Canada

Knowledge transfer can boost neural machine translation (NMT), for example, by finetuning a pretrained masked language model (LM). However, it may suffer from the forgetting problem and the structural inconsistency between pretrained LMs and NMT models. Knowledge distillation (KD) may be a potential solution to alleviate these issues, but few studies have investigated language knowledge transfer from pretrained language models to NMT models through KD. In this paper, we propose Pretrained Bidirectional Distillation (PBD) for NMT, which aims to efficiently transfer bidirectional language knowledge from masked language pretraining to NMT models. Its advantages are reflected in efficiency and effectiveness through a globally defined and bidirectional context-aware distillation objective. Bidirectional language knowledge of the entire sequence is transferred to an NMT model concurrently during translation training. Specifically, we propose self-distilled masked language pretraining to obtain the PBD objective. We also design PBD losses to efficiently distill the language knowledge, in the form of token probabilities, to the encoder and decoder of an NMT model using the PBD objective. Extensive experiments reveal that pretrained bidirectional distillation can significantly improve machine translation performance and achieve competitive or even better results than previous pretrain-finetune or unified multilingual translation methods in supervised, unsupervised, and zero-shot scenarios. Empirically, it is concluded that pretrained bidirectional distillation is an effective and efficient method for transferring language knowledge from pretrained language models to NMT models.

&lt;iframe src=&quot;https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/e1fcb319-69f3-4d4e-8a07-8da3cfad4312&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Pretrained Bidirectional Distillation for Machine Translation

translation

distillation

pretraining

# 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. <br><br>
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. <br><br>

<br><br>
We wish you a wonderful conference! <br><br>
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
<br><br>
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing)<br>
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing)<br>
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)


ACL 2022

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). 

Knowledge transfer can boost neural machine translation (NMT), for example, by finetuning a pretrained masked language model (LM). However, it may suffer from the forgetting problem and the structural inconsistency between pretrained LMs and NMT models. Knowledge distillation (KD) may be a potential solution to alleviate these issues, but few studies have investigated language knowledge transfer from pretrained language models to NMT models through KD. In this paper, we propose Pretrained Bidirectional Distillation (PBD) for NMT, which aims to efficiently transfer bidirectional language knowledge from masked language pretraining to NMT models. Its advantages are reflected in efficiency and effectiveness through a globally defined and bidirectional context-aware distillation objective. Bidirectional language knowledge of the entire sequence is transferred to an NMT model concurrently during translation training. Specifically, we propose self-distilled masked language pretraining to obtain the PBD objective. We also design PBD losses to efficiently distill the language knowledge, in the form of token probabilities, to the encoder and decoder of an NMT model using the PBD objective. Extensive experiments reveal that pretrained bidirectional distillation can significantly improve machine translation performance and achieve competitive or even better results than previous pretrain-finetune or unified multilingual translation methods in supervised, unsupervised, and zero-shot scenarios. Empirically, it is concluded that pretrained bidirectional distillation is an effective and efficient method for transferring language knowledge from pretrained language models to NMT models.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/e1fcb319-69f3-4d4e-8a07-8da3cfad4312" 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.

In open-domain dialogue generation tasks, contexts and responses in most datasets are one-to-one mapped, violating an important many-to-many characteristic: a context leads to various responses, and a response answers multiple contexts. Without such patterns, models poorly generalize and prefer responding safely. Many attempts have been made in either multi-turn settings from a one-to-many perspective or in a many-to-many perspective but limited to single-turn settings. The major challenge to many-to-many augment multi-turn dialogues is that discretely replacing each turn with semantic similarity breaks fragile context coherence. In this paper, we propose DialoGue Path Sampling (DialoGPS) method in continuous semantic space, the first many-to-many augmentation method for multi-turn dialogues. Specifically, we map a dialogue to our extended Brownian Bridge, a special Gaussian process. We sample latent variables to form coherent dialogue paths in the continuous space. A dialogue path corresponds to a new multi-turn dialogue and is used as augmented training data. We show the effect of DialoGPS with both automatic and human evaluation.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/06a86c25-f778-4c49-bec5-d7dd785560cc" width="300" height="400"></iframe>

DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations

Despite recent advances in detecting fake news generated by neural models, their results are not readily applicable to effective detection of human-written disinformation. What limits the successful transfer between them is the sizable gap between machine-generated fake news and human-authored ones, including the notable differences in terms of style and underlying intent. With this in mind, we propose a novel framework for generating training examples that are informed by the known styles and strategies of human-authored propaganda. Specifically, we perform self-critical sequence training guided by natural language inference to ensure the validity of the generated articles, while also incorporating propaganda techniques, such as appeal to authority and loaded language. In particular, we create a new training dataset, PropaNews, with 2,256 examples, which we release for future use. Our experimental results show that fake news detectors trained on PropaNews are better at detecting human-written disinformation by 3.62 - 7.69% F1 score on two public datasets.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/eb25b7c7-8503-428b-aaf1-a50f320b3598" width="300" height="400"></iframe>

Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation

Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for knowledge graphs. Existing unsupervised approaches become suitable candidates for jointly learning the two tasks due to their avoidance of using graph-text parallel data. However, they adopt multiple complex modules and still require entity information or relation type for training. To this end, we propose INFINITY, a simple yet effective unsupervised method with a unified pretrained language model that does not introduce external annotation tools or additional parallel information. It achieves fully unsupervised graph-text mutual conversion for the first time. Specifically, INFINITY treats both G2T and T2G as a bidirectional sequence generation task by fine-tuning only one pretrained seq2seq model. A novel back-translation-based framework is then designed to generate synthetic parallel data automatically. Besides, we investigate the impact of graph linearization and introduce the structure-aware fine-tuning strategy to alleviate possible performance deterioration via retaining structural information in graph sequences. As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks. Additionally, we also devise a new training setting called cross learning for low-resource unsupervised information extraction.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/429438ca-3e25-4b77-9f01-3e3deeb82292" width="300" height="400"></iframe>

Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model

Multimodal Sarcasm Explanation (MuSE) is a new yet challenging task, which aims to generate a natural language sentence for a multimodal social post (an image as well as its caption) to explain why it contains sarcasm. Although the existing pioneer study has achieved great success with the BART backbone, it overlooks the gap between the visual feature space and the decoder semantic space, the object-level metadata of the image, as well as the potential external knowledge. To solve these limitations, in this work, we propose a novel mulTi-source sEmantic grAph-based Multimodal sarcasm explanation scheme, named TEAM. In particular, TEAM extracts the object-level semantic meta-data instead of the traditional global visual features from the input image. Meanwhile, TEAM resorts to ConceptNet to obtain the external related knowledge concepts for the input text and the extracted object meta-data. Thereafter, TEAM introduces a multi-source semantic graph that comprehensively characterize the multi-source (i.e., caption, object meta-data, external knowledge) semantic relations to facilitate the sarcasm reasoning. Extensive experiments on a public released dataset MORE verify the superiority of our model over cutting-edge methods.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/096c5bd4-22e1-47c9-a4ba-1392a6f62e80" width="300" height="400"></iframe>

Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation

Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We focus on Knowledge Distillation (KD) techniques, in which a small student model learns to imitate a large teacher model, allowing to transfer knowledge from the teacher to the student. In contrast to much of the previous work, our goal is to optimize the model for a specific NLG task and a specific dataset. Typically in real-world applications, in addition to labeled data there is abundant unlabeled task-specific data, which is crucial for attaining high compression rates via KD. In this work, we conduct a systematic study of task-specific KD techniques for various NLG tasks under realistic assumptions. We discuss the special characteristics of NLG distillation and particularly the exposure bias problem. Following, we derive a family of Pseudo-Target (PT) augmentation methods, substantially extending prior work on sequence-level KD. We propose the Joint-Teaching method, which applies word-level KD to multiple PTs generated by both the teacher and the student.Finally, we validate our findings in an extreme setup with no labeled examples using GPT-4 as the teacher. Our study provides practical model design observations and demonstrates the effectiveness of PT training for task-specific KD in NLG.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/203697da-2e97-450a-8c2e-ee479cdd810c" width="300" height="400"></iframe>

A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

Event-centric structured prediction involves predicting structured outputs of events. In most NLP cases, event structures are complex with manifold dependency, and it is challenging to effectively represent these complicated structured events. To address these issues, we propose Structured Prediction with Energy-based Event-Centric Hyperspheres (SPEECH). SPEECH models complex dependency among event structured components with energy-based modeling, and represents event classes with simple but effective hyperspheres. Experiments on two unified-annotated event datasets indicate that SPEECH is predominant in event detection and event-relation extraction tasks.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/3a4fea7b-28b7-4384-9675-f513d42b8af0" width="300" height="400"></iframe>

SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres

In everyday life, humans often plan their actions by following step-by-step instructions in the form of goal-oriented scripts. Previous work has exploited language models (LMs) to plan for abstract goals of stereotypical activities (e.g., "make a cake"), but leaves more specific goals with multi-facet constraints understudied (e.g., "make a cake for diabetics"). In this paper, we define the task of constrained language planning for the first time. We propose an over-generate-then-filter approach to improve large language models (LLMs) on this task, and use it to distill a novel constrained language planning dataset, Coscript, which consists of 55,000 scripts. Empirical results demonstrate that our method significantly improves the constrained language planning ability of LLMs, especially on constraint faithfulness. Furthermore, Coscript is demonstrated to be quite effective in endowing smaller LMs with constrained language planning ability.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/61868b9b-9a80-4263-bf22-5a2d45ac15cd" width="300" height="400"></iframe>

Distilling Script Knowledge from Large Language Models for Constrained Language Planning

Despite the extensive applications of relation extraction (RE) tasks in various domains, little has been explored in the historical context, which contains promising data across hundreds and thousands of years. To promote the historical RE research, we present HistRED constructed from Yeonhaengnok. Yeonhaengnok is a collection of records originally written in Hanja, the classical Chinese writing, which has later been translated into Korean. HistRED provides bilingual annotations such that RE can be performed on Korean and Hanja texts. In addition, HistRED supports various self-contained subtexts with different lengths, from a sentence level to a document level, supporting diverse context settings for researchers to evaluate the robustness of their RE models. To demonstrate the usefulness of our dataset, we propose a bilingual RE model that leverages both Korean and Hanja contexts to predict relations between entities. Our model outperforms monolingual baselines on HistRED, showing that employing multiple language contexts supplements the RE predictions. The dataset is publicly available at: https://huggingface.co/datasets/Soyoung/HistRED under CC BY-NC-ND 4.0 license.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/6e1326cf-cb2b-489f-bea8-7f95d12b2968" width="300" height="400"></iframe>

HistRED: A Historical Document-Level Relation Extraction Dataset

Reasoning about actions and change (RAC) is essential to understand and interact with the ever-changing environment. Previous AI research has shown the importance of fundamental and indispensable knowledge of actions, i.e., preconditions and effects. However, traditional methods rely on logical formalization which hinders practical applications. With recent transformer-based language models (LMs), reasoning over text is desirable and seemingly feasible, leading to the question of whether LMs can effectively and efficiently learn to solve RAC problems. We propose four essential RAC tasks as a comprehensive textual benchmark and generate problems in a way that minimizes the influence of other linguistic requirements (e.g., grounding) to focus on RAC. The resulting benchmark, TRAC, encompassing problems of various complexities, facilitates a more granular evaluation of LMs, precisely targeting the structural generalization ability much needed for RAC. Experiments with three high-performing transformers indicate that additional efforts are needed to tackle challenges raised by TRAC.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/880ca3fb-6ec8-4661-8f4e-a8e3f0013929" width="300" height="400"></iframe>

Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change

Named entity recognition (NER) is the task to detect and classify entity spans in the text. When entity spans overlap between each other, the task is named as nested NER. Span-based methods have been widely used to tackle nested NER. Most of these methods get a score matrix, where each entry corresponds to a span. However, previous work ignores spatial relations in the score matrix. In this paper, we propose using Convolutional Neural Network (CNN) to model these spatial relations. Despite being simple, experiments in three commonly used nested NER datasets show that our model surpasses several recently proposed methods with the same pre-trained encoders. Further analysis shows that using CNN can help the model find more nested entities. Besides, we find that different papers use different sentence tokenizations for the three nested NER datasets, which will influence the comparison. Thus, we release a pre-processing script to facilitate future comparison.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/0ba5d22f-b038-416d-9337-2d9c278f3536" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations

Similar lecture

Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation