Ireland

Coreference resolution – which is a crucial task for understanding discourse and language at large – has yet to witness widespread benefits from large language models (LLMs). Moreover, coreference resolution systems largely rely on supervised labels, which are highly ex- pensive and difficult to annotate, thus making it ripe for prompt engineering. In this paper, we introduce a QA-based prompt-engineering method and discern generative, pre-trained LLMs’ abilities and limitations toward the task of coreference resolution. Our experiments show that GPT-2 and GPT-Neo can return valid answers, but that their capabilities to identify coreferent mentions are limited and prompt-sensitive, leading to inconsistent results.

ACL 2022

What GPT Knows About Who is Who

prompt engineering

coreference

discourse

coreference resolution

# 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). 

workshop paper

Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone. Meanwhile, static word representations (e.g., Word2Vec or GloVe) have been shown to benefit from isotropic spaces. Therefore, previous work has developed methods to calibrate the embedding space of transformers in order to ensure isotropy. However, a recent study (Cai et al. 2021) shows that the embedding space of transformers is locally isotropic, which suggests that these models are already capable of exploiting the expressive capacity of their embedding space. In this work, we conduct an empirical evaluation of state-of-the-art methods for isotropy calibration on transformers and find that they do not provide consistent improvements across models and tasks. These results support the thesis that, given the local isotropy, transformers do not benefit from additional isotropy calibration.

On Isotropy Calibration of Transformer Models

We evaluated 12 existing data augmentation methods for natural language processing in a unified experimental setting. In addition, we evaluated the strength of data augmentation in terms of how large a perturbation it causes to a sentence, and we examined the correlation between this value and changes in performance. The results showed that when there were several thousand data points, data augmentation rarely improved performance, and the strength of data augmentation also did not correlate clearly with changes in performance.

On the Impact of Data Augmentation on Downstream Performance in Natural Language Processing

Question rewriting (QR) is a subtask of conversational question answering (CQA) aiming to ease the challenges of understanding dependencies among dialogue history by reformulating questions in a self-contained form. Despite seeming plausible, little evidence is available to justify QR as a mitigation method for CQA. To verify the effectiveness of QR in CQA, we investigate a reinforcement learning approach that integrates QR and CQA tasks and does not require corresponding QR datasets for targeted CQA. We find, however, that the RL method is on par with the end-to-end baseline. We provide an analysis of the failure and describe the difficulty of exploiting QR for CQA.

Can Question Rewriting Help Conversational Question Answering?

In this paper we present a set of multilingual experiments tackling the task of Stance Detection in five different languages: English, Spanish, Catalan, French and Italian. Furthermore, we study the phenomenon of stance with respect to six different targets – one per language, and two different for Italian – employing a variety of machine learning algorithms that primarily exploit morphological and syntactic knowledge as features, represented throughout the format of Universal Dependencies. Results seem to suggest that the methodology employed is not beneficial per se, but might be useful to exploit the same features with a different methodology and/or classification technique.

Do Dependency Relations Help in the Task of Stance Detection?

We investigate potential label errors present in the popular BANKING77 dataset and the associated negative impacts on intent classification methods. Motivated by our own negative results when constructing an intent classifier, we applied two automated approaches to identify potential label errors in the dataset. We found that over 1,400 (14%) of the 10,003 training utterances may have been incorrectly labelled. In a simple experiment, we found that by removing the utterances with potential errors, our intent classifier saw an increase of 4.5% and 8% for the F1-Score and Adjusted Rand Index, respectively, in supervised and unsupervised classification. This paper serves as a warning of the potential of noisy labels in popular NLP datasets. Further study is needed to fully identify the breadth and depth of label errors in BANKING77 and other datasets.

Label Errors in BANKING77

In this work, we examine the problems associated with neural dialog models under the common theme of compositionality. Specifically, we investigate three manifestations of compositionality: (1) Productivity, (2) Substitutivity, and (3) Systematicity. These manifestations shed light on the generalization, syntactic robustness, and semantic capabilities of neural dialog models. We design probing experiments by perturbing the training data to study the above phenomenon. We make informative observations based on automated metrics and hope that this work increases research interest in understanding the capacity of these models.

An Empirical study to understand the Compositional Prowess of Neural Dialog Models

Replication of research results has become more and more important in Natural Language Processing. Nevertheless, we still rely on results reported in the literature for comparison. Additionally, elements of an experimental setup are not always completely reported. This includes, but is not limited to reporting specific parameters used or omitting an implementational detail. In our experiments based on two frequently used data sets from the domain of automatic summarization and the seemingly full disclosure of research artifacts, we examine how well results reported are replicable and what elements influence the success or failure of replication. Our results indicate that publishing research artifacts is far from sufficient, and that publishing all relevant parameters in all possible detail is crucial, but often neglected, making the situation in automatic summarization only near-perfect.

Replicability under Near-Perfect Conditions – A Case-Study from Automatic Summarization

Open-world classification in dialog systems require models to detect open intents, while ensuring the quality of in-domain (ID) intent classification. In this work, we revisit methods that leverage distance-based statistics for unsupervised out-of-domain (OOD) detection. We show that despite their superior performance on threshold-independent metrics like AUROC on test-set, threshold values chosen based on the performance on a validation-set do not generalize well to the test-set, thus resulting in substantially lower performance on ID or OOD detection accuracy and F1-scores. Our analysis shows that this lack of generalizability can be successfully mitigated by setting aside a hold-out set from validation data for threshold selection (sometimes achieving relative gains as high as 100%). Extensive experiments on seven benchmark datasets show that this fix puts the performance of these methods at par with, or sometimes even better than, the current state-of-the-art OOD detection techniques.

Evaluating the Practical Utility of Confidence-score based Techniques for Unsupervised Open-world Classification

BPE tokenization merges characters into longer tokens by finding frequently occurring contiguous patterns within the word boundary. An intuitive relaxation would be to extend a BPE vocabulary with multi-word expressions (MWEs): bigrams (in_a), trigrams (out_of_the), and skip-grams (he·his). In the context of Neural Machine Translation (NMT), we replace the least frequent subword/whole-word tokens with the most frequent MWEs. We find that these modifications to BPE end up hurting the model, resulting in a net drop of BLEU and chrF scores across two language pairs. We observe that naively extending BPE beyond word boundaries results in incoherent tokens which are themselves better represented as individual words. Moreover, we find that Pointwise Mutual Information (PMI) instead of frequency finds better MWEs (e.g., New_Y work, Statue_of_Liberty, neither·nor) which consistently improves translation performance.

BPE beyond Word Boundary: How NOT to use Multi Word Expressions in Neural Machine Translation

Evaluating generated text received new attention with the introduction of model-based metrics in recent years. These new metrics have a higher correlation with human judgments and seemingly overcome many issues of previous n-gram based metrics from the symbolic age. In this work, we examine the recently introduced metrics BERTScore, BLEURT, NUBIA, MoverScore, and Mark-Evaluate (Petersen). We investigate their sensitivity to different types of semantic deterioration (part of speech drop and negation), word order perturbations, word drop, and the common problem of repetition. No metric showed appropriate behaviour for negation, and further none of them was overall sensitive to the other issues mentioned above.

What GPT Knows About Who is Who

Downloads

Next from ACL 2022

On Isotropy Calibration of Transformer Models

Similar lecture

Kronecker Decomposition for GPT Compression

What GPT Knows About Who is Who

.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 2022

On Isotropy Calibration of Transformer Models

Similar lecture

Kronecker Decomposition for GPT Compression

Downloads