

pdf
Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style
Reid Pryzant | Sugato Basu | Kazoo Sone

How much does “free shipping!” help an advertisement’s ability to persuade? This paper presents two methods for performance attribution: finding the degree to which an outcome can be attributed to parts of a text while controlling for potential confounders. Both algorithms are based on interpreting the behaviors and parameters of trained neural networks. One method uses a CNN to encode the text, an adversarial objective function to control for confounders, and projects its weights onto its activations to interpret the importance of each phrase towards each output class. The other method leverages residualization to control for confounds and performs interpretation by aggregating over learned word vectors. We demonstrate these algorithms’ efficacy on 118,000 internet search advertisements and outcomes, finding language indicative of high and low click through rate (CTR) regardless of who the ad is by or what it is for. Our results suggest the proposed algorithms are high performance and data efficient, able to glean actionable insights from fewer than 10,000 data points. We find that quick, easy, and authoritative language is associated with success, while lackluster embellishment is related to failure. These findings agree with the advertising industry’s emperical wisdom, automatically revealing insights which previously required manual A/B testing to discover.

pdf
Interpreting Neural Networks with Nearest Neighbors
Eric Wallace | Shi Feng | Jordan Boyd-Graber

Local model interpretation methods explain individual predictions by assigning an importance value to each input feature. This value is often determined by measuring the change in confidence when a feature is removed. However, the confidence of neural networks is not a robust measure of model uncertainty. This issue makes reliably judging the importance of the input features difficult. We address this by changing the test-time behavior of neural networks using Deep k-Nearest Neighbors. Without harming text classification accuracy, this algorithm provides a more robust uncertainty metric which we use to generate feature importance values. The resulting interpretations better align with human perception than baseline methods. Finally, we use our interpretation method to analyze model predictions on dataset annotation artifacts.

pdf
‘Indicatements’ that character language models learn English morpho-syntactic units and regularities
Yova Kementchedjhieva | Adam Lopez

Character language models have access to surface morphological patterns, but it is not clear whether or how they learn abstract morphological regularities. We instrument a character language model with several probes, finding that it can develop a specific unit to identify word boundaries and, by extension, morpheme boundaries, which allows it to capture linguistic properties and regularities of these units. Our language model proves surprisingly good at identifying the selectional restrictions of English derivational morphemes, a task that requires both morphological and syntactic awareness. Thus we conclude that, when morphemes overlap extensively with the words of a language, a character language model can perform morphological abstraction.

pdf
LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation
Pankaj Gupta | Hinrich Schütze

Recurrent neural networks (RNNs) are temporal networks and cumulative in nature that have shown promising results in various natural language processing tasks. Despite their success, it still remains a challenge to understand their hidden behavior. In this work, we analyze and interpret the cumulative nature of RNN via a proposed technique named as Layer-wIse-Semantic-Accumulation (LISA) for explaining decisions and detecting the most likely (i.e., saliency) patterns that the network relies on while decision making. We demonstrate (1) LISA: “How an RNN accumulates or builds semantics during its sequential processing for a given text example and expected response” (2) Example2pattern: “How the saliency patterns look like for each category in the data according to the network in decision making”. We analyse the sensitiveness of RNNs about different inputs to check the increase or decrease in prediction scores and further extract the saliency patterns learned by the network. We employ two relation classification datasets: SemEval 10 Task 8 and TAC KBP Slot Filling to explain RNN predictions via the LISA and example2pattern.

pdf
Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue
Dieuwke Hupkes | Sanne Bouwmeester | Raquel Fernández

We investigate how encoder-decoder models trained on a synthetic dataset of task-oriented dialogues process disfluencies, such as hesitations and self-corrections. We find that, contrary to earlier results, disfluencies have very little impact on the task success of seq-to-seq models with attention. Using visualisations and diagnostic classifiers, we analyse the representations that are incrementally built by the model, and discover that models develop little to no awareness of the structure of disfluencies. However, adding disfluencies to the data appears to help the model create clearer representations overall, as evidenced by the attention patterns the different models exhibit.

pdf
An Operation Sequence Model for Explainable Neural Machine Translation
Felix Stahlberg | Danielle Saunders | Bill Byrne

