Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We focus on Knowledge Distillation (KD) techniques, in which a small student model learns to imitate a large teacher model, allowing to transfer knowledge from the teacher to the student. In contrast to much of the previous work, our goal is to optimize the model for a specific NLG task and a specific dataset. Typically in real-world applications, in addition to labeled data there is abundant unlabeled task-specific data, which is crucial for attaining high compression rates via KD. In this work, we conduct a systematic study of task-specific KD techniques for various NLG tasks under realistic assumptions. We discuss the special characteristics of NLG distillation and particularly the exposure bias problem. Following, we derive a family of Pseudo-Target (PT) augmentation methods, substantially extending prior work on sequence-level KD. We propose the Joint-Teaching method, which applies word-level KD to multiple PTs generated by both the teacher and the student.Finally, we validate our findings in an extreme setup with no labeled examples using GPT-4 as the teacher. Our study provides practical model design observations and demonstrates the effectiveness of PT training for task-specific KD in NLG.

Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact of compression on the generalizability and robustness of compressed models for out-of-distribution (OOD) data. Towards this end, we study two popular model compression techniques including knowledge distillation and pruning and show that the compressed models are significantly less robust than their PLM counterparts on OOD test sets although they obtain similar performance on in-distribution development sets for a task. Further analysis indicates that the compressed models overfit on the shortcut samples and generalize poorly on the hard ones. We further leverage this observation to develop a regularization strategy for robust model compression based on sample uncertainty.

State-of-the-art few-shot learning (FSL) methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. While much of the prior FSL methods focus on improving downstream task performance, there is a limited understanding of the adversarial robustness of such methods. In this work, we conduct an extensive study of several state-of-the-art FSL methods to assess their robustness to adversarial perturbations. To better understand the impact of various factors towards robustness (or the lack of it), we evaluate prompt-based FSL methods against fully fine-tuned models for aspects such as the use of unlabeled data, multiple prompts, number of few-shot examples, model size and type. Our results on six GLUE tasks indicate that compared to fully fine-tuned models, vanilla FSL methods lead to a notable relative drop in task performance (i.e., are less robust) in the face of adversarial perturbations. However, using (i) unlabeled data for prompt-based FSL and (ii) multiple prompts flip the trend – the few-shot learning approaches demonstrate a lesser drop in task performance than fully fine-tuned models. We further demonstrate that increasing the number of few-shot examples and model size lead to increased adversarial robustness of vanilla FSL methods. Broadly, our work sheds light on the adversarial robustness evaluation of prompt-based FSL methods for NLU tasks.

Mixture-of-Expert (MoE) models have obtained state-of-the-art performance in Neural Machine Translation (NMT) tasks. Existing works in MoE mostly consider a homogeneous design where the same number of experts of the same size are placed uniformly throughout the network. Furthermore, existing MoE works do not consider computational constraints (e.g., FLOPs, latency) to guide their design. To this end, we develop AutoMoE – a framework for designing heterogeneous MoE’s under computational constraints. AutoMoE leverages Neural Architecture Search (NAS) to obtain efficient sparse MoE sub-transformers with 4x inference speedup (CPU) and FLOPs reduction over manually designed Transformers, with parity in BLEU score over dense Transformer and within 1 BLEU point of MoE SwitchTransformer, on aggregate over benchmark datasets for NMT.Heterogeneous search space with dense and sparsely activated Transformer modules (e.g., how many experts? where to place them? what should be their sizes?) allows for adaptive compute – where different amounts of computations are used for different tokens in the input. Adaptivity comes naturally from routing decisions which send tokens to experts of different sizes. AutoMoE code, data, and trained models are available at https://aka.ms/AutoMoE.

We present a new method LiST for efficient fine-tuning of large pre-trained language models (PLMs) in few-shot learning settings. LiST improves over recent methods that adopt prompt-based fine-tuning (FN) using two key techniques. The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings. We use self-training in conjunction with meta-learning for re-weighting noisy pseudo-prompt labels. Traditionally, self-training is expensive as it requires updating all the model parameters repetitively. Therefore, we use a second technique for light-weight fine-tuning where we introduce a small number of task-specific parameters that are fine-tuned during self-training while keeping the PLM encoder frozen. Our experiments show that LiST can effectively leverage unlabeled data to improve the model performance for few-shot learning. Additionally, the finetuning process is efficient as it only updates a small percentage of the parameters and the overall model footprint is reduced since several tasks can share a common PLM encoder as backbone. We present a comprehensive study on six NLU tasks to validate the effectiveness of LiST. The results show that LiST improves by 35% over classic fine-tuning methods and 6% over prompt-based FN with 96% reduction in number of trainable parameters when fine-tuned with no more than 30 labeled examples from each task. With only 14M tunable parameters, LiST outperforms GPT-3 in-context learning by 33% on few-shot NLU tasks

Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this, parameter-efficient fine-tuning (PEFT) techniques were introduced where small trainable components are injected in the PLM and updated during fine-tuning. We propose AdaMix as a general PEFT method that tunes a mixture of adaptation modules – given the underlying PEFT method of choice – introduced in each Transformer layer while keeping most of the PLM weights frozen. For instance, AdaMix can leverage a mixture of adapters like Houlsby or a mixture of low rank decomposition matrices like LoRA to improve downstream task performance over the corresponding PEFT methods for fully supervised and few-shot NLU and NLG tasks. Further, we design AdaMix such that it matches the same computational cost and the number of tunable parameters as the underlying PEFT method. By only tuning 0.1-0.2% of PLM parameters, we show that AdaMix outperforms SOTA parameter-efficient fine-tuning and full model fine-tuning for both NLU and NLG tasks.

