We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model's prediction. White-box approaches have been successfully applied to similar problems in vision where one can directly optimize the continuous input. Optimization-based approaches become difficult in the language domain due to the discrete nature of text. We bypass this issue by directly optimizing in the latent space and leveraging a language model to generate candidate modifications from optimized latent representations. We additionally use Shapley values to estimate the combinatoric effect of multiple changes. We then use these estimates to guide a beam search for the final counterfactual text. We achieve favorable performance compared to recent white-box and black-box baselines using human and automatic evaluations. Ablation studies show that both latent optimization and the use of Shapley values improve success rate and the quality of the generated counterfactuals.
Transformer-based models achieve impressive performance on numerous Natural Language Inference (NLI) benchmarks when trained on respective training datasets. However, in certain cases, training samples may not be available or collecting them could be time-consuming and resource-intensive. In this work, we address the above challenge and present an explorative study on unsupervised NLI, a paradigm in which no human-annotated training samples are available. We investigate it under three settings: PH, P, and NPH that differ in the extent of unlabeled data available for learning. As a solution, we propose a procedural data generation approach that leverages a set of sentence transformations to collect PHL (Premise, Hypothesis, Label) triplets for training NLI models, bypassing the need for human-annotated training data. Comprehensive experiments with several NLI datasets show that the proposed approach results in accuracies of up to 66.75%, 65.9%, 65.39% in PH, P, and NPH settings respectively, outperforming all existing unsupervised baselines. Furthermore, fine-tuning our model with as little as ~0.1% of the human-annotated training dataset (500 instances) leads to 12.2% higher accuracy than the model trained from scratch on the same 500 instances. Supported by this superior performance, we conclude with a recommendation for collecting high-quality task-specific data.
NLP practitioners often want to take existing trained models and apply them to data from new domains. While fine-tuning or few-shot learning can be used to adapt a base model, there is no single recipe for making these techniques work; moreover, one may not have access to the original model weights if it is deployed as a black box. We study how to improve a black box model's performance on a new domain by leveraging explanations of the model's behavior. Our approach first extracts a set of features combining human intuition about the task with model attributions generated by black box interpretation techniques, then uses a simple calibrator, in the form of a classifier, to predict whether the base model was correct or not. We experiment with our method on two tasks, extractive question answering and natural language inference, covering adaptation from several pairs of domains with limited target-domain data. The experimental results across all the domain pairs show that explanations are useful for calibrating these models, boosting accuracy when predictions do not have to be returned on every example. We further show that the calibration model transfers to some extent between tasks.
Analysis of vision-and-language models has revealed their brittleness under linguistic phenomena such as paraphrasing, negation, textual entailment, and word substitutions with synonyms or antonyms. While data augmentation techniques have been designed to mitigate against these failure modes, methods that can integrate this knowledge into the training pipeline remain under-explored. In this paper, we present \textbf{SDRO}, a model-agnostic method that utilizes a set linguistic transformations in a distributed robust optimization setting, along with an ensembling technique to leverage these transformations during inference. Experiments on benchmark datasets with images (NLVR$^2$) and video (VIOLIN) demonstrate performance improvements as well as robustness to adversarial attacks. Experiments on binary VQA explore the generalizability of this method to other V\&L tasks.
In attempts to develop sample-efficient and interpretable algorithms, researcher have explored myriad mechanisms for collecting and exploiting feature feedback (or rationales) auxiliary annotations provided for training (but not test) instances that highlight salient evidence. Examples include bounding boxes around objects and salient spans in text. Despite its intuitive appeal, feature feedback has not delivered significant gains in practical problems as assessed on iid holdout sets. However, recent works on counterfactually augmented data suggest an alternative benefit of supplemental annotations, beyond interpretability: lessening sensitivity to spurious patterns and consequently delivering gains in out-of-domain evaluations. We speculate that while existing methods for incorporating feature feedback have delivered negligible in-sample performance gains, they may nevertheless provide out-of-domain benefits. Our experiments addressing sentiment analysis, show that feature feedback methods perform significantly better on various natural out-of-domain datasets despite comparable in-domain evaluations. By contrast, performance on natural language inference remains comparable. Finally, we compare those tasks where feature feedback does (and does not) help.