We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the target sentence by monotonically walking through the source sentence. Word reordering is modeled by operations which allow setting markers in the target sentence and move a target-side write head between those markers. In contrast to many modern neural models, our system emits explicit word alignment information which is often crucial to practical machine translation as it improves explainability. Our technique can outperform a plain text system in terms of BLEU score under the recent Transformer architecture on Japanese-English and Portuguese-English, and is within 0.5 BLEU difference on Spanish-English.

pdf
Introspection for convolutional automatic speech recognition
Andreas Krug | Sebastian Stober

Artificial Neural Networks (ANNs) have experienced great success in the past few years. The increasing complexity of these models leads to less understanding about their decision processes. Therefore, introspection techniques have been proposed, mostly for images as input data. Patterns or relevant regions in images can be intuitively interpreted by a human observer. This is not the case for more complex data like speech recordings. In this work, we investigate the application of common introspection techniques from computer vision to an Automatic Speech Recognition (ASR) task. To this end, we use a model similar to image classification, which predicts letters from spectrograms. We show difficulties in applying image introspection to ASR. To tackle these problems, we propose normalized averaging of aligned inputs (NAvAI): a data-driven method to reveal learned patterns for prediction of specific classes. Our method integrates information from many data examples through local introspection techniques for Convolutional Neural Networks (CNNs). We demonstrate that our method provides better interpretability of letter-specific patterns than existing methods.

pdf
Learning and Evaluating Sparse Interpretable Sentence Embeddings
Valentin Trifonov | Octavian-Eugen Ganea | Anna Potapenko | Thomas Hofmann

Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data. In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation. We further introduce a novel, quantitative and automated evaluation metric for sentence embedding interpretability, based on topic coherence methods. We observe an increase in interpretability compared to dense models, on a dataset of movie dialogs and on the scene descriptions from the MS COCO dataset.

pdf
What do RNN Language Models Learn about Filler–Gap Dependencies?
Ethan Wilcox | Roger Levy | Takashi Morita | Richard Futrell

RNN language models have achieved state-of-the-art perplexity results and have proven useful in a suite of NLP tasks, but it is as yet unclear what syntactic generalizations they learn. Here we investigate whether state-of-the-art RNN language models represent long-distance filler–gap dependencies and constraints on them. Examining RNN behavior on experimentally controlled sentences designed to expose filler–gap dependencies, we show that RNNs can represent the relationship in multiple syntactic positions and over large spans of text. Furthermore, we show that RNNs learn a subset of the known restrictions on filler–gap dependencies, known as island constraints: RNNs show evidence for wh-islands, adjunct islands, and complex NP islands. These studies demonstrates that state-of-the-art RNN models are able to learn and generalize about empty syntactic positions.

pdf
Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items
Jaap Jumelet | Dieuwke Hupkes

In this paper, we attempt to link the inner workings of a neural language model to linguistic theory, focusing on a complex phenomenon well discussed in formal linguistics: (negative) polarity items. We briefly discuss the leading hypotheses about the licensing contexts that allow negative polarity items and evaluate to what extent a neural language model has the ability to correctly process a subset of such constructions. We show that the model finds a relation between the licensing context and the negative polarity item and appears to be aware of the scope of this context, which we extract from a parse tree of the sentence. With this research, we hope to pave the way for other studies linking formal linguistics to deep learning.

pdf
Closing Brackets with Recurrent Neural Networks
Natalia Skachkova | Thomas Trost | Dietrich Klakow

Many natural and formal languages contain words or symbols that require a matching counterpart for making an expression well-formed. The combination of opening and closing brackets is a typical example of such a construction. Due to their commonness, the ability to follow such rules is important for language modeling. Currently, recurrent neural networks (RNNs) are extensively used for this task. We investigate whether they are capable of learning the rules of opening and closing brackets by applying them to synthetic Dyck languages that consist of different types of brackets. We provide an analysis of the statistical properties of these languages as a baseline and show strengths and limits of Elman-RNNs, GRUs and LSTMs in experiments on random samples of these languages. In terms of perplexity and prediction accuracy, the RNNs get close to the theoretical baseline in most cases.

pdf
Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information
Mario Giulianelli | Jack Harding | Florian Mohnert | Dieuwke Hupkes | Willem Zuidema

