Thailand

We study a family of data augmentation methods, substructure substitution (SUB2), that generalizes prior methods. SUB2 generates new examples by substituting substructures (e.g., subtrees or subsequences) with others having the same label. This idea can be applied to many structured NLP tasks such as part-of-speech tagging and parsing. For more general tasks (e.g., text classification) which do not have explicitly annotated substructures, we present variations of SUB2 based on text spans or parse trees, introducing structure-aware data augmentation methods to general NLP tasks. For most cases, training with a dataset augmented by SUB2 achieves better performance than training with the original training set. Further experiments show that SUB2 has more consistent performance than other investigated augmentation methods, across different tasks and sizes of the seed dataset.

ACL-IJCNLP 2021

Substructure Substitution: Structured Data Augmentation for NLP

part-of-speech tagging

dependency parsing

text classification

structured prediction

constituency parsing

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).

technical paper

Despite their impressive performance in NLP, self-attention networks were recently proved to be limited for processing formal languages with hierarchical structure, such as Dyck-k, the language consisting of well-nested parentheses of k types. This suggested that natural language can be approximated well with models that are too weak for formal languages, or that the role of hierarchy and recursion in natural language might be limited. We qualify this implication by proving that self-attention networks can process Dyck-(k, D), the subset of Dyck-k with depth bounded by D, which arguably better captures the bounded hierarchical structure of natural language. Specifically, we construct a hard-attention network with D+1 layers and O(log k) memory size (per token per layer) that recognizes Dyck-(k, D), and a soft-attention network with two layers and O(log k) memory size that generates Dyck-(k, D). Experiments show that self-attention networks trained on Dyck-(k, D) generalize to longer inputs with near-perfect accuracy, and also verify the theoretical memory advantage of self-attention networks over recurrent networks.

Self-Attention Networks Can Process Bounded Hierarchical Languages

We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjacent sentences, and uses labeled data only at inference time. We adapt T5 (Raffel et al., 2020), a strong pretrained text-to-text model, to extract a style vector from text and use it to condition the decoder to perform style transfer. As our label-free training results in a style vector space encoding many facets of style, we recast transfers as ``targeted restyling'' vector operations that adjust specific attributes of the input while preserving others. We demonstrate that training on unlabeled Amazon reviews data results in a model that is competitive on sentiment transfer, even compared to models trained fully on labeled data. Furthermore, applying our novel method to a diverse corpus of unlabeled web text results in a single model capable of transferring along multiple dimensions of style (dialect, emotiveness, formality, politeness, sentiment) despite no additional training and using only a handful of exemplars at inference time.

TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling

As describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical analysis community, and has linear run time and memory complexity. We perform extensive experiments to show that the inductive bias embodied by our hierarchical attention is effective in capturing the hierarchical structure in the sequences typical for natural language and vision tasks. Our method is superior to alternative sub-quadratic proposals by over +6 points on average on the Long Range Arena benchmark.
It also sets a new SOTA test perplexity on One-Billion Word dataset with 5x fewer model parameters than that of the previous-best Transformer-based models.

H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF—better few-shot fine-tuning of language models—a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning.

Making Pre-trained Language Models Better Few-shot Learners

Event language models represent plausible sequences of events. Most existing approaches train autoregressive models on text, which successfully capture event co-occurrence but unfortunately constrain the model to follow the discourse order in which events are presented. Other domains may employ different discourse orders, and for many applications, we may care about different notions of ordering (e.g., temporal) or not care about ordering at all (e.g., when predicting related events in a schema). We propose a simple yet surprisingly effective strategy for improving event language models by perturbing event sequences so we can relax model dependence on text order. Despite generating completely synthetic event orderings, we show that this technique improves the performance of the event language models on both applications and out-of-domain events data.

Don't Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

Multiple studies have shown that Transformers are remarkably robust to pruning. Contrary to this received wisdom, we demonstrate that pre-trained Transformer encoders are surprisingly fragile to the removal of a very small number of features in the layer outputs (<0.0001% of model weights). In case of BERT and other pre-trained encoder Transformers, the affected component is the scaling factors and biases in the LayerNorm. The outliers are high-magnitude normalization parameters that emerge early in pre-training and show up consistently in the same dimensional position throughout the model. We show that disabling them significantly degrades both the MLM loss and the downstream task performance. This effect is observed across several BERT-family models and other popular pre-trained Transformer architectures, including BART, XLNet and ELECTRA; we also show a similar effect in GPT-2.

BERT Busters: Outlier Dimensions that Disrupt Transformers

In an election campaign, political parties pledge to implement various projects--should they be elected. But do they follow through? 
To track election pledges from parties' election manifestos, 
we need to distinguish between pledges and general statements.
In this paper, we use election manifestos of Swedish and Indian political parties to learn neural models that distinguish actual pledges from generic political positions. 
Since pledges might vary by election year and party, we implement a Multi-Task Learning (MTL) setup, predicting election year and manifesto's party as auxiliary tasks.
Pledges can also span several sentences, so we use hierarchical models that incorporate contextual information.
Lastly, we evaluate the models in a Zero-Shot Learning (ZSL) framework across countries and languages.
Our results indicate that year and party have predictive power even in ZSL, while context introduces some noise. 
We finally discuss the linguistic features of pledges.

"We will Reduce Taxes" - Identifying Election Pledges with Language Models

Methodologies for training visual question answering (VQA) models assume the availability of datasets with human-annotated \textit{Image-Question-Answer} (I-Q-A) triplets.
This has led to heavy reliance on datasets and a lack of generalization to new types of questions and scenes. Linguistic priors along with biases and errors due to annotator subjectivity have been shown to percolate into VQA models trained on such samples.
We study whether models can be trained without any human-annotated Q-A pairs, but only with images and their associated textual descriptions or captions.
We present a method to train models with synthetic Q-A pairs generated procedurally from captions.
Additionally, we demonstrate the efficacy of spatial-pyramid image patches as a simple but effective alternative to dense and costly object bounding box annotations used in existing VQA models.
Our experiments on three VQA benchmarks demonstrate the efficacy of this weakly-supervised approach, especially on the VQA-CP challenge, which tests performance under changing linguistic priors.

WeaQA: Weak Supervision via Captions for Visual Question Answering

Using multiple treebanks to improve parsing performance has shown positive results. However, to what extent similar, yet competing annotation decisions play in parser behavior is unclear. We investigate this within a multi-task learning (MTL) dependency parser setup on two parallel treebanks, UD and SUD, which, while possessing similar annotation schemes, differ in specific linguistic annotation preferences. We perform a set of experiments with different MTL architectural choices, comparing performance across various input embeddings. We find languages tend to pattern in lose typological associations, but generally the performance within an MTL setting is lower than single model baseline parsers for each annotation scheme. The main contributing factor seems to be the competing syntactic annotation information shared between treebanks in an MTL setting, which is shown in experiments against differently annotated treebanks.This suggests that the impact of how the signal is encoded for annotations and its influence on possible negative transfer is more important than that of the input embeddings in an MTL setting.

Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD

The purpose of an argumentative text is to support a certain conclusion. Yet, they are often omitted, expecting readers to infer them rather. While appropriate when reading an individual text, this rhetorical device limits accessibility when browsing many texts (e.g., on a search engine or on social media). In these scenarios, an explicit conclusion makes for a good candidate summary of an argumentative text. This is especially true if the conclusion is informative, emphasizing specific concepts from the text. With this paper we introduce the task of generating informative conclusions: First, Webis-ConcluGen-21 is compiled, a large-scale corpus of 136,996 samples of argumentative texts and their conclusions. Second, two paradigms for conclusion generation are investigated; one extractive, the other abstractive in nature. The latter exploits argumentative knowledge that augment the data via control codes and finetuning the BART model on several subsets of the corpus. Third, insights are provided into the suitability of our corpus for the task, the differences between the two generation paradigms, the trade-off between informativeness and conciseness, and the impact of encoding argumentative knowledge. The corpus, code, and the trained models are publicly available.

Downloads

Next from ACL-IJCNLP 2021

Self-Attention Networks Can Process Bounded Hierarchical Languages

Similar lecture

Automated Concatenation of Embeddings for Structured Prediction

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

Self-Attention Networks Can Process Bounded Hierarchical Languages

Similar lecture

Automated Concatenation of Embeddings for Structured Prediction

Downloads