Optimal transport is a framework for comparing measures whereby a cost is incurred for transporting one measure to another. Recent works have aimed to improve optimal transport plans through the introduction of various forms of structure. We introduce novel order constraints into the optimal transport formulation to allow for the incorporation of structure. We define an efficient method for obtaining explainable solutions to the new formulation that scales far better than standard approaches. The theoretical properties of the method are provided. We demonstrate experimentally that order constraints improve explainability using the e-SNLI (Stanford Natural Language Inference) dataset that includes human-annotated rationales as well as on several image color transfer examples.
We present a framework for deriving inference relations between Dutch sentence pairs. The proposed framework relies on logic-based reasoning to produce inspectable proofs leading up to inference labels; its judgements are therefore transparent and formally verifiable. At its core, the system is powered by two ${\lambda}$-calculi, used as syntactic and semantic theories, respectively. Sentences are first converted to syntactic proofs and terms of the linear ${\lambda}$-calculus using a choice of two parsers: an Alpino-based pipeline, and Neural Proof Nets. The syntactic terms are then converted to semantic terms of the simply typed ${\lambda}$-calculus, via a set of hand designed type- and term-level transformations. Pairs of semantic terms are then fed to an automated theorem prover for natural logic which reasons with them while using the lexical relations found in the Open Dutch WordNet. We evaluate the reasoning pipeline on the recently created Dutch natural language inference dataset, and achieve promising results, remaining only within a $1.1-3.2{\%}$ performance margin to strong neural baselines. To the best of our knowledge, the reasoning pipeline is the first logic-based system for Dutch.
We propose a new approach, Knowledge Distillation using Optimal Transport (KNOT), to distill the natural language semantic knowledge from multiple teacher networks to a student network. KNOT aims to train a (global) student model by learning to minimize the optimal transport cost of its assigned probability distribution over the labels to the weighted sum of probabilities predicted by the (local) teacher models, under the constraints, that the student model does not have access to teacher models' parameters or training data. To evaluate the quality of knowledge transfer, we introduce a new metric, Semantic Distance (SD), that measures semantic closeness between the predicted and ground truth label distributions. The proposed method shows improvements in the global model's SD performance over the baseline across three NLP tasks while performing on par with Entropy-based distillation on standard accuracy and F1 metrics. The implementation pertaining to this work is publicly available at: https://github.com/declare-lab/KNOT.
Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent complex tasks) often pertain to various types of sub-tasks, requiring different kinds of reasoning. Certain types of reasoning have proven to be more difficult to learn in a monolingual context, and in the crosslingual context, similar observations may shed light on zero-shot transfer efficiency and few-shot sample selection. Hence, to investigate the effects of types of reasoning on transfer performance, we propose a category-annotated multilingual NLI dataset and discuss the challenges to scale monolingual annotations to multiple languages. We statistically observe interesting effects that the confluence of reasoning types and language similarities have on transfer performance.
Reviewing contracts is a time-consuming procedure that incurs large expenses to companies and social inequality to those who cannot afford it. In this work, we propose "document-level natural language inference (NLI) for contracts", a novel, real-world application of NLI that addresses such problems. In this task, a system is given a set of hypotheses (such as "Some obligations of Agreement may survive termination.") and a contract, and it is asked to classify whether each hypothesis is "entailed by", "contradicting to" or "not mentioned by" (neutral to) the contract as well as identifying "evidence" for the decision as spans in the contract. We annotated and release the largest corpus to date consisting of 607 annotated contracts. We then show that existing models fail badly on our task and introduce a strong baseline, which (1) models evidence identification as multi-label classification over spans instead of trying to predict start and end tokens, and (2) employs more sophisticated context segmentation for dealing with long documents. We also show that linguistic characteristics of contracts, such as negations by exceptions, are contributing to the difficulty of this task and that there is much room for improvement.
We present three Natural Language Inference (NLI) challenge sets that can evaluate NLI models on their understanding of temporal expressions. More specifically, we probe these models for three temporal properties: (a) the order between points in time, (b) the duration between two points in time, (c) the relation between the magnitude of times specified in different units. We find that although large language models fine-tuned on MNLI have some basic perception of the order between points in time, at large, these models do not have a thorough understanding of the relation between temporal expressions.