How do neural language models keep track of number agreement between subject and verb? We show that ‘diagnostic classifiers’, trained to predict number from the internal states of a language model, provide a detailed understanding of how, when, and where this information is represented. Moreover, they give us insight into when and where number information is corrupted in cases where the language model ends up making agreement errors. To demonstrate the causal role played by the representations we find, we then use agreement information to influence the course of the LSTM during the processing of difficult sentences. Results from such an intervention reveal a large increase in the language model’s accuracy. Together, these results show that diagnostic classifiers give us an unrivalled detailed look into the representation of linguistic information in neural models, and demonstrate that this knowledge can be used to improve their performance.

pdf
Iterative Recursive Attention Model for Interpretable Sequence Classification
Martin Tutek | Jan Šnajder

Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks that involve a series of inference steps. We describe an iterative recursive attention model, which constructs incremental representations of input data through reusing results of previously computed queries. We train our model on sentiment classification datasets and demonstrate its capacity to identify and combine different aspects of the input in an easily interpretable manner, while obtaining performance close to the state of the art.

pdf
Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models
Avery Hiebert | Cole Peterson | Alona Fyshe | Nishant Mehta

While Long Short-Term Memory networks (LSTMs) and other forms of recurrent neural network have been successfully applied to language modeling on a character level, the hidden state dynamics of these models can be difficult to interpret. We investigate the hidden states of such a model by using the HDBSCAN clustering algorithm to identify points in the text at which the hidden state is similar. Focusing on whitespace characters prior to the beginning of a word reveals interpretable clusters that offer insight into how the LSTM may combine contextual and character-level information to identify parts of speech. We also introduce a method for deriving word vectors from the hidden state representation in order to investigate the word-level knowledge of the model. These word vectors encode meaningful semantic information even for words that appear only once in the training text.

pdf
Importance of Self-Attention for Sentiment Analysis
Gaël Letarte | Frédérik Paradis | Philippe Giguère | François Laviolette

Despite their superior performance, deep learning models often lack interpretability. In this paper, we explore the modeling of insightful relations between words, in order to understand and enhance predictions. To this effect, we propose the Self-Attention Network (SANet), a flexible and interpretable architecture for text classification. Experiments indicate that gains obtained by self-attention is task-dependent. For instance, experiments on sentiment analysis tasks showed an improvement of around 2% when using self-attention compared to a baseline without attention, while topic classification showed no gain. Interpretability brought forward by our architecture highlighted the importance of neighboring word interactions to extract sentiment.

pdf
Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell
Pia Sommerauer | Antske Fokkens

This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and compares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.

pdf
An Analysis of Encoder Representations in Transformer-Based Machine Translation
Alessandro Raganato | Jörg Tiedemann

The attention mechanism is a successful technique in modern NLP, especially in tasks like machine translation. The recently proposed network architecture of the Transformer is based entirely on attention mechanisms and achieves new state of the art results in neural machine translation, outperforming other sequence-to-sequence models. However, so far not much is known about the internal properties of the model and the representations it learns to achieve that performance. To study this question, we investigate the information that is learned by the attention mechanism in Transformer models with different translation quality. We assess the representations of the encoder by extracting dependency relations based on self-attention weights, we perform four probing tasks to study the amount of syntactic and semantic captured information and we also test attention in a transfer learning scenario. Our analysis sheds light on the relative strengths and weaknesses of the various encoder representations. We observe that specific attention heads mark syntactic dependency relations and we can also confirm that lower layers tend to learn more about syntax while higher layers tend to encode more semantics.

pdf
Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation
Johnny Wei | Khiem Pham | Brendan O’Connor | Brian Dillon

Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93% of the model translations are parseable, suggesting that it learns to generate conforming to a grammar. The model has trouble learning the distribution of rarer syntactic rules, and we pinpoint several constructions that differentiate translations between the references and our model.

pdf
Context-Free Transductions with Neural Stacks
Yiding Hao | William Merrill | Dana Angluin | Robert Frank | Noah Amsel | Andrew Benz | Simon Mendelsohn

This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more complex networks often find approximate solutions by using the stack as unstructured memory.

pdf
Learning Explanations from Language Data
David Harbecke | Robert Schwarzenberg | Christoph Alt

PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks. We demonstrate that it also generates meaningful interpretations in the language domain.

