Singapore

Detecting out-of-distribution (OOD) instances is crucial for NLP models in practical applications. Although numerous OOD detection methods exist, most of them are empirical. Backed by theoretical analysis, this paper advocates for the measurement of the &quot;OOD-ness&quot; of a test case $\boldsymbol{x}$ through the \emph{likelihood ratio} between out-distribution $\mathcal P_{\textit{out}}$ and in-distribution $\mathcal P_{\textit{in}}$. We argue that the state-of-the-art (SOTA) feature-based OOD detection methods, such as Maha and KNN, are suboptimal since they only estimate in-distribution density $p_{\textit{in}}(\boldsymbol{x})$. To address this issue, we propose \textbf{FLATS}, a principled solution for OOD detection based on likelihood ratio. Moreover, we demonstrate that FLATS can serve as a general framework capable of enhancing other OOD detection methods by incorporating out-distribution density $p_{\textit{out}}(\boldsymbol{x})$ estimation. Experiments show that FLATS establishes a new SOTA on popular benchmarks.

EMNLP 2023

FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score

hypothesis test

likelihood ratio

ood detection

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
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. 
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)**

ACL 2023

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.

Detecting out-of-distribution (OOD) instances is crucial for NLP models in practical applications. Although numerous OOD detection methods exist, most of them are empirical. Backed by theoretical analysis, this paper advocates for the measurement of the "OOD-ness" of a test case $\boldsymbol{x}$ through the \emph{likelihood ratio} between out-distribution $\mathcal P_{\textit{out}}$ and in-distribution $\mathcal P_{\textit{in}}$. We argue that the state-of-the-art (SOTA) feature-based OOD detection methods, such as Maha and KNN, are suboptimal since they only estimate in-distribution density $p_{\textit{in}}(\boldsymbol{x})$. To address this issue, we propose \textbf{FLATS}, a principled solution for OOD detection based on likelihood ratio. Moreover, we demonstrate that FLATS can serve as a general framework capable of enhancing other OOD detection methods by incorporating out-distribution density $p_{\textit{out}}(\boldsymbol{x})$ estimation. Experiments show that FLATS establishes a new SOTA on popular benchmarks.

poster

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

Recently, methods have been developed to improve the performance of dense passage retrieval by using context-supervised pre-training. These methods simply consider two passages from the same document to be relevant, without taking into account the potential negative impacts of weakly correlated pairs. Thus, this paper proposes query-as-context pre-training, a simple yet effective pre-training technique to alleviate the issue. Query-as-context pre-training assumes that the query derived from a passage is more likely to be relevant to that passage and forms a passage-query pair. These passage-query pairs are then used in contrastive or generative context-supervised pre-training. The pre-trained models are evaluated on large-scale passage retrieval benchmarks and out-of-domain zero-shot benchmarks. Experimental results show that query-as-context pre-training brings considerable gains for retrieval performances, demonstrating its effectiveness and efficiency.

Query-as-context Pre-training for Dense Passage Retrieval

Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern datasets, standard data filtering is not straight-forward to apply, because of the multifacetedness of the harmful data and elusiveness of filtering rules that would generalize across multiple tasks. We study the fitness of task-agnostic self-influence scores of training examples for data cleaning, analyze their efficacy in capturing naturally occurring outliers, and investigate to what extent self-influence based data cleaning can improve downstream performance in machine translation, question answering and text classification, building up on recent approaches to self-influence calculation and automated curriculum learning.

Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets

Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a ***noise audit*** at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of ***vicarious offense***. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through https://github.com/Homan-Lab/voiced.

Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive | VIDEO

Legal case retrieval is a critical process for modern legal information systems. While recent studies have utilized pre-trained language models (PLMs) based on the general domain self-supervised pre-training paradigm to build models for legal case retrieval, there are limitations in using general domain PLMs as backbones. Specifically, these models may not fully capture the underlying legal features in legal case documents. To address this issue, we propose CaseEncoder, a legal document encoder that leverages fine-grained legal knowledge in both the data sampling and pre-training phases. In the data sampling phase, we enhance the quality of the training data by utilizing fine-grained law article information to guide the selection of positive and negative examples. In the pre-training phase, we design legal-specific pre-training tasks that align with the judging criteria of relevant legal cases. Based on these tasks, we introduce an innovative loss function called Biased Circle Loss to enhance the model's ability to recognize case relevance in fine grains. Experimental results on multiple benchmarks demonstrate that CaseEncoder significantly outperforms both existing general pre-training models and legal-specific pre-training models in zero-shot legal case retrieval. The source code of CaseEncoder can be found at https://github.com/Anonymous-EMNLP2023/CaseEncoder.

CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding | VIDEO

Recent studies show that prompt tuning can better leverage the power of large language models than fine-tuning on downstream natural language understanding tasks. However, the existing prompt tuning methods have training instability issues, as the variance of scores under different random seeds is quite large. To address this critical problem, we first investigate and find that the loss landscape of vanilla prompt tuning is precipitous when it is visualized, where a slight change of input data can cause a big fluctuation in the loss landscape. This is an essential factor that leads to the instability of prompt tuning. Based on this observation, we introduce perturbation-based regularizers, which can smooth the loss landscape, into prompt tuning. We propose a new algorithm, called Prompt Tuning with Perturbation-based regularizer~(PTP), which can not only alleviate training instability dramatically but also boost the performance of prompt tuning. We design two kinds of perturbation-based regularizers, including random-noise-based and adversarial-based. In particular, our proposed perturbations are flexible on both text space and embedding space. Extensive experiments show the effectiveness of our proposed methods in stabilizing the training. Our new algorithms improve the state-of-the-art prompt tuning methods by 1.94\% and 2.34\% on SuperGLUE and FewGLUE benchmarks, respectively.

PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer

Metaphor detection is an important and challenging task in natural language processing, which aims to distinguish between metaphorical and literal expressions in text. Previous studies mainly leverage the incongruity of source and target domains and contextual clues for detection, neglecting similar attributes shared between source and target concepts in metaphorical expressions. Based on conceptual metaphor theory, these similar attributes are essential to infer implicit meanings conveyed by the metaphor. Under the guidance of conceptual metaphor theory, in this paper, we model the likeness of attribute for the first time and propose a novel Attribute Likeness and Domain Inconsistency Learning framework (AIDIL) for word-pair metaphor detection. Specifically, we propose an attribute siamese network to mine similar attributes between source and target concepts. We then devise a domain contrastive learning strategy to learn the semantic inconsistency of concepts in source and target domains. Extensive experiments on four datasets verify that our method significantly outperforms the previous state-of-the-art methods, and demonstrate the generalization ability of our method.

Modeling Conceptual Attribute Likeness and Domain Inconsistency for Metaphor Detection

Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data. As opposed to constructing increasingly complex logic, this paper probes into the boolean logic, the root capability of a logical reasoner. We find that any pre-trained language models even including large language models only behave like a random selector in the face of multi-nested boolean logic, a task that humans can handle with ease. To empower language models with this fundamental capability, this paper proposes a new self-supervised learning method Curriculum Logical Reasoning (Clr), where we augment the training data with nested boolean logic chain step-by-step, and program the training from simpler logical patterns gradually to harder ones. This new training paradigm allows language models to effectively generalize to much harder and longer-hop logic, which can hardly be learned through naive training. Furthermore, we show that boolean logic is a great foundation for improving the subsequent general logical tasks.

Empower Nested Boolean Logic via Self-Supervised Curriculum Learning

Pre-trained language models (PLMs) have achieved the preeminent position in dense retrieval due to their powerful capacity in modeling intrinsic semantics. However, most existing PLM-based retrieval models encounter substantial computational costs and are infeasible for processing long documents. In this paper, a novel retrieval model Longtriever is proposed to embrace three core challenges of long document retrieval: substantial computational cost, incomprehensive document understanding, and scarce annotations. Longtriever splits long documents into short blocks and then efficiently models the local semantics within a block and the global context semantics across blocks in a tightly-coupled manner. A pre-training phase is further proposed to empower Longtriever to achieve a better understanding of underlying semantic correlations. Experimental results on two popular benchmark datasets demonstrate the superiority of our proposal.

Longtriever: a Pre-trained Long Text Encoder for Dense Document Retrieval

In this work, we carry out a data archaeology to infer books that are known to ChatGPT and GPT-4 using a name cloze membership inference query. We find that OpenAI models have memorized a wide collection of copyrighted materials, and that the degree of memorization is tied to the frequency with which passages of those books appear on the web. The ability of these models to memorize an unknown set of books complicates assessments of measurement validity for cultural analytics by contaminating test data; we show that models perform much better on memorized books than on non-memorized books for downstream tasks. We argue that this supports a case for open models whose training data is known.

Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4

Current approaches to Argument Mining (AM) tend to take a holistic or black-box view of the overall pipeline. This paper, in contrast, aims to provide a solution to achieve increased performance based on current components instead of independent all-new solutions. To that end, it presents the Deployment of Recombination and Ensemble methods for Argument Miners (DREAM) framework that allows for the (automated) combination of AM components. Using ensemble methods, DREAM combines sets of AM systems to improve accuracy for the four tasks in the AM pipeline. Furthermore, it leverages recombination by using different argument miners elements throughout the pipeline. Experiments with five systems previously included in a benchmark show that the systems combined with DREAM can outperform the previous best single systems in terms of accuracy measured by an AM benchmark.

Downloads

Next from EMNLP 2023

Query-as-context Pre-training for Dense Passage Retrieval

Similar lecture

Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks