United States

Article prediction is a task that has long defied accurate linguistic description. As such, this task is ideally suited to evaluate models on their ability to emulate native-speaker intuition. To this end, we compare the performance of native English speakers and pre-trained models on the task of article prediction set up as a three way choice (a/an, the, zero). Our experiments with BERT show that BERT outperforms humans on this task across all articles. In particular, BERT is far superior to humans at detecting the zero article, possibly because we insert them using rules that the deep neural model can easily pick up. More interestingly, we find that BERT tends to agree more with annotators than with the corpus when inter-annotator agreement is high but switches to agreeing more with the corpus as inter-annotator agreement drops. We contend that this alignment with annotators, despite being trained on the corpus, suggests that BERT is not memorising article use, but captures a high level generalisation of article use akin to human intuition.


NAACL 2022

Abstraction not Memory: BERT and the English Article System

article prediction

bertology

bert

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

poster

The task of natural language inference (NLI), to decide if a hypothesis entails or contradicts a premise, received considerable attention in recent years. All competitive systems build on top of contextualized representations and make use of transformer architectures for learning an NLI model. When somebody is faced with a particular NLI task, they need to select the best model that is available. This is a time-consuming and resource-intense endeavour. To solve this practical problem, we propose a simple method for predicting the performance without actually fine-tuning the model. We do this by testing how well the pre-trained models perform on the aNLI task when just comparing sentence embeddings with cosine similarity to what kind of performance is achieved when training a classifier on top of these embeddings. We show that the accuracy of the cosine similarity approach correlates strongly with the accuracy of the classification approach with a Pearson correlation coefficient of 0.65. Since the similarity is orders of magnitude faster to compute on a given dataset (less than a minute vs.\ hours), our method can lead to significant time savings in the process of model selection.

Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to the training model. Thus, the perturbed samples may not aid in regularization due to their ease of classification from the model. In this context, we propose an augmentation method of adding a discrete noise that would incur the highest divergence between predictions. This virtual adversarial discrete noise obtained by replacing a small portion of tokens while keeping original semantics as much as possible efficiently pushes a training model's decision boundary. Experimental results show that our proposed method outperforms other consistency training baselines with text editing, paraphrasing, or a continuous noise on semi-supervised text classification tasks and a robustness benchmark.

Consistency Training with Virtual Adversarial Discrete Perturbation

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive learning framework that clusters inputs from the same class for better generality of models trained with only limited examples. Specifically, we propose a supervised contrastive framework that clusters inputs from the same class under different augmented "views" and repel the ones from different classes. We create different "views" of an example by appending it with different language prompts and contextual demonstrations. Combining a contrastive loss with the standard masked language modeling (MLM) loss in prompt-based few-shot learners, the experimental results show that our method can improve over the state-of-the-art methods in a diverse set of 15 language tasks. Our framework makes minimal assumptions on the task or the base model, and can be applied to many recent methods with little modification.

Contrastive Learning for Prompt-based Few-shot Language Learners

Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language model can cause severe over-fitting. In this paper, we propose an Embedding Hallucination (EmbedHalluc) method, which generates auxiliary embedding-label pairs to expand the fine-tuning dataset. The hallucinator is trained by playing an adversarial game with the discriminator, such that the hallucinated embedding is indiscriminative to the real ones in the fine-tuning dataset. By training with the extended dataset, the language learner effectively learns from the diverse hallucinated embeddings to overcome the over-fitting issue. Experiments demonstrate that our proposed method is effective in a wide range of language tasks, outperforming current fine-tuning methods. Further, we show that EmbedHalluc outperforms other methods that address this over-fitting problem, such as common data augmentation, semi-supervised pseudo-labeling, and regularization.

Embedding Hallucination for Few-shot Language Fine-tuning

MixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels. However, selecting random pairs is not potentially an optimal choice. In this work, we propose TDMixUp, a novel MixUp strategy that leverages Training Dynamics and allows more informative samples to be combined for generating new data samples. Our proposed TDMixUp first measures confidence, variability, (Swayamdipta et al., 2020), and Area Under the Margin (AUM) (Pleiss et al., 2020) to identify the characteristics of training samples (e.g., as easy-to-learn or ambiguous samples), and then interpolates these characterized samples. We empirically validate that our method not only achieves competitive performance using a smaller subset of the training data compared with strong baselines, but also yields lower expected calibration error on the pre-trained language model, BERT, on both in-domain and out-of-domain settings in a wide range of NLP tasks. We publicly release our code.

A Data Cartography based MixUp for Pre-trained Language Models

Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to newly specified few-shot tasks with potentially unseen intent categories. Prototypical networks have been commonly used in this setting, with the hope that good prototypical representations could be learned to capture the semantic similarity between the query and a few labeled instances. This intuition naturally leaves a question of whether or not a good sentence representation scheme could suffice for the task without further domain-specific adaptation. In this paper, we conduct empirical studies on a number of general-purpose sentence embedding schemes, showing that good sentence embeddings without any fine-tuning on intent detection data could produce a non-trivially strong performance. Inspired by the results from our qualitative analysis, we propose a frustratingly easy modification, which leads to consistent improvements over all sentence encoding schemes, including those from the state-of-the-art prototypical network variants with task-specific fine-tuning.

On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning

We present a generic and trend-aware curriculum learning approach that effectively integrates textual and structural information in text graphs for relation extraction between entities, which we consider as node pairs in graphs. The proposed model extends existing curriculum learning approaches by incorporating sample-level loss trends to better discriminate easier from harder samples and schedule them for training. The model results in a robust estimation of sample difficulty and shows sizable improvement over the state-of-the-art approaches across several datasets.

Generic and Trend-aware Curriculum Learning for Relation Extraction

Many natural language processing tasks involve text spans and thus high-quality span representations are needed to enhance neural approaches to these tasks.  Most existing methods of span representation are based on simple derivations (such as max-pooling) from word representations and do not utilize compositional structures of natural language. In this paper, we aim to improve representations of constituent spans using a novel hypertree neural networks (HTNN) that is structured with constituency parse trees. Each node in the HTNN represents a constituent of the input sentence and each hyperedge represents a composition of smaller child constituents into a larger parent constituent. In each update iteration of the HTNN, the representation of each constituent is computed based on all the hyperedges connected to it, thus incorporating both bottom-up and top-down compositional information. We conduct comprehensive experiments to evaluate HTNNs against other span representation models and the results show the effectiveness of HTNN.

Improving Constituent Representation with Hypertree Neural Networks

Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored, especially for the natural language understanding classification task. Intuitively, the class label itself has the intrinsic ability to perform hard positive/negative mining, which is crucial for CL. Motivated by this, we propose a novel label anchored contrastive learning approach (denoted as LaCon) for language understanding. Specifically, three contrastive objectives are devised, including a multi-head instance-centered contrastive loss (ICL), a label-centered contrastive loss (LCL), and a label embedding regularizer (LER). Our approach does not require any specialized network architecture or any extra data augmentation, thus it can be easily plugged into existing powerful pre-trained language models. Compared to the state-of-the-art baselines, LaCon obtains up to 4.1% improvement on the popular datasets of GLUE and CLUE benchmarks. Besides, LaCon also demonstrates significant advantages under the few-shot and data imbalance settings, which obtains up to 9.4% improvement on the FewGLUE and FewCLUE benchmarking tasks.

Label Anchored Contrastive Learning for Language Understanding

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.

Abstraction not Memory: BERT and the English Article System

Downloads

Next from NAACL 2022

Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference

Similar lecture

Probe-Less Probing of BERT’s Layer-Wise Linguistic Knowledge with Masked Word Prediction