pdf
How much should you ask? On the question structure in QA systems.
Barbara Rychalska | Dominika Basaj | Anna Wróblewska | Przemyslaw Biecek

Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner. However, users are still used to query-like systems where they type in keywords to search for answer. In this study we validate which parts of questions are essential for obtaining valid answer. In order to conclude that, we take advantage of LIME - a framework that explains prediction by local approximation. We find that grammar and natural language is disregarded by QA. State-of-the-art model can answer properly even if ’asked’ only with a few words with high coefficients calculated with LIME. According to our knowledge, it is the first time that QA model is being explained by LIME.

pdf
Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System
Barbara Rychalska | Dominika Basaj | Anna Wróblewska | Przemyslaw Biecek

In this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset. We show that main verbs in questions carry little influence on the decisions made by the system - in over 90% of researched cases swapping verbs for their antonyms did not change system decision. We track this phenomenon down to the insides of the net, analyzing the mechanism of self-attention and values contained in hidden layers of RNN. Finally, we recognize the characteristics of the SQuAD dataset as the source of the problem. Our work refers to the recently popular topic of adversarial examples in NLP, combined with investigating deep net structure.

pdf
Interpretable Textual Neuron Representations for NLP
Nina Poerner | Benjamin Roth | Hinrich Schütze

Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs. We propose and evaluate ways of transferring this technology to NLP. Our results suggest that gradient ascent with a gumbel softmax layer produces n-gram representations that outperform naive corpus search in terms of target neuron activation. The representations highlight differences in syntax awareness between the language and visual models of the Imaginet architecture.

pdf
Language Models Learn POS First
Naomi Saphra | Adam Lopez

A glut of recent research shows that language models capture linguistic structure. Such work answers the question of whether a model represents linguistic structure. But how and when are these structures acquired? Rather than treating the training process itself as a black box, we investigate how representations of linguistic structure are learned over time. In particular, we demonstrate that different aspects of linguistic structure are learned at different rates, with part of speech tagging acquired early and global topic information learned continuously.

pdf
Predicting and interpreting embeddings for out of vocabulary words in downstream tasks
Nicolas Garneau | Jean-Samuel Leboeuf | Luc Lamontagne

We propose a novel way to handle out of vocabulary (OOV) words in downstream natural language processing (NLP) tasks. We implement a network that predicts useful embeddings for OOV words based on their morphology and on the context in which they appear. Our model also incorporates an attention mechanism indicating the focus allocated to the left context words, the right context words or the word’s characters, hence making the prediction more interpretable. The model is a “drop-in” module that is jointly trained with the downstream task’s neural network, thus producing embeddings specialized for the task at hand. When the task is mostly syntactical, we observe that our model aims most of its attention on surface form characters. On the other hand, for tasks more semantical, the network allocates more attention to the surrounding words. In all our tests, the module helps the network to achieve better performances in comparison to the use of simple random embeddings.

pdf
Probing sentence embeddings for structure-dependent tense
Geoff Bacon | Terry Regier

Learning universal sentence representations which accurately model sentential semantic content is a current goal of natural language processing research. A prominent and successful approach is to train recurrent neural networks (RNNs) to encode sentences into fixed length vectors. Many core linguistic phenomena that one would like to model in universal sentence representations depend on syntactic structure. Despite the fact that RNNs do not have explicit syntactic structural representations, there is some evidence that RNNs can approximate such structure-dependent phenomena under certain conditions, in addition to their widespread success in practical tasks. In this work, we assess RNNs’ ability to learn the structure-dependent phenomenon of main clause tense.

pdf
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
Adam Poliak | Aparajita Haldar | Rachel Rudinger | J. Edward Hu | Ellie Pavlick | Aaron Steven White | Benjamin Van Durme

We present a large scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation encoded by a neural network captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. Our collection of diverse datasets is available at http://www.decomp.net/, and will grow over time as additional resources are recast and added from novel sources.

pdf
Interpretable Word Embedding Contextualization
Kyoung-Rok Jang | Sung-Hyon Myaeng | Sang-Bum Kim

In this paper, we propose a method of calibrating a word embedding, so that the semantic it conveys becomes more relevant to the context. Our method is novel because the output shows clearly which senses that were originally presented in a target word embedding become stronger or weaker. This is possible by utilizing the technique of using sparse coding to recover senses that comprises a word embedding.

pdf
State Gradients for RNN Memory Analysis
Lyan Verwimp | Hugo Van hamme | Vincent Renkens | Patrick Wambacq

We present a framework for analyzing what the state in RNNs remembers from its input embeddings. We compute the gradients of the states with respect to the input embeddings and decompose the gradient matrix with Singular Value Decomposition to analyze which directions in the embedding space are best transferred to the hidden state space, characterized by the largest singular values. We apply our approach to LSTM language models and investigate to what extent and for how long certain classes of words are remembered on average for a certain corpus. Additionally, the extent to which a specific property or relationship is remembered by the RNN can be tracked by comparing a vector characterizing that property with the direction(s) in embedding space that are best preserved in hidden state space.

pdf
Extracting Syntactic Trees from Transformer Encoder Self-Attentions
David Mareček | Rudolf Rosa

This is a work in progress about extracting the sentence tree structures from the encoder’s self-attention weights, when translating into another language using the Transformer neural network architecture. We visualize the structures and discuss their characteristics with respect to the existing syntactic theories and annotations.

pdf
Portable, layer-wise task performance monitoring for NLP models
Tom Lippincott

There is a long-standing interest in understanding the internal behavior of neural networks. Deep neural architectures for natural language processing (NLP) are often accompanied by explanations for their effectiveness, from general observations (e.g. RNNs can represent unbounded dependencies in a sequence) to specific arguments about linguistic phenomena (early layers encode lexical information, deeper layers syntactic). The recent ascendancy of DNNs is fueling efforts in the NLP community to explore these claims. Previous work has tended to focus on easily-accessible representations like word or sentence embeddings, with deeper structure requiring more ad hoc methods to extract and examine. In this work, we introduce Vivisect, a toolkit that aims at a general solution for broad and fine-grained monitoring in the major DNN frameworks, with minimal change to research patterns.

pdf
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Alex Wang | Amanpreet Singh | Julian Michael | Felix Hill | Omer Levy | Samuel Bowman

Human ability to understand language is general, flexible, and robust. In contrast, most NLU models above the word level are designed for a specific task and struggle with out-of-domain data. If we aspire to develop models with understanding beyond the detection of superficial correspondences between inputs and outputs, then it is critical to develop a unified model that can execute a range of linguistic tasks across different domains. To facilitate research in this direction, we present the General Language Understanding Evaluation (GLUE, gluebenchmark.com): a benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models. For some benchmark tasks, training data is plentiful, but for others it is limited or does not match the genre of the test set. GLUE thus favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. While none of the datasets in GLUE were created from scratch for the benchmark, four of them feature privately-held test data, which is used to ensure that the benchmark is used fairly. We evaluate baselines that use ELMo (Peters et al., 2018), a powerful transfer learning technique, as well as state-of-the-art sentence representation models. The best models still achieve fairly low absolute scores. Analysis with our diagnostic dataset yields similarly weak performance over all phenomena tested, with some exceptions.

pdf
Explicitly modeling case improves neural dependency parsing
Clara Vania | Adam Lopez

Neural dependency parsing models that compose word representations from characters can presumably exploit morphosyntax when making attachment decisions. How much do they know about morphology? We investigate how well they handle morphological case, which is important for parsing. Our experiments on Czech, German and Russian suggest that adding explicit morphological case—either oracle or predicted—improves neural dependency parsing, indicating that the learned representations in these models do not fully encode the morphological knowledge that they need, and can still benefit from targeted forms of explicit linguistic modeling.

pdf
Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis
Kelly Zhang | Samuel Bowman

Recently, researchers have found that deep LSTMs trained on tasks like machine translation learn substantial syntactic and semantic information about their input sentences, including part-of-speech. These findings begin to shed light on why pretrained representations, like ELMo and CoVe, are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives—language modeling, translation, skip-thought, and autoencoding—on their ability to induce syntactic and part-of-speech information, holding constant the quantity and genre of the training data, as well as the LSTM architecture.

pdf
Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model
Steven Derby | Paul Miller | Brian Murphy | Barry Devereux

Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge.

pdf
Interpretable Structure Induction via Sparse Attention
Ben Peters | Vlad Niculae | André F. T. Martins

