Ireland

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious correlations between inputs and outputs that do not represent a generally held causal relationship between features and classes; models that exploit such correlations may appear to perform a given task well, but fail on out of sample data. In this paper, we evaluate use of different attribution methods for aiding identification of training data artifacts. We propose new hybrid approaches that combine saliency maps (which highlight important input features) with instance attribution methods (which retrieve training samples influential to a given prediction). We show that this proposed training-feature attribution can be used to efficiently uncover artifacts in training data when a challenging validation set is available. We also carry out a small user study to evaluate whether these methods are useful to NLP researchers in practice, with promising results. We make code for all methods and experiments in this paper available.

ACL 2022

Combining Feature and Instance Attribution to Detect Artifacts

attribution method

influence functions

artifact

language model

bert

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

poster

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
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, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 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 will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

Data-hungry deep neural networks have established themselves as the defacto standard for many NLP tasks including the traditional sequence tagging ones. Despite their state-of-the-art performance on high-resource languages, they still fall behind of their statistical counter-parts in low-resource scenarios. One methodology to counter attack this problem is text augmentation, i.e., generating new synthetic training data points from existing data. Although NLP has recently
witnessed a load of textual augmentation techniques, the field still lacks a systematic performance analysis on a diverse set of languages and sequence tagging tasks. To fill this gap, we investigate three categories of text augmentation methodologies which perform changes on the syntax (e.g., cropping sub-sentences), token (e.g., random word insertion) and character (e.g., character swapping) levels. We systematically compare the methods on part-of-speech tagging, dependency parsing and semantic role labeling for a diverse set of language families using various models
including the architectures that rely on pretrained multilingual contextualized language models such as mBERT. Augmentation most significantly improves dependency parsing, followed by part-of-speech tagging and semantic role labeling. We find the experimented techniques to be effective on morphologically rich languages in general rather than analytic languages such as Vietnamese. Our results suggest that the augmentation techniques can further improve over strong baselines based on mBERT, especially for dependency parsing. We identify the character-level methods as the most consistent performers, while synonym replacement and syntactic augmenters provide inconsistent improvements. Finally, we discuss that the results most heavily depend on the task, language pair (e.g., syntactic-level techniques mostly benefit higher-level tasks and morphologically richer languages), and the model type (e.g., token-level augmentation provide significant improvements for BPE, while character-level ones give generally higher scores for char and mBERT based models).

To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP

Few-Shot Relation Extraction aims at predicting the relation for a pair of entities in a sentence by training with a few labelled examples in each relation. Some recent works have introduced relation information (i.e., relation labels or descriptions) to assist model learning based on Prototype Network. However, most of them constrain the prototypes of each relation class implicitly with relation information, generally through designing complex network structures, like generating hybrid features, combining with contrastive learning or attention networks. We argue that relation information can be introduced more explicitly and effectively into the model. Thus, this paper proposes a direct addition approach to introduce relation information. Specifically, for each relation class, the relation representation is first generated by concatenating two views of relations (i.e., [CLS] token embedding and the mean value of embeddings of all tokens) and then directly added to the original prototype for both train and prediction. Experimental results on the benchmark dataset FewRel 1.0 show significant improvements and achieve comparable results to the state-of-the-art, which demonstrates the effectiveness of our proposed approach. Besides, further analyses verify that the direct addition is a much more effective way to integrate the relation representations and the original prototypes.

A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction

Several studies have explored various advantages of multilingual pre-trained models (such as multilingual BERT) in capturing shared linguistic knowledge. However, less attention has been paid to their limitations. In this paper, we investigate the multilingual BERT for two known issues of the monolingual models: anisotropic embedding space and outlier dimensions. We show that, unlike its monolingual counterpart, the multilingual BERT model exhibits no outlier dimension in its representations while it has a highly anisotropic space. There are a few dimensions in the monolingual BERT with high contributions to the anisotropic distribution. However, we observe no such dimensions in the multilingual BERT. Furthermore, our experimental results demonstrate that increasing the isotropy of multilingual space can significantly improve its representation power and performance, similarly to what had been observed for monolingual CWRs on semantic similarity tasks. Our
analysis indicates that, despite having different degenerated directions, the embedding spaces in various languages tend to be partially similar with respect to their structures.

An Isotropy Analysis in the Multilingual BERT Embedding Space

The biaffine parser of Dozat and Manning (2017) was successfully extended to semantic dependency parsing (SDP) (Dozat and Man- ning, 2018). Its performance on graphs is surprisingly high given that, without the constraint of producing a tree, all arcs for a given sentence are predicted independently from each other (modulo a shared representation of to- kens). To circumvent such an independence of decision, while retaining the O(n2) complexity and highly parallelizable architecture, we propose to use simple auxiliary tasks that introduce some form of interdependence between arcs. Experiments on the three English acyclic datasets of SemEval 2015 task 18 (Oepen et al., 2015), and on French deep syntactic cyclic graphs (Ribeyre et al., 2014) show modest but systematic performance gains on a near state-of- the-art baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.

Auxiliary tasks to boost Biaffine Semantic Dependency Parsing

While multilingual training is now an essential ingredient in machine translation (MT) systems, recent work has demonstrated that it has different effects in different multilingual settings, such as many-to-one, one-to-many, and many-to-many learning. These training settings expose the encoder and the decoder in a machine translation model with different data distributions. In this paper, we examine how different varieties of multilingual training contribute to learning these two components of the MT model. Specifically, we compare bilingual models with encoders and/or decoders initialized by multilingual training. We show that multilingual training is beneficial to encoders in general, while it only benefits decoders for low-resource languages (LRLs). We further find the important attention heads for each language pair and compare their correlations during inference. Our analysis sheds light on how multilingual translation models work and enables us to propose methods to improve performance by training with highly related languages. Our many-to-one models for high-resource languages and one-to-many models for LRL outperform the best results reported by Aharoni et al. (2019)

Breaking Down Multilingual Machine Translation

In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks. But, in the unsupervised POS tagging task, works utilizing PLMs are few and fail to achieve state-of-the-art (SOTA) performance. The recent SOTA performance is yielded by a Guassian HMM variant proposed by He et al. (2018). However, as a generative model, HMM makes very strong independence assumptions, making it very challenging to incorporate contexualized word representations from PLMs. In this work, we for the first time propose a neural conditional random field autoencoder (CRF-AE) model for unsupervised POS tagging. The discriminative encoder of CRF-AE can straightforwardly incorporate ELMo word representations. Moreover, inspired by feature-rich HMM, we reintroduce hand-crafted features into the decoder of CRF-AE. Finally, experiments clearly show that our model outperforms previous state-of-the-art models by a large margin on Penn Treebank and multilingual Universal Dependencies treebank v2.0.

Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity. Several recent efforts have been made to acknowledge and embrace the existence of ambiguity, and explore how to capture the human disagreement distribution. In contrast with directly learning from gold ambiguity labels, relying on special re source, we argue that the model has naturally captured the human ambiguity distribution as long as it’s calibrated, i.e. the predictive probability can reflect the true correctness likelihood. Our experiments show that when model is well-calibrated, either by label smoothing or temperature scaling, it can obtain competitive performance as prior work, on both divergence scores between predictive probability and the true human opinion distribution, and the accuracy. This reveals the overhead of collecting gold ambiguity labels can be cut, by broadly solving how to calibrate the NLI network.

Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference

Neural constituency parsers have reached practical performance on news-domain benchmarks. However, their generalization ability to other domains remains weak. Existing findings on cross-domain constituency parsing are only made on a limited number of domains. Tracking this, we manually annotate a high-quality constituency treebank containing five domains. We analyze challenges to open-domain constituency parsing using a set of linguistic features on various strong constituency parsers. Primarily, we find that 1) BERT significantly increases parsers’ cross-domain performance by reducing their sensitivity on the domain-variant features. 2) Compared with single metrics such as unigram distribution and OOV rate, challenges to open-domain constituency parsing arise from combinations of factors, including cross-domain lexical and constituent structure variations.

Challenges to Open-Domain Constituency Parsing

Natural Language Understanding (NLU) models can be trained on sensitive information such as phone numbers, zip-codes etc. Recent literature has focused on Model Inversion Attacks (ModIvA) that can extract training data from model parameters. In this work, we present a version of such an attack by extracting canaries inserted in NLU training data. In the attack, an adversary with open-box access to the model reconstructs the canaries contained in the model's training set. We evaluate our approach by performing text completion on canaries and demonstrate that by using the prefix (non-sensitive) tokens of the canary, we can generate the full canary. As an example, our attack is able to reconstruct a four digit code in the training dataset of the NLU model with a probability of 0.5 in its best configuration. As countermeasures, we identify several defense mechanisms that, when combined, effectively eliminate the risk of ModIvA in our experiments.

Canary Extraction in Natural Language Understanding Models

Humor is a common experience that has great societal value. However, humor generation is a challenging problem for the language technologies community as it involves a significant understanding of context. To address this, previous works on humor generation have employed linguistic expertise to produce jokes with a set structure. However this approach is not scalable, since there is a wide range of possible joke structures across various types of jokes (e.g. question-answer formats, one-liners, etc.). In addition, studies on topic-controlled joke generation has been limited, which can hinder the usability of such models in real life. Topic control is important since jokes are often used in a specific context or setting, and choosing the right topic for the setting is crucial for a good use of a joke. This work introduces EDDIE, a keyword-based humor generation model that allows the user to have a fine-grained topic control on the jokes produced. Our system primarily focuses on producing Question and Answer (Q&A) style jokes with occasional one-liners. We have developed a humor generation pipeline that incorporates humor classifier, humor generator, and toxicity filter in order to produce responsible and humorous content. We evaluate EDDIE in a quantitative and qualitative manner. For the former evaluation, we assess the ability of various language models to learn and utilize mechanisms of humor given no linguistic knowledge. For the latter, we have designed three evaluation criteria : funniness, understandability, and complexity. The study has been conducted with both expert comedians and general volunteers from the general public in order to gain insights into machine humor generation and its application in real life.

Downloads

Next from ACL 2022

To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP

Similar lecture

Do Feature Attribution Methods Correctly Attribute Features?