Canada

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current approaches focus on the input side, seeking powerful prompts to stimulate models for correct answers. However, we argue that input-side adaptation could be arduous due to the lack of gradient signals and they usually require thousands of API queries, resulting in high computation and time costs. Specifically, DecT first extracts prompt-stimulated output scores for initial predictions. On top of that, we train an additional decoder network on the output representations to incorporate posterior data knowledge. By gradient-based optimization, DecT can be trained within several seconds and requires only one PTM query per sample. Empirically, we conduct extensive natural language understanding experiments and show that DecT significantly outperforms state-of-the-art algorithms with a 200x speed-up. Our code is available at https://github.com/thunlp/DecT.

&lt;iframe src=&quot;https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/3669e294-76d9-423e-8a95-924db4522817&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Decoder Tuning: Efficient Language Understanding as Decoding

llms

prompt

adaptation

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022!  I believe this conference has been complicated beyond any precedent.  Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm.  We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community.  Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well:  we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

<br>*Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA*<br>
***EMNLP 2022 General Chair***
<br><br><br>
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
<br><br>
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)



To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current approaches focus on the input side, seeking powerful prompts to stimulate models for correct answers. However, we argue that input-side adaptation could be arduous due to the lack of gradient signals and they usually require thousands of API queries, resulting in high computation and time costs. Specifically, DecT first extracts prompt-stimulated output scores for initial predictions. On top of that, we train an additional decoder network on the output representations to incorporate posterior data knowledge. By gradient-based optimization, DecT can be trained within several seconds and requires only one PTM query per sample. Empirically, we conduct extensive natural language understanding experiments and show that DecT significantly outperforms state-of-the-art algorithms with a 200x speed-up. Our code is available at https://github.com/thunlp/DecT.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/3669e294-76d9-423e-8a95-924db4522817" 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.

Context information modeling is an important task in conversational KBQA. However, existing methods usually assume the independence of utterances and model them in isolation. In this paper, we propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history while maintaining low computational cost. The framework incorporates a context-aware encoder, which employs a dynamic memory decay mechanism and models context at different levels of granularity. We evaluate HSGE on a widely used benchmark dataset for complex sequential question answering. Experimental results demonstrate that it outperforms existing baselines averaged on all question types.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/01313d0e-ab89-4b42-8950-4c15685e287e" width="300" height="400"></iframe>

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling

In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs. First, we represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. To enable pure-text input during inference, we devise a visual scene hallucination mechanism that dynamically generates pseudo visual SG from the given textual SG. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. On the benchmark Multi30K data, our SG-based method outperforms the best-performing baseline by significant BLEU scores on the task and setup, helping yield translations with better completeness, relevance and fluency without relying on paired images. Further in-depth analyses reveal how our model advances in the task setting.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/a97782d4-6513-4d25-ab09-d00379e30820" width="300" height="400"></iframe>

Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination

Out-of-domain (OOD) intent classification is an active field of natural language understanding, which is of great practical significance for intelligent devices such as the Task-Oriented Dialogue System. It mainly contains two challenges: it requires the model to know what it knows and what it does not know.This paper investigates "overthinking" in the open-world scenario and its impact on OOD intent classification. Inspired by this, we propose a two-birds-one-stone method, which allows the model to decide whether to make a decision on OOD classification early during inference and can ensure accuracy and accelerate inference. At the same time, to adapt to the behavior of dynamic inference, we also propose a training method based on ensemble methods. In addition to bringing certain theoretical insights, we also conduct detailed experiments on three real-world intent datasets. Compared with the previous baselines, our method can not only improve inference speed, but also achieve significant performance improvements.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/0adc1d9a-e6a4-440a-b5bc-29a853412eeb" width="300" height="400"></iframe>

Two Birds One Stone: Dynamic Ensemble for OOD Intent Classification

Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are inherently slow due to one-by-one token generation, so non-autoregressive alternatives are needed. In this work, we propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network that outputs a self-attention weight matrix that can be used in beam search to find the best permutation of input tokens (with auxiliary <ins> tokens) and a decoder network based on a step-unrolled denoising autoencoder that fills in specific tokens. This allows us to find the token permutation after only one forward pass of the permutation network, avoiding autoregressive constructions. We show that the resulting network improves over previously known non-autoregressive methods for GEC and reaches the level of autoregressive methods that do not use language-specific synthetic data generation methods. Our results are supported by a comprehensive experimental validation on the ConLL-2014 and BEA datasets and an extensive ablation study that supports our architectural and algorithmic choices.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/fdfafc87-a5ef-4387-afe7-25a41aabd7be" width="300" height="400"></iframe>

GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding

Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks. However, they are also known to be significantly brittle against specifically crafted adversarial examples, leading to increasing interest in probing the adversarial robustness of NLP systems. We introduce RSMI, a novel two-stage framework that combines randomized smoothing (RS) with masked inference (MI) to improve the adversarial robustness of NLP systems. RS transforms a classifier into a smoothed classifier to obtain robust representations, whereas MI forces a model to exploit the surrounding context of a masked token in an input sequence. RSMI improves adversarial robustness by 2 to 3 times over existing state-of-the-art methods on benchmark datasets. We also perform in-depth qualitative analysis to validate the effectiveness of the different stages of RSMI and probe the impact of its components through extensive ablations. By empirically proving the stability of RSMI, we put it forward as a practical method to robustly train large-scale NLP models. Our code and datasets are available at https://github.com/Han8931/rsmi_nlp