Neural network methods are experiencing wide adoption in NLP, thanks to their empirical performance on many tasks. Modern neural architectures go way beyond simple feedforward and recurrent models: they are complex pipelines that perform soft, differentiable computation instead of discrete logic. The price of such soft computing is the introduction of dense dependencies, which make it hard to disentangle the patterns that trigger a prediction. Our recent work on sparse and structured latent computation presents a promising avenue for enhancing interpretability of such neural pipelines. Through this extended abstract, we aim to discuss and explore the potential and impact of our methods.

pdf
Debugging Sequence-to-Sequence Models with Seq2Seq-Vis
Hendrik Strobelt | Sebastian Gehrmann | Michael Behrisch | Adam Perer | Hanspeter Pfister | Alexander Rush

Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks. They have become the standard approach for automatic translation of text, at the cost of increased model complexity and uncertainty. End-to-end trained neural models act as a black box, which makes it difficult to examine model decisions and attribute errors to a specific part of a model. The highly connected and high-dimensional internal representations pose a challenge for analysis and visualization tools. The development of methods to understand seq2seq predictions is crucial for systems in production settings, as mistakes involving language are often very apparent to human readers. For instance, a widely publicized incident resulted from a translation system mistakenly translating “good morning” into “attack them” leading to a wrongful arrest (Hern, 2017).

pdf
Grammar Induction with Neural Language Models: An Unusual Replication
Phu Mon Htut | Kyunghyun Cho | Samuel Bowman

Grammar induction is the task of learning syntactic structure without the expert-labeled treebanks (Charniak and Carroll, 1992; Klein and Manning, 2002). Recent work on latent tree learning offers a new family of approaches to this problem by inducing syntactic structure using the supervision from a downstream NLP task (Yogatama et al., 2017; Maillard et al., 2017; Choi et al., 2018). In a recent paper published at ICLR, Shen et al. (2018) introduce such a model and report near state-of-the-art results on the target task of language modeling, and the first strong latent tree learning result on constituency parsing. During the analysis of this model, we discover issues that make the original results hard to trust, including tuning and even training on what is effectively the test set. Here, we analyze the model under different configurations to understand what it learns and to identify the conditions under which it succeeds. We find that this model represents the first empirical success for neural network latent tree learning, and that neural language modeling warrants further study as a setting for grammar induction.

pdf
Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages?
Prajit Dhar | Arianna Bisazza

Recent work has shown that neural models can be successfully trained on multiple languages simultaneously. We investigate whether such models learn to share and exploit common syntactic knowledge among the languages on which they are trained. This extended abstract presents our preliminary results.

pdf
Exploiting Attention to Reveal Shortcomings in Memory Models
Kaylee Burns | Aida Nematzadeh | Erin Grant | Alison Gopnik | Tom Griffiths

The decision making processes of deep networks are difficult to understand and while their accuracy often improves with increased architectural complexity, so too does their opacity. Practical use of machine learning models, especially for question and answering applications, demands a system that is interpretable. We analyze the attention of a memory network model to reconcile contradictory performance on a challenging question-answering dataset that is inspired by theory-of-mind experiments. We equate success on questions to task classification, which explains not only test-time failures but also how well the model generalizes to new training conditions.

pdf
End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space
Pranava Swaroop Madhyastha | Josiah Wang | Lucia Specia

We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn ‘distributional similarity’ in a multimodal feature space, by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the ‘image’ side of image captioning, and vary the input image representation but keep the RNN text generation model of a CNN-RNN constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (ii) experience virtually no significant performance loss when a high dimensional representation is compressed to a lower dimensional space; (iii) cluster images with similar visual and linguistic information together. Our experiments all point to one fact: that our distributional similarity hypothesis holds. We conclude that, regardless of the image representation, image captioning systems seem to match images and generate captions in a learned joint image-text semantic subspace.

pdf
Limitations in learning an interpreted language with recurrent models
Denis Paperno

In this submission I report work in progress on learning simplified interpreted languages by means of recurrent models. The data is constructed to reflect core properties of natural language as modeled in formal syntax and semantics. Preliminary results suggest that LSTM networks do generalise to compositional interpretation, albeit only in the most favorable learning setting.