Canada

While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. The basic idea is to sequentially transfer knowledge from each trained model to the distilled model. Extensive experiments on Chinese-English and German-English datasets show that our method achieves significant and consistent improvements over strong baselines under both homogeneous and heterogeneous trained model settings and is robust to malicious models.

&lt;iframe src=&quot;https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e32628b4-33d4-492c-bfb2-8aed949c9c25&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Continual Knowledge Distillation for Neural Machine Translation

continual learning

knowledge distillation

machine translation

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. The basic idea is to sequentially transfer knowledge from each trained model to the distilled model. Extensive experiments on Chinese-English and German-English datasets show that our method achieves significant and consistent improvements over strong baselines under both homogeneous and heterogeneous trained model settings and is robust to malicious models.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e32628b4-33d4-492c-bfb2-8aed949c9c25" 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.

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a prompting strategy that formulates a number of different NLU tasks as contextual entailment. This approach improves the zero-shot adaptation of pretrained entailment models. Secondly, we notice that self-training entailment-based models with unlabeled data can significantly improve the adaptation performance on downstream tasks. To achieve more stable improvement, we propose the Simple Pseudo-Label Editing (SimPLE) algorithm for better pseudo-labeling quality in self-training. We also found that both pretrained entailment-based models and the self-trained models are robust against adversarial evaluation data. Experiments on binary and multi-class classification tasks show that SimPLE leads to more robust self-training results, indicating that the self-trained entailment models are more efficient and trustworthy than large language models on language understanding tasks.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/9546392e-e41d-4bab-b8ed-0283ce2aed71" width="300" height="400"></iframe>

Entailment as Robust Self-Learner

Pre-trained large language models (PLMs) underly most new developments in natural language processing. They have shifted the field from application-specific model pipelines to a single model that is adapted to a wide range of tasks. Autoregressive PLMs like GPT-3 or PaLM and associated techniques like fewshot learning, have additionally shifted the output modality to generation instead of classification or regression. Despite their ubiquitous use, the generation quality of language models is rarely evaluated when these models are introduced. Additionally, it is unclear how existing generation taskswhile they can be used to compare systems at a high levelrelate to the real world use cases for which people have been adopting them. In this work, we discuss how to adapt existing application-specific generation benchmarks to PLMs and provide an in-depth, empirical study of the limitations and capabilities of PLMs in natural language generation tasks along dimensions such as scale, architecture, input and output language. Our results show that PLMs differ in their applicability to different data regimes and their generalization to multiple languages. They further inform practitioners as to which PLMs to use for a given generation task setup. We share best practices to be taken into consideration when benchmarking generation capabilities during the development of upcoming PLMs.

Benchmarking Large Language Model Capabilities for Conditional Generation

The ability to understand a user's underlying needs is critical for conversational systems, especially with limited input from users in a conversation. Thus, in such a domain, Asking Clarification Questions (ACQs) to reveal users' true intent from their queries or utterances arise as an essential task. However, it is noticeable that a key limitation of the existing ACQs studies is their incomparability, from inconsistent use of data, distinct experimental setups and evaluation strategies. Therefore, in this paper, to assist the development of ACQs techniques, we comprehensively analyse the current ACQs research status, which offers a detailed comparison of publicly available datasets, and discusses the applied evaluation metrics, joined with benchmarks for multiple ACQs-related tasks. In particular, given a thorough analysis of the ACQs task, we discuss a number of corresponding research directions for the investigation of ACQs as well as the development of conversational systems.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/5644a02c-3df8-4bc6-8e30-c46c5dac8660" width="300" height="400"></iframe>

A Survey on Asking Clarification Questions Datasets in Conversational Systems

Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models. This raises the question of why Transformers perform well in practice and whether they have any properties that enable them to generalize better than recurrent models. In this work, we conduct an extensive empirical study on Boolean functions to demonstrate the following: (i) Random Transformers are relatively more biased towards functions of low sensitivity. (ii) When trained on Boolean functions, both Transformers and LSTMs prioritize learning functions of low sensitivity, with Transformers ultimately converging to functions of lower sensitivity. (iii) On sparse Boolean functions which have low sensitivity, we find that Transformers generalize near perfectly even in the presence of noisy labels whereas LSTMs overfit and achieve poor generalization accuracy. Overall, our results provide strong quantifiable evidence that suggests differences in the inductive biases of Transformers and recurrent models which may help explain Transformer's effective generalization performance despite relatively limited expressiveness.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/bf3d0931-95a3-40b1-873a-961c906b051c" width="300" height="400"></iframe>

Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions

Hierarchical topic models, which can extract semantically meaningful topics from a textcorpus in an unsupervised manner and automatically organise them into a topic hierarchy, have been widely used to discover the underlying semantic structure of documents. However, the existing models often assume in the prior that the topic hierarchy is a tree structure, ignoring symmetrical dependenciesbetween topics at the same level. Moreover, the sparsity of text data often complicate the analysis. To address these issues, we propose NSEM-GMHTM as a deep topic model, witha Gaussian mixture prior distribution to improve the model's ability to adapt to sparse data, which explicitly models hierarchical and symmetric relations between topics through the dependency matrices and nonlinear structural equations. Experiments on widely used datasets show that our NSEM-GMHTM generates more coherent topics and a more rational topic structure when compared to state-of-theart baselines. Our code is available at https: //github.com/nbnbhwyy/NSEM-GMHTM.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/12ab3698-e3e3-498a-b768-6a32af31bf27" width="300" height="400"></iframe>

Nonlinear Structural Equation Model Guided Gaussian Mixture Hierarchical Topic Modeling

This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5. We study various designs to pretrain T5 using an auxiliary model to construct more challenging token replacements for the main model to denoise. Key aspects under study include the decoding target, the location of the RTD head, and the masking pattern. Based on these studies, we develop a new model, METRO-T0, which is pretrained using the redesigned ELECTRA-Style pretraining strategies and then prompt-finetuned on a mixture of NLP tasks. METRO-T0 outperforms all similar-sized baselines on prompted NLP benchmarks, such as _T0 Eval_ and MMLU, and rivals the state-of-the-art T0-11B model with only **8%** of its parameters. Our analysis on model's neural activation and parameter sensitivity reveals that the effectiveness of METRO-T0 stems from more balanced contribution of parameters and better utilization of their capacity. The code and model checkpoints are available at [https://github.com/gonglinyuan/metro_t0](https://github.com/gonglinyuan/metro_t0).

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/5a902eb8-85f8-4ff7-aae4-4a782b544387" width="300" height="400"></iframe>

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers

Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to be explored for vision and multimodal tasks. In this work, we introduce MultiInstruct, the first multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories. The tasks are derived from 21 existing open-source datasets and each task is equipped with 5 expert-written instructions. We take OFA as the base pre-trained model for multimodal instruction tuning, and to further improve its zero-shot performance, we explore multiple transfer learning strategies to leverage the large-scale Natural Instructions dataset. Experimental results demonstrate strong zero-shot performance on various unseen multimodal tasks and the benefit of transfer learning from a text-only instruction dataset. We also design a new evaluation metric -- Sensitivity, to evaluate how sensitive the model is to the variety of instructions. Our results indicate that fine-tuning the model on a diverse set of tasks and instructions leads to a reduced sensitivity to variations in instructions for each task.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/1aacea1c-0953-4c67-acf6-cc4e297c0369" width="300" height="400"></iframe>

MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning

In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts entity mention spans irrespective of entity type; (2) Span Classification which classifies the spans into their entity types. Further, we formulate both sub-tasks as question-answering (QA) problems and produce two leaner models which can be optimized separately for each sub-task. Experiments with four cross-domain datasets demonstrate that this two-step approach is both effective and time efficient. Our system, SplitNER outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG. In all cases, it achieves a significant reduction in training time compared to its QA baseline counterpart. The effectiveness of our system stems from fine-tuning the BERT model twice, separately for span detection and classification. The source code can be found at https://github.com/c3sr/split-ner.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/74761fbf-7921-48dd-a198-198cb955924c" width="300" height="400"></iframe>

Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications

Large pre-trained language models are acknowledged to carry social bias towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an important task, models of which are mainly adopted by administrative industries, where unfair decisions may lead to catastrophic consequences. However, existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQL. This, to some extent, cover up social bias in models under ideal conditions, which nevertheless may emerge in real application scenarios. In this work, we aim to uncover and mitigate social bias in Text-to-SQL models. We summarize the categories of social bias that may occur in structural data for Text-to-SQL models. We build test benchmarks and reveal that models with similar task accuracy can contain social bias at very different rates. We show how to take advantage of our methodology to assess and mitigate social bias in the downstream Text-to-SQL task.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/ccb310a5-36cd-4b03-8194-996e46032655" width="300" height="400"></iframe>

Uncovering and Categorizing Social Biases in Text-to-SQL

While pretraining on large-scale imagetext data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability to recognise relationships, verbs, and numbers in images. This has resulted in an increased interest in the community to either develop new benchmarks or models for such capabilities. To better understand and quantify progress in this direction, we investigate four competitive V&L models on four fine-grained benchmarks. Through our analysis, we find that X-VLM (Zeng et al., 2022) consistently outperforms other baselines, and that modelling innovations can impact performance more than scaling Web data, which even degrades performance sometimes. Through a deeper investigation of X-VLM, we highlight the importance of both novel losses and rich data sources for learning fine-grained skills. Finally, we inspect training dynamics, and discover that for some tasks, performance peaks early in training or significantly fluctuates, never converging.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/4e28ce5e-459e-4bc5-afb4-43284e9ee5cc" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Entailment as Robust Self-Learner

Similar lecture

Building a Multi-domain Neural Machine Translation Model using Knowledge Distillation