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/cb59b6a0-28d2-4049-bcb9-8834f467ba30" width="300" height="400"></iframe>

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-labeled data and can perform consistently across domains. To solve this problem, we propose a seq2seq model that consists of two modules, namely phraseness and informativeness module, both of which can be built in an unsupervised and open-domain fashion. The phraseness module generates phrases, while the informativeness module guides the generation towards those that represent the core concepts of the text. We thoroughly evaluate our proposed method using eight benchmark datasets from different domains. Results on in-domain datasets show that our approach achieves state-of-the-art results compared with existing unsupervised models, and overall narrows the gap between supervised and unsupervised methods down to about 16%. Furthermore, we demonstrate that our model performs consistently across domains, as it surpasses the baselines on out-of-domain datasets.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/2c9fdc57-2ccc-4bfe-a1f4-d8e6bd6117a7" width="300" height="400"></iframe>

Unsupervised Open-domain Keyphrase Generation

Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task. We execute the generated code on the example test case provided in the question and wrap execution results into a supplementary comment. Utilizing this comment as guidance, our fault-aware code editor is employed to correct errors in the generated code.We perform extensive evaluations across two competitive programming datasets with nine different LLMs. Compared to directly generating from LLMs, our approach can improve the average of pass@1 by 89\% on APPS-dev, 31\% on APPS-test, and 48\% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. Compared to other post-processing methods, our method demonstrates superior accuracy and efficiency.

<iframe src="https://app.sli.do/event/nDU9hzdsVZXUCPdEbR3oSF/embed/polls/0c4bf465-1285-43ea-9885-ec1f8b17681e" width="300" height="400"></iframe>

Self-Edit: Fault-Aware Code Editor for Code Generation

Autoregressive language models (LMs) map token sequences to probabilities. The usual practice for computing the probability of any character string (e.g. English sentences) is to first transform it into a sequence of tokens that is scored by the model. However, there are exponentially many token sequences that represent any given string. To truly compute the probability of a string one should marginalize over all tokenizations, which is typically intractable. Here, we analyze whether the practice of ignoring the marginalization is justified. To this end, we devise an importance-sampling-based algorithm that allows us to compute estimates of the marginal probabilities and compare them to the default procedure in a range of state-of-the-art models and datasets. Our results show that the gap in log-likelihood is no larger than 0.5% in most cases, but that it becomes more pronounced for data with long complex words.

<iframe src="https://app.sli.do/event/nDU9hzdsVZXUCPdEbR3oSF/embed/polls/ceccc225-660e-40d6-ab11-988e6bd5fa69" width="300" height="400"></iframe>

Should you marginalize over possible tokenizations?

Pretrained models are a mainstay in modern NLP applications. Pretraining requires access to large volumes of unlabeled text. While monolingual text is readily available for many of the world's languages, access to large quantities of code-switched text (i.e., text with tokens of multiple languages interspersed within a sentence) is much more scarce. Given this resource constraint, the question of how pretraining using limited amounts of code-switched text could be altered to improve performance for code-switched NLP becomes important to tackle. In this paper, we explore different masked language modeling (MLM) pretraining techniques for code-switched text that are cognizant of language boundaries prior to masking. The language identity of the tokens can either come from human annotators, trained language classifiers, or simple relative frequency-based estimates. We also present an MLM variant by introducing a residual connection from an earlier layer in the pretrained model that uniformly boosts performance on downstream tasks. Experiments on two downstream tasks, Question Answering (QA) and Sentiment Analysis (SA), involving four code-switched language pairs (Hindi-English, Spanish-English, Tamil-English, Malayalam-English) yield relative improvements of up to 5.8 and 2.7 F1 scores on QA (Hindi-English) and SA (Tamil-English), respectively, compared to standard pretraining techniques. To understand our task improvements better, we use a series of probes to study what additional information is encoded by our pretraining techniques and also introduce an auxiliary loss function that explicitly models language identification to further aid the residual MLM variants.

<iframe src="https://app.sli.do/event/nDU9hzdsVZXUCPdEbR3oSF/embed/polls/729157ef-1f91-4a8f-b6eb-8085724c51d3" width="300" height="400"></iframe>

Improving Pretraining Techniques for Code-Switched NLP

Subword tokenization is a key part of most NLP pipelines.However, little is known about why some tokenizer and hyperparameter combinations lead to improved downstream model performance over others. We propose that good tokenizers lead to efficient channel usage, where the channel is the means by which some input is conveyed to the model and efficiency can be quantified in information-theoretic terms as the ratio of the Shannon entropy to the maximum entropy of the subword distribution.Nevertheless, an optimal encoding according to Shannon entropy assigns extremely long codes to low-frequency subwords and very short codes to high-frequency subwords.Defining efficiency in terms of Rnyi entropy, on the other hand, penalizes distributions with either very high or very low-frequency subwords.We posit that (1) extremely high-frequency subwords are problematic because their meaning is not distinct and (2) that low-frequency subwords may not appear frequently enough for their meaning to be learned properly; encodings that induce unigram distributions with either can harm model performance.In machine translation, we find that across multiple tokenizers, the Rnyi entropy has a very strong correlation with BLEU: 0.82 in comparison to just -0.30 for compressed length.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/b7017d00-0285-4079-8722-b9a76c1ea1ad" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling

Similar lecture

BBTv2: Towards a Gradient-Free Future with Large Language Models