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing neural predictions by highlighting salient concepts in the text as justifications or rationales, they rely on thousands of labeled training examples for both task labels as well as annotated rationales for every instance. Such extensive large-scale annotations are infeasible to obtain for many tasks. To this end, we develop a multi-task teacher-student framework based on self-training pre-trained language models with limited task-specific labels and rationales and judicious sample selection to learn from informative pseudo-labeled examples. We study several characteristics of what constitutes a good rationale and demonstrate that the neural model performance can be significantly improved by making it aware of its rationalized predictions, particularly in low-resource settings. Extensive experiments in several benchmark datasets demonstrate the effectiveness of our approach.

The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an understudied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages – without access to large-scale monolingual corpora or large amounts of labeled data – for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to automatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.

Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to using them in practice. Some recent works use knowledge distillation to compress these huge models into shallow ones. In this work we study knowledge distillation with a focus on multilingual Named Entity Recognition (NER). In particular, we study several distillation strategies and propose a stage-wise optimization scheme leveraging teacher internal representations, that is agnostic of teacher architecture, and show that it outperforms strategies employed in prior works. Additionally, we investigate the role of several factors like the amount of unlabeled data, annotation resources, model architecture and inference latency to name a few. We show that our approach leads to massive compression of teacher models like mBERT by upto 35x in terms of parameters and 51x in terms of latency for batch inference while retaining 95% of its F1-score for NER over 41 languages.

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings, such as cross-lingual transfer, where a natural language processing (NLP) model trained on one language is deployed to another language. While the cross-lingual transfer techniques are powerful, they carry gender bias from the source to target languages. In this paper, we study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations from both the intrinsic and extrinsic perspectives. Experimental results show that the magnitude of bias in the multilingual representations changes differently when we align the embeddings to different target spaces and that the alignment direction can also have an influence on the bias in transfer learning. We further provide recommendations for using the multilingual word representations for downstream tasks.

Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks. In this work, we explore a new application, Smart-To-Do, that helps users with task management over emails. We introduce a new task and dataset for automatically generating To-Do items from emails where the sender has promised to perform an action. We design a two-stage process leveraging recent advances in neural text generation and sequence-to-sequence learning, obtaining BLEU and ROUGE scores of 0.23 and 0.63 for this task. To the best of our knowledge, this is the first work to address the problem of composing To-Do items from emails.

Controversial claims are abundant in online media and discussion forums. A better understanding of such claims requires analyzing them from different perspectives. Stance classification is a necessary step for inferring these perspectives in terms of supporting or opposing the claim. In this work, we present a neural network model for stance classification leveraging BERT representations and augmenting them with a novel consistency constraint. Experiments on the Perspectrum dataset, consisting of claims and users’ perspectives from various debate websites, demonstrate the effectiveness of our approach over state-of-the-art baselines.

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level inference relying on embedding for (subject, object) pairs, thus cannot handle pairs absent in any existing triples; or they perform predicate-level mapping and completely ignore background evidence from individual entities, thus cannot achieve satisfying quality. We propose OpenKI to handle sparsity of OpenIE extractions by performing instance-level inference: for each entity, we encode the rich information in its neighborhood in both KB and OpenIE extractions, and leverage this information in relation inference by exploring different methods of aggregation and attention. In order to handle unseen entities, our model is designed without creating entity-specific parameters. Extensive experiments show that this method not only significantly improves state-of-the-art for conventional OpenIE extractions like ReVerb, but also boosts the performance on OpenIE from semi-structured data, where new entity pairs are abundant and data are fairly sparse.

Misinformation such as fake news is one of the big challenges of our society. Research on automated fact-checking has proposed methods based on supervised learning, but these approaches do not consider external evidence apart from labeled training instances. Recent approaches counter this deficit by considering external sources related to a claim. However, these methods require substantial feature modeling and rich lexicons. This paper overcomes these limitations of prior work with an end-to-end model for evidence-aware credibility assessment of arbitrary textual claims, without any human intervention. It presents a neural network model that judiciously aggregates signals from external evidence articles, the language of these articles and the trustworthiness of their sources. It also derives informative features for generating user-comprehensible explanations that makes the neural network predictions transparent to the end-user. Experiments with four datasets and ablation studies show the strength of our method.

In this work, we propose an author-specific sentiment aggregation model for polarity prediction of reviews using an ontology. We propose an approach to construct a Phrase Annotated Author Specific Sentiment Ontology Tree (PASOT), where the facet nodes are annotated with opinion phrases of the author, used to describe the facets, as well as the author’s preference for the facets. We show that an author-specific aggregation of sentiment over an ontology fares better than a flat classification model, which does not take the domain-specific facet importance or author-specific facet preference into account. We compare our approach to supervised classification using Support Vector Machines, as well as other baselines from previous works, where we achieve an accuracy improvement of 7.55% over the SVM baseline. Furthermore, we also show the effectiveness of our approach in capturing thwarting in reviews, achieving an accuracy improvement of 11.53% over the SVM baseline.