Reporting and providing test sets for harmful bias in NLP applications is essential for building a robust understanding of the current problem. We present a new observation of gender bias in a downstream NLP application: marked attribute bias in natural language inference. Bias in downstream applications can stem from training data, word embeddings, or be amplified by the model in use. However, focusing on biased word embeddings is potentially the most impactful first step due to their universal nature. Here we seek to understand how the intrinsic properties of word embeddings contribute to this observed marked attribute effect, and whether current post-processing methods address the bias successfully. An investigation of the current debiasing landscape reveals two open problems: none of the current debiased embeddings mitigate the marked attribute error, and none of the intrinsic bias measures are predictive of the marked attribute effect. By noticing that a new type of intrinsic bias measure correlates meaningfully with the marked attribute effect, we propose a new postprocessing debiasing scheme for static word embeddings. The proposed method applied to existing embeddings achieves new best results on the marked attribute bias test set. See https://github.com/hillary-dawkins/MAB.
It is well known that natural language models are vulnerable to adversarial attacks, which are mostly input-specific in nature. Recently, it has been shown that there also exist input-agnostic attacks in NLP models, called universal adversarial triggers. However, existing methods to craft universal triggers are data intensive. They require large amounts of data samples to generate adversarial triggers, which are typically inaccessible by attackers. For instance, previous works take 3000 data samples per class for the SNLI dataset to generate adversarial triggers. In this paper, we present a novel data-free approach, MINIMAL, to mine input-agnostic adversarial triggers from models. Using the triggers produced with our data-free algorithm, we reduce the accuracy of Stanford Sentiment Treebank's positive class from 93.6% to 9.6%. Similarly, for the Stanford Natural Language Inference (SNLI), our single-word trigger reduces the accuracy of the entailment class from 90.95% to less than 0.6\%. Despite being completely data-free, we get equivalent accuracy drops as data-dependent methods.
Human evaluation for summarization tasks is reliable but brings in issues of reproducibility and high costs. Automatic metrics are cheap and reproducible but sometimes poorly correlated with human judgment. In this work, we propose flexible semiautomatic to automatic summary evaluation metrics, following the Pyramid human evaluation method. Semi-automatic Lite2Pyramid retains the reusable human-labeled Summary Content Units (SCUs) for reference(s) but replaces the manual work of judging SCUs' presence in system summaries with a natural language inference (NLI) model. Fully automatic Lite3Pyramid further substitutes SCUs with automatically extracted Semantic Triplet Units (STUs) via a semantic role labeling (SRL) model. Finally, we propose in-between metrics, Lite2.xPyramid, where we use a simple regressor to predict how well the STUs can simulate SCUs and retain SCUs that are more difficult to simulate, which provides a smooth transition and balance between automation and manual evaluation. Comparing to 15 existing metrics, we evaluate human-metric correlations on 3 existing meta-evaluation datasets and our newly-collected PyrXSum (with 100/10 XSum examples/systems). It shows that Lite2Pyramid consistently has the best summary-level correlations; Lite3Pyramid works better than or comparable to other automatic metrics; Lite2.xPyramid trades off small correlation drops for larger manual effort reduction, which can reduce costs for future data collection. Our code and data are publicly available at: https://github.com/ZhangShiyue/Lite2-3Pyramid
We explore the impact of leveraging the relatedness of languages that belong to the same family in NLP models using multilingual fine-tuning. We hypothesize and validate that multilingual fine-tuning of pre-trained language models can yield better performance on downstream NLP applications, compared to models fine-tuned on individual languages. A first of its kind detailed study is presented to track performance change as languages are added to a base language in a graded and greedy (in the sense of best boost of performance) manner; which reveals that careful selection of subset of related languages can significantly improve performance than utilizing all related languages. The Indo-Aryan (IA) language family is chosen for the study, the exact languages being Bengali, Gujarati, Hindi, Marathi, Oriya, Punjabi and Urdu. The script barrier is crossed by simple rule-based transliteration of the text of all languages to Devanagari. Experiments are performed on mBERT, IndicBERT, MuRIL and two RoBERTa-based LMs, the last two being pre-trained by us. Low resource languages, such as Oriya and Punjabi, are found to be the largest beneficiaries of multilingual fine-tuning. Textual Entailment, Entity Classification, Section Title Prediction, tasks of IndicGLUE and POS tagging form our test bed. Compared to monolingual fine tuning we get relative performance improvement of up to 150% in the downstream tasks. The surprise take-away is that for any language there is a particular combination of other languages which yields the best performance, and any additional language is in fact detrimental.
Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.
Natural language inference (NLI) aims to determine the logical relationship between two sentences, such as Entailment, Contradiction, and Neutral. In recent years, deep learning models have become a prevailing approach to NLI, but they lack interpretability and explainability. In this work, we address the explainability of NLI by weakly supervised logical reasoning, and propose an Explainable Phrasal Reasoning (EPR) approach. Our model first detects phrases as the semantic unit and aligns corresponding phrases in the two sentences. Then, the model predicts the NLI label for the aligned phrases, and induces the sentence label by fuzzy logic formulas. Our EPR is almost everywhere differentiable and thus the system can be trained end to end. In this way, we are able to provide explicit explanations of phrasal logical relationships in a weakly supervised manner. We further show that such reasoning results help textual explanation generation.
Large pretrained language models (PreLMs) are revolutionizing natural language processing across all benchmarks. However, their sheer size is prohibitive for small laboratories or for deployment on mobile devices. Approaches like pruning and distillation reduce the model size but typically retain the same model architecture. In contrast, we explore distilling PreLMs into a different, more efficient architecture, Continual Multiplication of Words (CMOW), which embeds each word as a matrix and uses matrix multiplication to encode sequences. We extend the CMOW architecture and its CMOW/CBOW-Hybrid variant with a bidirectional component for more expressive power, per-token representations for a general (task-agnostic) distillation during pretraining, and a two-sequence encoding scheme that facilitates downstream tasks on sentence pairs, such as sentence similarity and natural language inference. Our matrix-based bidirectional CMOW/CBOW-Hybrid model is competitive to DistilBERT on question similarity and recognizing textual entailment, but uses only half of the number of parameters and is three times faster in terms of inference speed. We match or exceed the scores of ELMo for all tasks of the GLUE benchmark except for the sentiment analysis task SST-2 and the linguistic acceptability task CoLA. However, compared to previous cross-architecture distillation approaches, we demonstrate a doubling of the scores on detecting linguistic acceptability. This shows that matrix-based embeddings can be used to distill large PreLM into competitive models and motivates further research in this direction.
Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilities that go far beyond sentence completion including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems, exploiting language models as a source of task knowledge, especially for task learning, offers significant, near-term benefits. We introduce language models and the various tasks to which they have been applied and then review methods of knowledge extraction from language models. The resulting analysis outlines both the challenges and opportunities for using language models as a new knowledge source for cognitive systems. It also identifies possible ways to improve knowledge extraction from language models using the capabilities provided by cognitive systems. Central to success will be the ability of a cognitive agent to itself learn an abstract model of the knowledge implicit in the LM as well as methods to extract high-quality knowledge effectively and efficiently. To illustrate, we introduce a hypothetical robot agent and describe how language models could extend its task knowledge and improve its performance and the kinds of knowledge and methods the agent can use to exploit the knowledge within a language model.
Natural language inference (NLI) requires models to learn and apply commonsense knowledge. These reasoning abilities are particularly important for explainable NLI systems that generate a natural language explanation in addition to their label prediction. The integration of external knowledge has been shown to improve NLI systems, here we investigate whether it can also improve their explanation capabilities. For this, we investigate different sources of external knowledge and evaluate the performance of our models on in-domain data as well as on special transfer datasets that are designed to assess fine-grained reasoning capabilities. We find that different sources of knowledge have a different effect on reasoning abilities, for example, implicit knowledge stored in language models can hinder reasoning on numbers and negations. Finally, we conduct the largest and most fine-grained explainable NLI crowdsourcing study to date. It reveals that even large differences in automatic performance scores do neither reflect in human ratings of label, explanation, commonsense nor grammar correctness.