Thailand

The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standard benchmarks has scaled with size, compression techniques such as knowledge distillation have been key in making them practical. We present MATE-KD, a novel text-based adversarial training algorithm which improves the performance of knowledge distillation. MATE-KD first trains a masked language model-based generator to perturb text by maximizing the divergence between teacher and student logits. Then using knowledge distillation a student is trained on both the original and the perturbed training samples. We evaluate our algorithm, using BERT-based models, on the GLUE benchmark and demonstrate that MATE-KD outperforms competitive adversarial learning and data augmentation baselines. On the GLUE test set our 6 layer RoBERTa based model outperforms BERT-large.

IJCNLP-AACL 2021

MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation

adversarial learning

knowledge distillation

data augmentation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

poster

Whereas much of the success of the current generation of neural language models has been driven by increasingly large training corpora, relatively little research has been dedicated to analyzing these massive sources of textual
data. In this exploratory analysis, we delve deeper into the Common Crawl, a colossal web corpus that is extensively used for training language models. We find that it contains a significant amount of undesirable content, including hate speech and sexually explicit content, even after filtering procedures. We discuss the potential impacts of this content on language models and conclude with future research directions and a more mindful approach to corpus collection and analysis.

What's in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus

Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include biomedical and encyclopedic knowledge and use an existing commonsense KG dataset to explore KG completion in the more realistic setting where dense connectivity is not guaranteed. We develop a deep convolutional network that utilizes textual entity representations and demonstrate that our model outperforms recent KG completion methods in this challenging setting. We find that our model's performance improvements stem primarily from its robustness to sparsity. We then distill the knowledge from the convolutional network into a student network that re-ranks promising candidate entities. This re-ranking stage leads to further improvements in performance and demonstrates the effectiveness of entity re-ranking for KG completion.

Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network

Computing precise evidences, namely minimal sets of sentences that support or refute a given claim, rather than larger evidences is crucial in fact verification (FV), since larger evidences may contain conflicting pieces some of which support the claim while the other refute, thereby misleading FV. Despite being important, precise evidences are rarely studied by existing methods for FV. It is challenging to find precise evidences due to a large search space with lots of local optimums. Inspired by the strong exploration ability of the deep Q-learning network (DQN), we propose a DQN-based approach to retrieval of precise evidences. In addition, to tackle the label bias on Q-values computed by DQN, we design a post-processing strategy which seeks best thresholds for determining the true labels of computed evidences. Experimental results confirm the effectiveness of DQN in computing precise evidences and demonstrate improvements in achieving accurate claim verification.

A DQN-based Approach to Finding Precise Evidences for Fact Verification

Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs. Those out-of-domain inputs can lead to unpredictable outputs and sometimes catastrophic safety issues. 
Prior studies on out-of-domain detection require in-domain task labels and are limited to supervised classification scenarios.
Our work tackles the problem of detecting out-of-domain samples with only unsupervised in-domain data. 
We utilize the latent representations of pre-trained transformers and propose a simple yet effective method to transform features across all layers to construct out-of-domain detectors efficiently. 
Two domain-specific fine-tuning approaches are further proposed to boost detection accuracy.
Our empirical evaluations of related methods on two datasets validate that our method greatly improves out-of-domain detection ability in a more general scenario.

Unsupervised Out-of-Domain Detection via Pre-trained Transformers

Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora.
This method relies on the assumption that the two embedding spaces are structurally similar, which does not necessarily hold true in general.
In this paper, we argue that using a pseudo-parallel corpus generated by an unsupervised machine translation model facilitates the structural similarity of the two embedding spaces and improves the quality of CLWEs in the unsupervised mapping method.
We show that our approach outperforms other alternative approaches given the same amount of data, and, through detailed analysis, we show that data augmentation with the pseudo data from unsupervised machine translation is especially effective for mapping-based CLWEs because (1) the pseudo data makes the source and target corpora (partially) parallel; (2) the pseudo data contains information on the original language that helps to learn similar embedding spaces between the source and target languages.

Data augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings

Television shows play an important role in propagating societal norms. Owing to the
popularity of the situational comedy (sitcom) genre, it contributes significantly to the overall development of society. In an effort to analyze the content of television shows belonging to this genre, we present a dataset of dialogue turns from popular sitcoms annotated for the presence of sexist remarks. We train a text classification model to detect sexism using domain adaptive learning. We apply
the model to our dataset to analyze the evolution of sexist content over the years. We propose a domain-specific semi-supervised architecture for the aforementioned detection of sexism. Through extensive experiments, we show that our model often yields better classification performance over generic deep learning-based sentence classification that does not employ domain-specific training. We find that
while sexism decreases overtime on average, the proportion of sexist dialogue for the most sexist sitcom actually increases. A quantitative analysis along with a detailed error analysis presents the case for our proposed methodology.

"Hold on honey, men at work": A semisupervised approach to detecting sexism in sitcoms

In this paper we present our observations and
evaluations by observing the linguistic performance
of the system on several steps on the
training process of various English-to-German
Neural Machine Translation models. The
linguistic performance is measured through
a semi-automatic process using a test suite.
Among several linguistic observations, we find
that the translation quality of some linguistic
categories decreased within the recorded iterations.
Additionally, we notice some drops
of the translation quality of certain categories
when using a larger corpus.

Observing the Learning Curve of Neural Machine Translation with regard to Linguistic Phenomena

Question answering (QA) models for reading comprehension have achieved human-level accuracy on in-distribution test sets.
However, they have been demonstrated to lack robustness to challenge sets, whose distribution is different from that of training sets.
Existing data augmentation methods mitigate this problem by simply augmenting training sets with synthetic examples sampled from the same distribution as the challenge sets.
However, these methods assume that the distribution of a challenge set is known a priori, making them less applicable to unseen challenge sets.
In this study, we focus on question-answer pair generation (QAG) to mitigate this problem.
While most existing QAG methods aim to improve the quality of synthetic examples,
we conjecture that diversity-promoting QAG can mitigate the sparsity of training sets and lead to better robustness.
We present a variational QAG model that generates multiple diverse QA pairs from a paragraph.
Our experiments show that our method can improve the accuracy of 12 challenge sets, as well as the in-distribution accuracy.

Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation

The quality of the annotated data directly influences in the success of supervised NLP models. However, creating annotated datasets is often time-consuming and expensive. Although the annotation tool takes an important role, we know little about how it influences annotation quality. We compare the quality of annotations for the task of chat-untangling made by non- experts annotators using two different tools. The first is SLATE, an existing command-line based tool, and the second is Parlay, a new tool we developed that integrates mouse interaction and visual links. Our experimental results indicate that, while both tools perform similarly in terms of annotation quality, Parlay offers a significantly better user experience.

Tools Impact on the Quality of Annotations for Chat Untangling

In this study, we investigate the role of the multiple layers in deep transformer models. We design a variant of ALBERT that dynamically adapts the number of layers for each token of the input. The key specificity of ALBERT is that weights are tied across layers. Therefore, the stack of encoder layers iteratively repeats the application of the same transformation function on the input. We interpret the repetition of this application as an iterative process where the token contextualized representations are progressively refined. We analyze this process at the token level during pre-training, fine-tuning, and inference. We show that tokens do not require the same amount of iterations and that difficult or crucial tokens for the task are subject to more iterations.

MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation

Downloads

Next from IJCNLP-AACL 2021

What's in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus

Similar lecture

Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax