Ireland

Modern NLP classifiers are known to return uncalibrated estimations of class posteriors. Existing methods for posterior calibration rescale the predicted probabilities but often have an adverse impact on final classification accuracy,
thus leading to poorer generalization. We propose an end-to-end trained calibrator, Platt-Binning, that directly optimizes the objective while minimizing the difference between the predicted and empirical posterior probabilities. Our method leverages the sample efficiency of Platt scaling and the verification guarantees of histogram binning, thus not only reducing the calibration error but also improving task performance. In contrast to existing calibrators, we perform this efficient calibration during training. Empirical evaluation of benchmark NLP classification tasks echoes the efficacy of our proposal.

ACL 2022

Platt-Bin: Efficient Posterior Calibrated Training for NLP Classifiers

platt scaling

histogram binning

posterior calibration

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

poster

# 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). 

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the output to be invariant of the order of the inputs, inconsistency is often observed in the predicted labels or confidence scores. We highlight this model shortcoming and apply a consistency loss function to alleviate inconsistency in symmetric classification. Our results show an improved consistency in predictions for three paraphrase detection datasets without a significant drop in the accuracy scores. We examine the classification performance of six datasets (both symmetric and non-symmetric) to showcase the strengths and limitations of our approach.

Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks

Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted one-pass issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.

Synchronous Refinement for Neural Machine Translation

Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue in domain and scale makes fine-tuning fail to efficiently capture task-specific patterns, especially in low data regime. To address this issue, we propose Task-guided Disentangled Tuning (TDT) for PLMs, which enhances the generalization of representations by disentangling task-relevant signals from the entangled representations. For a given task, we introduce a learnable confidence model to detect indicative guidance from context, and further propose a disentangled regularization to mitigate the over-reliance problem. Experimental results on GLUE and CLUE benchmarks show that TDT gives consistently better results than fine-tuning with different PLMs, and extensive analysis demonstrates the effectiveness and robustness of our method.

Task-guided Disentangled Tuning for Pretrained Language Models

Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors, which are mainly caused by the phonological or visual similarity. Recently, pre-trained language models (PLMs) promote the progress of CSC task. However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task. PLMs focus on the semantics in text and tend to correct the erroneous characters to semantically proper or commonly used ones, but these aren’t the ground-truth corrections. To address this issue, we propose an Error-driven COntrastive Probability Optimization (ECOPO) framework for CSC task. ECOPO reﬁnes the knowledge representations of PLMs, and guides the model to avoid predicting these common characters through an error-driven way. Particularly, ECOPO is model-agnostic and it can be combined with existing CSC methods to achieve better performance. Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective.

The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking

Most of the existing defense methods improve the adversarial robustness by making the models adapt to the training set augmented with some adversarial examples. However, the augmented adversarial examples may not be natural, which might distort the training distribution, resulting in inferior performance both in clean accuracy and adversarial robustness. In this study, we explore the feasibility of introducing a reweighting mechanism to calibrate the training distribution to obtain robust models. We propose to train text classifiers by a sample reweighting method in which the example weights are learned to minimize the loss of a validation set mixed with the clean examples and their adversarial ones in an online learning manner.

Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples

Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results in predicting the overall quality of translated sentences. However, detecting specifically which translated words are incorrect is a more challenging task, especially when dealing with limited amounts of training data. We hypothesize that, not unlike humans, successful QE models rely on translation errors to predict overall sentence quality. By exploring a set of feature attribution methods that assign relevance scores to the inputs to explain model predictions, we study the behaviour of state-of-the-art sentence-level QE models and show that explanations (i.e. rationales) extracted from these models can indeed be used to detect translation errors. We therefore (i) introduce a novel semi-supervised method for word-level QE; and (ii) propose to use the QE task as a new benchmark for evaluating the plausibility of feature attribution, i.e. how interpretable model explanations are to humans.

Translation Error Detection as Rationale Extraction

Existing algorithms consider Word Segmentation as the sequence tagging task and the dominant tagging schemas are “BMES”, ”BIS”, “START-NONSTART”, and “SEP-APP”. For the existing tagging schemas, there are two issues:
1. The implicit information of position restricts the tag-to-tag transition. For the “BMES” tagging schema, tag “B” can not be transferred to tag “B” or “S”.
2. The first tag in the sentence must be “B”, “START” or “SEP”. 
Therefore, we propose the "Connection (C) – NoConnection (NC)" tagging schema to directly describe the connection state of every two adjacent characters. "C-NC" eliminates the implicit restriction of position for the existing tagging schemas.
Our Separation Inference framework is constructed on the "Connection (C) – NoConnection (NC)" tagging schema and its specially tailored bigram features. Our Separation Inference framework is evaluated on five public datasets, is demonstrated to work for machine learning and deep learning models, and outperforms state-of-the-art performance for CWS in all experiments. Performance boosts on Japanese Word Segmentation (JWS) and Korean Word Segmentation (KWS) further prove the framework is universal and effective for East Asian Languages.

Word Segmentation by Separation Inference for East Asian Languages

Interpretation methods to reveal the internal reasoning processes behind machine learning models have attracted increasing attention in recent years. To quantify the extent to which the identified interpretations truly reflect the intrinsic decision-making mechanisms, various faithfulness evaluation metrics have been proposed. However, we find that different faithfulness metrics show conflicting preferences when comparing different interpretations. Motivated by this observation, we aim to conduct a comprehensive and comparative study of the widely adopted faithfulness metrics. In particular, we introduce two assessment dimensions, namely diagnosticity and time complexity. Diagnosticity refers to the degree to which the faithfulness metric favours relatively faithful interpretations over randomly generated ones, and time complexity is measured by the average number of model forward passes. According to the experimental results, we find that sufficiency and comprehensiveness metrics have higher diagnosticity and lower time complexity than the other faithfulness metrics.

A Comparative Study of Faithfulness Metrics for Model Interpretability Methods

Program understanding is a fundamental task in program language processing. Despite the success, existing works fail to take human behaviors as reference in understanding programs. In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components. On the one hand, inspired by the “divide-and-conquer” reading behaviors of humans, we present a partitioning-based graph neural network model PGNN on the upgraded AST of codes. On the other hand, to characterize human behaviors of resorting to other resources to help code comprehension, we transform raw codes with external knowledge and apply pre-training techniques for information extraction. Finally, we combine the two embeddings generated from the two components to output code embeddings. We conduct extensive experiments to show the superior performance of PGNN-EK on the code summarization and code clone detection tasks. In particular, to show the generalization ability of our model, we release a new dataset that is more challenging for code clone detection and could advance the development of the community. Our codes and data are publicly available at https://github.com/RecklessRonan/PGNN-EK.

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors

In dialogue state tracking, dialogue history is a crucial material, and its utilization varies between different models. However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated. Apparently, it requires different dialogue history to update different slots in different turns. Therefore, using consistent dialogue contents may lead to insufficient or redundant information for different slots, which affects the overall performance. To address this problem, we devise DiCoS-DST to dynamically select the relevant dialogue contents corresponding to each slot for state updating. Specifically, it first retrieves turn-level utterances of dialogue history and evaluates their relevance to the slot from a combination of three perspectives: (1) its explicit connection to the slot name; (2) its relevance to the current turn dialogue; (3) Implicit Mention Oriented Reasoning. Then these perspectives are combined to yield a decision, and only the selected dialogue contents are fed into State Generator, which explicitly minimizes the distracting information passed to the downstream state prediction. Experimental results show that our approach achieves new state-of-the-art performance on MultiWOZ 2.1 and MultiWOZ 2.2, and achieves superior performance on multiple mainstream benchmark datasets (including Sim-M, Sim-R, and DSTC2).

Downloads

Next from ACL 2022

Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks

Similar lecture

Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies