Canada

Reasoning about events and their relations attracts surging research efforts since it is regarded as an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. However, these tasks often suffer from limited data availability due to the labor-intensive nature of their annotations. Consequently, recent studies have explored knowledge transfer approaches within a multi-task learning framework to address this challenge. Although such methods have achieved acceptable results, such brute-force solutions struggle to effectively transfer event-relational knowledge due to the vast array of inter-event relations (e.g. temporal, causal, conditional) and reasoning formulations (e.g. discriminative, abductive, ending prediction). To enhance knowledge transfer and enable zero-shot generalization among various combinations, in this work we propose a novel unified framework, called UNIEVENT. Inspired by prefix-based multitask learning, our approach organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. We then train a unified text-to-text generative model that utilizes coordinate-assigning prefixes for each task. By leveraging our adapted prefixes, our unified model achieves state-of-the-art or competitive performance on both zero-shot and supervised reasoning tasks, as demonstrated in extensive experiments

&lt;iframe src=&quot;https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/3a358fa6-3650-48e2-ab66-3e6b96082fe3&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning

event; reasoning; unified model

Reasoning about events and their relations attracts surging research efforts since it is regarded as an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. However, these tasks often suffer from limited data availability due to the labor-intensive nature of their annotations. Consequently, recent studies have explored knowledge transfer approaches within a multi-task learning framework to address this challenge. Although such methods have achieved acceptable results, such brute-force solutions struggle to effectively transfer event-relational knowledge due to the vast array of inter-event relations (e.g. temporal, causal, conditional) and reasoning formulations (e.g. discriminative, abductive, ending prediction). To enhance knowledge transfer and enable zero-shot generalization among various combinations, in this work we propose a novel unified framework, called UNIEVENT. Inspired by prefix-based multitask learning, our approach organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. We then train a unified text-to-text generative model that utilizes coordinate-assigning prefixes for each task. By leveraging our adapted prefixes, our unified model achieves state-of-the-art or competitive performance on both zero-shot and supervised reasoning tasks, as demonstrated in extensive experiments

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/3a358fa6-3650-48e2-ab66-3e6b96082fe3" width="300" height="400"></iframe>

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

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.

Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language processing (NLP). Recent works have predominantly focused on improving the answering accuracy and have achieved promising progress. However, higher accuracy often requires more memory consumption and inference latency, which might not necessarily be efficient enough for direct deployment in the real world. Thus, a trade-off between accuracy, memory consumption and processing speed is pursued. In this paper, we will survey recent advancements in the efficiency of ODQA models and conclude core techniques for achieving efficiency. Additionally, we will provide a quantitative analysis of memory cost, query speed, accuracy, and overall performance comparison. Our goal is to keep scholars informed of the latest advancements and open challenges in ODQA efficiency research and contribute to the further development of ODQA efficiency.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/90d477a8-fab9-4f04-9194-c0d9e181dc5e" width="300" height="400"></iframe>

A Survey for Efficient Open Domain Question Answering

Pre-trained autoregressive (AR) language models such as BART and GPTs have dominated OPen-ended Long Text Generation (Open-LTG).However, the AR nature will decrease the inference efficiency along with the increase of generation length, which hinder their application in Open-LTG.To improve inference efficiency, we alternatively explore the potential of the pre-trained masked language models (MLMs) along with a representative iterative non-autoregressive (NAR) decoding strategy for Open-LTG.Our preliminary study shows that pre-trained MLMs can merely generate short text and will collapse for long text modeling.To enhance the long text generation capability of MLMs, we introduce two simple yet effective strategies for the iterative NAR model: dynamic sliding window attention (DSWA) and linear temperature decay (LTD). It can alleviate long-distance collapse problems and achieve longer text generation with a flexible trade-off between performance and inference speedup.Experiments on the storytelling and multi-paragraph opinionated article writing tasks show that pre-trained MLMs can achieve more than 3 $\times$ $\to$ 13 $\times$ speedup with better performance than strong AR models.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/edb21409-d100-4926-91ea-b0859d63c6eb" width="300" height="400"></iframe>

Open-ended Long Text Generation via Masked Language Modeling

Transformer-based architectures are the model of choice for natural language understanding, but they come at a significant cost, as they have quadratic complexity in the input length, require a lot of training data, and can be difficult to tune. In the pursuit of lower costs, we investigate simple MLP-based architectures. We find that existing architectures such as MLPMixer, which achieves token mixing through a static MLP applied to each feature independently, are too detached from the inductive biases required for natural language understanding. In this paper, we propose a simple variant, HyperMixer, which forms the token mixing MLP dynamically using hypernetworks. Empirically, we demonstrate that our model performs better than alternative MLP-based models, and on par with Transformers. In contrast to Transformers, HyperMixer achieves these results at substantially lower costs in terms of processing time, training data, and hyperparameter tuning.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/c4101619-7589-4afc-97a4-600e1064c428" width="300" height="400"></iframe>

HyperMixer: An MLP-based Low Cost Alternative to Transformers

Memes are a powerful tool for communication over social media. Their affinity for evolving across politics, history, and sociocultural phenomena renders them an ideal vehicle for communication. To comprehend the subtle message conveyed within a meme, one must understand the relevant background that facilitates its holistic assimilation. Besides digital archiving of memes and their metadata by a few websites like knowyourmeme.com, currently, there is no efficient way to deduce a meme's context dynamically. In this work, we propose a novel task, MEMEX - given a meme and a related document, the aim is to mine the context that succinctly explains the background of the meme. At first, we develop MCC (Meme Context Corpus), a novel dataset for MEMEX. Further, to benchmark MCC, we propose MIME (MultImodal Meme Explainer), a multimodal neural framework that uses external knowledge-enriched meme representation and a multi-level approach to capture the cross-modal semantic dependencies between the meme and the context. MIME surpasses several unimodal and multimodal systems and yields an absolute improvement of ~ 4% F1-score over the best baseline. Lastly, we conduct detailed analyses of MIME's performance, highlighting the aspects that could lead to optimal modeling of cross-modal contextual associations.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/8ec3ae5f-d63c-4a62-9b91-a00ed34b0f80" width="300" height="400"></iframe>

MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization

High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural models for generating rule sets, however, preliminary experiments show that they struggle with maintaining high coverage. In this work, we suggest three simple augmentations to existing rule sets: (1) transforming rules to their abductive forms, (2) generating equivalent rules that use inverse forms of constituent relations and (3) random walks that propose new rules. Finally, we prune potentially low quality rules. Experiments over four datasets and five ruleset-baseline settings suggest that these simple augmentations consistently improve results, and obtain up to 7.1 pt MRR and 8.5 pt Hits@1 gains over using rules without augmentations.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/ca351bc9-1e87-4618-986a-9a9cc00e9540" width="300" height="400"></iframe>

Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

The problems of unfaithful summaries have been widely discussed under the context of abstractive summarization. Though extractive summarization is less prone to the common unfaithfulness issues of abstractive summaries, does that mean extractive is equal to faithful? Turns out that the answer is no. In this work, we define a typology with five types of broad unfaithfulness problems (including and beyond not-entailment) that can appear in extractive summaries, including incorrect coreference, incomplete coreference, incorrect discourse, incomplete discourse, as well as other misleading information. We ask humans to label these problems out of 1600 English summaries produced by 16 diverse extractive systems. We find that 30% of the summaries have at least one of the five issues. To automatically detect these problems, we find that 5 existing faithfulness evaluation metrics for summarization have poor correlations with human judgment. To remedy this, we propose a new metric, ExtEval, that is designed for detecting unfaithful extractive summaries and is shown to have the best performance. We hope our work can increase the awareness of unfaithfulness problems in extractive summarization and help future work to evaluate and resolve these issues.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/8ee0cf45-a161-459f-8212-a033e9d7e6be" width="300" height="400"></iframe>

Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization

We introduce the problem of curriculum discovery and describe a curriculum learning framework capable of discovering effective curricula in a curriculum space based on prior knowledge about sample difficulty. Using annotation entropy and loss as measures of difficulty, we show that (i): the top-performing discovered curricula for a given model and dataset are often non-monotonic as apposed to monotonic curricula in existing literature, (ii): the prevailing easy-to-hard or hard-to-easy transition curricula are often at the risk of underperforming, and (iii): the curricula discovered for smaller datasets and models perform well on larger datasets and models respectively. The proposed framework encompasses some of the existing curriculum learning approaches and can discover curricula that outperform them across several NLP tasks.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/751966b6-0ad8-4b1b-b7e6-c96878d8d141" width="300" height="400"></iframe>

HuCurl: Human-induced Curriculum Discovery

Distant supervision reduces the reliance on human annotation in the named entity recognition tasks. The class-level imbalanced distant annotation is a realistic and unexplored problem, and the popular method of self-training can not handle class-level imbalanced learning. More importantly, self-training is dominated by the high-performance class in selecting candidates, and deteriorates the low-performance class with the bias of generated pseudo label. To address the class-level imbalance performance, we propose a class-rebalancing self-training framework for improving the distantly-supervised named entity recognition. In candidate selection, a class-wise flexible threshold is designed to fully explore other classes besides the high-performance class. In label generation, injecting the distant label, a hybrid pseudo label is adopted to provide straight semantic information for the low-performance class. Experiments on five flat and two nested datasets show that our model achieves state-of-the-art results. We also conduct extensive research to analyze the effectiveness of the flexible threshold and the hybrid pseudo label.

A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition

AI-driven chatbots have become an emerging solution to address psychological distress. Due to the lack of psychotherapeutic data, researchers use dialogues scraped from online peer support forums to train them. But since the responses in such platforms are not given by professionals, they contain both conforming and non-conforming responses. In this work, we attempt to recognize these conforming and non-conforming response types present in online distress-support dialogues using labels adapted from a well-established behavioral coding scheme named Motivational Interviewing Treatment Integrity (MITI) code and show how some response types could be rephrased into a more MI adherent form that can, in turn, enable chatbot responses to be more compliant with the MI strategy. As a proof of concept, we build several rephrasers by fine-tuning Blender and GPT3 to rephrase MI non-adherent Advise without permission responses into Advise with permission. We show how this can be achieved with the construction of pseudo-parallel corpora avoiding costs for human labor. Through automatic and human evaluation we show that in the presence of less training data, techniques such as prompting and data augmentation can be used to produce substantially good rephrasings that reflect the intended style and preserve the content of the original text.

Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy

Language tasks involving character-level manipulations (e.g., spelling corrections, arithmetic operations, word games) are challenging for models operating on subword units. To address this, we develop a causal intervention framework to learn robust and interpretable character representations inside subword-based language models. Our method treats each character as a typed variable in a causal model and learns such causal structures by adapting the interchange intervention training method of Geiger et al. (2021). We additionally introduce a suite of character-level tasks that systematically vary in their dependence on meaning and sequence-level context. While character-level models still perform best on purely form-based tasks like string reversal, our method outperforms character-level models on more complex tasks that blend form, meaning, and context, such as spelling correction in context and word search games. Compared with standard subword-based models, our approach also significantly improves robustness on unseen token sequences and leads to human-interpretable internal representations of characters.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/d1b425d9-11e6-4d18-826a-ec78e9ee6110" width="300" height="400"></iframe>

Premium content

UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning

Downloads

Next from ACL 2023

A Survey for Efficient Open Domain Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES