Thailand

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific pretraining is often not robust. In particular, the performance considerably varies as the random seed changes or the number of pretraining and/or fine-tuning iterations varies, and the fine-tuned model is vulnerable to adversarial attack. We propose a simple yet effective adapter-based approach to mitigate these issues. Specifically, we insert small bottleneck layers (i.e., adapter) within each layer of a pretrained model, then fix the pretrained layers and train the adapter layers on the downstream task data, with (1) task-specific unsupervised pretraining and then (2) task-specific supervised training (e.g., classification, sequence labeling). Our experiments demonstrate that such a training scheme leads to improved stability and adversarial robustness in transfer learning to various downstream tasks.

ACL-IJCNLP 2021

Robust Transfer Learning with Pretrained Language Models through Adapters

stability

robustness

transfer learning

**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

Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interactive Transformer (Hi-Transformer) for efficient and effective long document modeling. Hi-Transformer models documents in a hierarchical way, i.e., first learns sentence representations and then learns document representations. It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence. More specifically, we first use a sentence Transformer to learn the representations of each sentence. Then we use a document Transformer to model the global document context from these sentence representations. Next, we use another sentence Transformer to enhance sentence modeling using the global document context. Finally, we use hierarchical pooling method to obtain document embedding. Extensive experiments on three benchmark datasets validate the efficiency and effectiveness of Hi-Transformer in long document modeling.

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

Logical table-to-text generation aims to automatically generate fluent and logically faithful text from tables. The task remains challenging where deep learning models often generated linguistically fluent but logically inconsistent text. The underlying reason may be that deep learning models often capture surface-level spurious correlations rather than the causal relationships between the table $\boldsymbol{x}$ and the sentence $\boldsymbol{y}$. Specifically, in the training stage, a model can get a low empirical loss without understanding $\boldsymbol{x}$ and use spurious statistical cues instead. In this paper, we propose a de-confounded variational encoder-decoder (DCVED) based on causal intervention, learning the objective $p(\boldsymbol{y}|\text{do}(\boldsymbol{x}))$. Firstly, we propose to use variational inference to estimate the confounders in the latent space and cooperate with the causal intervention based on Pearl's do-calculus to alleviate the spurious correlations. Secondly, to make the latent confounder meaningful, we propose a back-prediction process to predict the not-used entities but linguistically similar to the exactly selected ones. Finally, since our variational model can generate multiple candidates, we train a table-text selector to find out the best candidate sentence for the given table. An extensive set of experiments show that our model outperforms the baselines and achieves new state-of-the-art performance on two logical table-to-text datasets in terms of logical fidelity.

De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation

Recent researches have shown that large natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack. Backdoor attacked models can achieve good performance on clean test sets but perform badly on those input sentences injected with designed trigger words. In this work, we point out a potential problem of current backdoor attacking research: its evaluation ignores the stealthiness of backdoor attacks, and most of existing backdoor attacking methods are not stealthy either to system deployers or to system users. To address this issue, we first propose two additional stealthiness-based metrics to make the backdoor attacking evaluation more credible. We further propose a novel word-based backdoor attacking method based on negative data augmentation and modifying word embeddings, making an important step towards achieving stealthy backdoor attacking. Experiments on sentiment analysis and toxic detection tasks show that our method is much stealthier while maintaining pretty good attacking performance. Our code is available at https://github.com/lancopku/SOS.

Rethinking Stealthiness of Backdoor Attack against NLP Models

Crowdsourcing is regarded as one prospective solution for effective supervised learning, aiming to build large-scale annotated training data by crowd workers. Previous studies focus on reducing the influences from the noises of the crowdsourced annotations for supervised models. We take a different point in this work, regarding all crowdsourced annotations as gold-standard with respect to the individual annotators. In this way, we find that crowdsourcing could be highly similar to domain adaptation, and then the recent advances of cross-domain methods can be almost directly applied to crowdsourcing. Here we take named entity recognition (NER) as a study case, suggesting an annotator-aware representation learning model that inspired by the domain adaptation methods which attempt to capture effective domain-aware features. We investigate both unsupervised and supervised crowdsourcing learning, assuming that no or only small-scale expert annotations are available. Experimental results on a benchmark crowdsourced NER dataset show that our method is highly effective, leading to a new state-of-the-art performance. In addition, under the supervised setting, we can achieve impressive performance gains with only a very small scale of expert annotations.

Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition

We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) additional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of treebanks from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multi-word token expansion, based on our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.

TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning

We describe the DCU-EPFL submission to the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative towards representing semantic structure. Evaluation is carried out on 29 treebanks in 17 languages and participants are required to parse the data from each language starting from raw strings. Our approach uses the Stanza pipeline to preprocess the text files, XLM-RoBERTa to obtain contextualized token representations, and an edge-scoring and labeling model to predict the enhanced graph. Finally, we run a postprocessing script to ensure all of our outputs are valid Enhanced UD graphs. Our system places 6th out of 9 participants with a coarse Enhanced Labeled Attachment Score (ELAS) of 83.57.
We carry out additional post-deadline experiments which include using Trankit for pre-processing, XLM-RoBERTa-large, treebank concatenation, and multi-task learning. All of these modifications improve our initial score and our final system has an ELAS of 88.04.

The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task

Strong and affordable in-domain data is a desirable
asset when transferring trained semantic
parsers to novel domains. As previous
methods for semi-automatically constructing
such data cannot handle the complexity of realistic
SQL queries, we propose to construct
SQL queries via context-dependent sampling,
and introduce the concept of topic. Along with
our SQL query construction method, we propose
a novel pipeline of semi-automatic Textto-
SQL dataset construction that covers the
broad space of SQL queries. We show that
the created dataset is comparable with expert
annotation along multiple dimensions, and is
capable of improving domain transfer performance
for SOTA semantic parsers.

Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer

We review two features of mixture of experts (MoE) models which we call averaging and clustering effects in the context of graph-based dependency parsers learned in a supervised probabilistic framework.

Averaging corresponds to the ensemble combination of parsers and is responsible for variance reduction which helps stabilizing and improving parsing accuracy.
Clustering describes the capacity of MoE models to give more credit to experts believed to be more accurate given an input. Although promising, this is difficult to achieve, especially without additional data.

We design an experimental set-up to study the impact of these effects. Whereas averaging is always beneficial, clustering requires good initialization and stabilization techniques, but its advantages over mere averaging seem to eventually vanish when enough experts are present.

As a by product, we show how this leads to state-of-the-art results on the PTB and the CoNLL09 Chinese treebank, with low variance across experiments.

Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing

Task-oriented household text games that target daily household activities to accomplish in natural languages are challenging for intelligent agents to play. Currently, there are no immediate rewards defined during game playing, and only finishing the task successfully can get a reward. Existing methods using reinforcement learning can only obtain results marginally above 0. In this position paper, we investigate whether an agent can meta-learn from multiple training tasks to improve the performance of a test task. On the publically available household text game platform ALFWorld (Shridhar et al., 2021), we conducted a set of experiments. Our preliminary results show that with meta-learning, using a large number of tasks blindly cannot help improve the performance of a new task significantly.

Meta-learning for Task-oriented Household Text Games

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel training data, as it is frequently the case there are multiple data sources of unequal size, with a mixture of labeled and unlabeled sentences. Moreover, the inherent style defined within each source might be distinct. A generic bidirectional (e.g., formal $\Leftrightarrow$ informal) style transfer regardless of different groups may not generalize well to different applications. In this work, we developed a task adaptive meta-learning framework that can simultaneously perform a multi-pair text-style transfer using a single model. The proposed method can adaptively balance the difference of meta-knowledge across multiple tasks. Results show that our method leads to better quantitative performance as well as coherent style variations. Common challenges of unbalanced data and mismatched domains are handled well by this method.

Robust Transfer Learning with Pretrained Language Models through Adapters

Downloads

Next from ACL-IJCNLP 2021

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

Similar lecture

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications