Thailand

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cross-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.

ACL-IJCNLP 2021

Preserving Cross-Linguality of Pre-trained Models via Continual Learning

multilingual pre-trained model

cross-lingual ability

part-of-speech tagging

named entity recognition

fine-tuning

**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).

workshop paper

Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others. The existent dominant approaches in the context of text data {either rely} on training an adversary (discriminator) that aims at making attribute values difficult to be inferred from the latent code {or rely on minimising variational bounds of the mutual information between latent code and the value attribute}. {However, the available methods suffer of the impossibility to provide
a fine-grained control of the degree (or force) of disentanglement.} {In contrast to} {adversarial methods}, which are remarkably simple, although the adversary seems to be performing perfectly well during the training phase, after it is completed a fair amount of information about the undesired attribute still remains. This paper introduces a novel variational upper bound to the mutual information between an attribute and the latent code of an encoder. Our bound aims at controlling the approximation error via the Renyi’s divergence, leading to both better disentangled representations and in particular, a precise control of the desirable degree of disentanglement {than state-of-the-art methods proposed for textual data}. Furthermore, it does not suffer from the degeneracy of other losses in multi-class scenarios. We show the superiority of this method on fair classification and on textual style transfer tasks. Additionally, we provide new insights illustrating various trade-offs in style transfer when attempting to learn disentangled representations and quality of the generated sentence.

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations

Beam search is a go-to strategy for decoding neural sequence models. The algorithm can naturally be viewed as a subset optimization problem, albeit one where the corresponding set function does not reflect interactions between candidates. Empirically, this leads to sets often exhibiting high overlap, e.g., strings may differ by only a single word. Yet in use-cases that call for multiple solutions, a diverse or representative set is often desired. To address this issue, we propose a reformulation of beam search, which we call determinantal beam search. Determinantal beam search has a natural relationship to determinantal point processes (DPPs), models over sets that inherently encode intra-set interactions. By posing iterations in beam search as a series of subdeterminant maximization problems, we can turn the algorithm into a diverse subset selection process. In a case study, we use the string subsequence kernel to explicitly encourage n-gram coverage in text generated from a sequence model. We observe that our algorithm offers competitive performance against other diverse set generation strategies in the context of language generation, while providing a more general approach to optimizing for diversity.

Determinantal Beam Search

Typing every character in a text message may require more time or effort than strictly necessary. Skipping spaces or other characters may be able to speed input and reduce a user's physical input effort. This can be particularly important for people with motor impairments. In a large crowdsourced study, we found workers frequently abbreviated text by omitting mid-word vowels. We designed a recognizer optimized for expanding noisy abbreviated input where users often omit spaces and mid-word vowels. We show using neural language models for selecting conversational-style training text and for rescoring the recognizer's n-best sentences improved accuracy. On noisy touchscreen data collected from hundreds of users, we found accurate abbreviated input was possible even if a third of characters was omitted. Finally, in a study where users had to dwell for a second on each key, sentence abbreviated input was competitive with a conventional keyboard with word predictions. After practice, users wrote abbreviated sentences at 9.6 words-per-minute versus word input at 9.9 words-per-minute.

Accelerating Text Communication via Abbreviated Sentence Input

Behavior of deep neural networks can be inconsistent between different versions.
Regressions during model update are a common cause of concern that often over-weigh the benefits in accuracy or efficiency gain. 
This work focuses on quantifying, reducing and analyzing regression errors in the NLP model updates.
Using negative flip rate as regression measure, we show that regression has a prevalent presence across tasks in the GLUE benchmark.
We formulate the regression-free model updates into a constrained optimization problem, and further reduce it into a relaxed form which can 
be approximately optimized through knowledge distillation training method. We empirically analyze how model ensemble reduces regression.
Finally, we conduct CheckList behavioral testing to understand the distribution of regressions across linguistic phenomena, and the efficacy of 
ensemble and distillation methods.

Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates

Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which learns a small student model from a large teacher PLM. However, the knowledge learned from a single teacher may be limited and even biased, resulting in low-quality student model. In this paper, we propose a multi-teacher knowledge distillation framework named MT-BERT for pre-trained language model compression, which can train high-quality student model from multiple teacher PLMs. In MT-BERT we design a multi-teacher co-finetuning method to jointly finetune multiple teacher PLMs in downstream tasks with shared pooling and prediction layers to align their output space for better collaborative teaching. In addition, we propose a multi-teacher hidden loss and a multi-teacher distillation loss to transfer the useful knowledge in both hidden states and soft labels from multiple teacher PLMs to the student model. Experiments on three benchmark datasets validate the effectiveness of MT-BERT in compressing PLMs.

One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers

Text generation from semantic parses is to generate textual descriptions for the formal representation inputs such as logic forms and SQL queries. This is challenging for two reasons: (1) the complex and intensive inner logic with data scarcity constraint, (2) the lack of automatic logic consistency evaluation metrics. To address these two challenges, this paper first proposes SNOWBALL, a framework for text generation from semantic parses that employs an iterative training procedure by recursively augmenting the training set with quality control. Second, we propose a novel automatic metric, BLEC, for evaluating the logical consistency between the semantic parses and generated texts. The experimental results on two benchmark datasets, Logic2Text and Spider, demonstrate the SNOWBALL framework enhances the logic consistency on both BLEC and human evaluation. Furthermore, our statistical analysis reveals that BLEC is more logically consistent with human evaluation than general-purpose automatic metrics including BLEU, ROUGE and BLEURT.

Logic-Consistency Text Generation from Semantic Parses

Recent work has demonstrated the effectiveness of cross-lingual language model pretraining for cross-lingual understanding. In this study, we present the results of two larger multilingual masked language models, with 3.5B and 10.7B parameters. Our two new models dubbed XLMR-XL and XLMR-XXL outperform XLM-R by 1.8% and 2.4% average accuracy on XNLI. Our model also outperforms the RoBERTa-Large model on several English tasks of the GLUE benchmark by 0.3% on average while handling 99 more languages. This suggests larger capacity models for language understanding may obtain strong performance on both high- and low-resource languages. We make our code and models publicly available.

Larger-Scale Transformers for Multilingual Masked Language Modeling


Learning effective language representations from crowdsourced labels is crucial for many real-world machine learning tasks. A challenging aspect of this problem is that the quality of crowdsourced labels suffer high intra- and inter-observer variability. Since the high-capacity deep neural networks can easily memorize all disagreements among crowdsourced labels, directly applying existing supervised language representation learning algorithms may yield suboptimal solutions. In this paper, we propose \emph{TACMA}, a \underline{t}emporal-\underline{a}ware language representation learning heuristic for \underline{c}rowdsourced labels with \underline{m}ultiple \underline{a}nnotators. The proposed approach (1) explicitly models the intra-observer variability with attention mechanism; (2) computes and aggregates per-sample confidence scores from multiple workers to address the inter-observer disagreements. The proposed heuristic is extremely easy to implement in around 5 lines of code. The proposed heuristic is evaluated on four synthetic and four real-world data sets. The results show that our approach outperforms a wide range of state-of-the-art baselines in terms of prediction accuracy and AUC. To encourage the reproducible results, we make our code publicly available at \url{https://github.com/CrowdsourcingMining/TACMA}.


Temporal-aware Language Representation Learning From Crowdsourced Labels

Recently, impressive performance on various natural language understanding tasks has been achieved by explicitly incorporating syntax and semantic information into pre-trained models, such as BERT and RoBERTa. However, this approach depends on problem-specific fine-tuning, and as widely noted, BERT-like models exhibit weak performance, and are inefficient, when applied to unsupervised similarity comparison tasks. Sentence-BERT (SBERT) has been proposed as a general-purpose sentence embedding method, suited to both similarity comparison and downstream tasks. In this work, we show that by incorporating structural information into SBERT, the resulting model outperforms SBERT and previous general sentence encoders on unsupervised semantic textual similarity (STS) datasets and transfer classification tasks.

Structure-aware Sentence Encoder in BERT-Based Siamese Network

Cross-lingual text classification (CLTC) is a challenging task made even harder still due to the lack of labelled data in low-resource languages. In this paper, we propose zero-shot instance-weighting, a general model-agnostic zero-shot learning framework for improving CLTC by leveraging source instance weighting. It adds a module on top of pre-trained language models for similarity computation of instance weights, thus aligning each source instance to the target language. During training, the framework utilizes gradient descent that is weighted by instance weights to update parameters. We evaluate this framework over seven target languages on three fundamental tasks and show its effectiveness and extensibility, by improving on F1 score up to 4% in single-source transfer and 8% in multi-source transfer. To the best of our knowledge, our method is the first to apply instance weighting in zero-shot CLTC. It is simple yet effective and easily extensible into multi-source transfer.

Next from ACL-IJCNLP 2021

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations

Similar lecture

Consistency Regularization for Cross-Lingual Fine-Tuning