Canada

Out-of-distribution (OOD) detection, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly to store fine-tuned models for each scenario. In this paper, we depart from the classic fine-tuning based OOD detection toward a parameter-efficient alternative, and propose an unsupervised prefix-tuning based OOD detection framework termed PTO. Additionally, to take advantage of optional training data labels and targeted OOD data, two practical extensions of PTO are further proposed. Overall, PTO and its extensions offer several key advantages of being lightweight, easy-to-reproduce, and theoretically justified. Experimental results show that our methods perform comparably to, even better than, existing fine-tuning based OOD detection approaches under a wide range of metrics, detection settings, and OOD types.

&lt;iframe src=&quot;https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/7d00b778-b059-4ed7-95e3-e919cb767507&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

On Prefix-tuning for Lightweight Out-of-distribution Detection

open-environment

prefix-tuning

out-of-distribution detection

### 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.

Out-of-distribution (OOD) detection, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly to store fine-tuned models for each scenario. In this paper, we depart from the classic fine-tuning based OOD detection toward a parameter-efficient alternative, and propose an unsupervised prefix-tuning based OOD detection framework termed PTO. Additionally, to take advantage of optional training data labels and targeted OOD data, two practical extensions of PTO are further proposed. Overall, PTO and its extensions offer several key advantages of being lightweight, easy-to-reproduce, and theoretically justified. Experimental results show that our methods perform comparably to, even better than, existing fine-tuning based OOD detection approaches under a wide range of metrics, detection settings, and OOD types.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/7d00b778-b059-4ed7-95e3-e919cb767507" width="300" height="400"></iframe>

poster

Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem. Prior works propose to utilize the translations by either humans or machines to alleviate such issues. However, human translations are expensive, while machine translations are cheap but prone to error and bias. In this work, we propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. Besides, we propose novel aggregated acquisition criteria that help our active learning method select utterances to be manually translated. Our experiments demonstrate that an ideal utterance selection can significantly reduce the error and bias in the translated data, resulting in higher parser accuracies than the parsers merely trained on the machine-translated data.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/af1dfda2-1afc-49a5-94f9-b5b6832a3802" width="300" height="400"></iframe>

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

This paper focuses on the task of cross domain few-shot named entity recognition (NER), which aims to adapt the knowledge learned from source domain to recognize named entities in target domain with only a few labeled examples. To address this challenging task, we propose MANNER, a variational memory-augmented few-shot NER model. Specifically, MANNER uses a memory module to store information from the source domain and then retrieve relevant information from the memory to augment few-shot task in the target domain. In order to effectively utilize the information from memory, MANNER uses optimal transport to retrieve and process information from memory, which can explicitly adapt the retrieved information from source domain to target domain and improve the performance in the cross domain few-shot setting. We conduct experiments on English and Chinese cross domain few-shot NER datasets, and the experimental results demonstrate that MANNER can achieve superior performance.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/261f4ff3-4ffa-4868-b8c7-17635efe3a81" width="300" height="400"></iframe>

MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition

Existing knowledge-grounded open-domain dialogue generation models often face the hallucination problem, i.e. the dialogue generative model will persist in an inappropriate knowledge and generate responses that inconsistent with the facts. We argue that this problem mainly stems from the polarized optimization objectives and weak knowledge generation ability. To mitigate the hallucination, we take inspiration from human communicating that people will replay euphemistic responses for the unclear or unrecognizable knowledge, and propose an Augmentative and Contrastive Knowledge Dialogue Expansion Framework (ACK-DEF). ACK-DEF constructs the augmentative and contrastive knowledge dialogue samples, which consist of the knowledge of different degrees of errors and the response of manual design, to expand the original training set and smooth the polarized optimization objective that enables models to generate ground-truth with or without gold knowledge. Not only the knowledge, ACK-DEF also provides the tactful responses of manual design corresponding to the incomplete correct knowledge. Experimental results on the Wikipedia of Wizard dataset show that employing the ACK-DEF is effective to alleviate the hallucination problem.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/ed15281f-90ca-46cf-90ed-fa9f59397f5e" width="300" height="400"></iframe>

Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue

We present a new multilingual multi-facet dataset of news articles, each annotated for the genre (writing style used), the framing (what key aspects are highlighted), and rhetoric appeals (which persuasion techniques are used). The persuasion techniques are annotated at the span level, using a taxonomy of 23 fine-grained techniques grouped into 6 coarse categories. The dataset contains 1,612 news articles covering news on current topics of public interest in six European languages (English, French, German, Italian, Polish, and Russian), with more than 37k annotated spans. We describe the dataset and the annotation process, and we report on preliminary multi-label classification experiments using state-of-the-art multilingual transformers at different levels of granularity: token, sentence, paragraph, document.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2a5a9d5f-8685-44c9-8d03-260adfc088de" width="300" height="400"></iframe>

Multilingual Multifaceted Understanding of Online News in Terms of Genre, Framing, and Persuasion Techniques

Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DiVeRSe (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DiVeRSe has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DiVeRSe on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/287a7362-a6b8-49b3-8360-7fe2dac05210" width="300" height="400"></iframe>

Making Language Models Better Reasoners with Step-Aware Verifier

Evaluating grounded neural language model performance with respect to pragmatic qualities like the trade off between truthfulness, contrastivity and overinformativity of generated utterances remains a challenge in absence of data collected from humans.To enable such evaluation, we present a novel open source image-text dataset "Annotated 3D Shapes" (A3DS) comprising over nine million exhaustive natural language annotations and over 12 million variable-granularity captions for the 480,000 images provided by Burgess & Kim (2018).We showcase the evaluation of pragmatic abilities developed by a task-neutral image captioner fine-tuned in a multi-agent communication setting to produce contrastive captions. The evaluation is enabled by the dataset because the exhaustive annotations allow to quantify the presence of contrastive features in the model's generations. We show that the model develops human-like patterns (informativity, brevity, over-informativity for specific features (e.g., shape, color biases)).

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/d1805778-b3ff-4bc7-9fe7-591ab9e0b10e" width="300" height="400"></iframe>

Evaluating pragmatic abilities of image captioners on A3DS

Weir has defined a hierarchy of language classes whose second member (L2) is generated by tree-adjoining grammars (TAG), linear indexed grammars (LIG), combinatory categorial grammars, and head grammars. The hierarchy is obtained using the mechanism of control, and L2 is obtained using a context-free grammar (CFG) whose derivations are controlled by another CFG. We adapt Weir's definition of a controllable CFG (called a labeled distinguished CFG) to give a definition of controllable pushdown automata (PDAs), called labeled distinguished PDAs. This yields three new characterizations of L2 as the class of languages generated by PDAs controlling PDAs, PDAs controlling CFGs, and CFGs controlling PDAs. We show that these four formalisms are not only weakly equivalent but equivalent in a stricter sense that we call d-weak equivalence. Furthermore, using an even stricter notion of equivalence called d-strong equivalence, we make precise the intuition that a CFG controlling a CFG is a TAG, a PDA controlling a PDA is an embedded PDA, and a PDA controlling a CFG is a LIG. The fourth member of this family, a CFG controlling a PDA, does not correspond to any kind of automaton we know of, so we invent one and call it a Pushdown Adjoining Automaton (PAA).

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/422eea28-c814-4fa9-ba91-d93c158d7521" width="300" height="400"></iframe>

Convergence and Diversity in the Control Hierarchy

Dialogue response generation requires an agent to generate a response according to the current dialogue history, in terms of which two-party dialogues have been well studied, but leaving a great gap for multi-party dialogues at the same time. Different from two-party dialogues where each response is a direct reply to its previous utterance, the addressee of a response utterance should be specified before it is generated in the multi-party scenario. Thanks to the huge amount of two-party conversational data, various pre-trained language models for two-party dialogue response generation have been proposed. However, due to the lack of annotated addressee labels in multi-party dialogue datasets, it is hard to use them to pre-train a response generation model for multi-party dialogues. To tackle this obstacle, we propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels, and the maximization steps to optimize a response generation model. Theoretical analyses and extensive experiments have justified the feasibility and effectiveness of our proposed method. The official implementation of this paper is available at https://github.com/EricLee8/MPDRG.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/9cdac8be-8cdd-4579-b463-b6003631d836" width="300" height="400"></iframe>

EM Pre-training for Multi-party Dialogue Response Generation

In automatic emotion recognition (AER), labels assigned by different human annotators to the same utterance are often inconsistent due to the inherent complexity of emotion and the subjectivity of perception. Though deterministic labels generated by averaging or voting are often used as the ground truth, it ignores the intrinsic uncertainty revealed by the inconsistent labels. This paper proposes a Bayesian approach, deep evidential emotion regression (DEER), to estimate the uncertainty in emotion attributes. Treating the emotion attribute labels of an utterance as samples drawn from an unknown Gaussian distribution, DEER places an utterance-specific normal-inverse gamma prior over the Gaussian likelihood and predicts its hyper-parameters using a deep neural network model. It enables a joint estimation of emotion attributes along with the aleatoric and epistemic uncertainties. AER experiments on the widely used MSP-Podcast and IEMOCAP datasets showed DEER produced state-of-the-art results for both the mean values and the distribution of emotion attributes.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/56475cd7-05a0-4ccc-8464-fee3028bf50e" width="300" height="400"></iframe>

Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression

Temporal knowledge graph embedding (TKGE) models are commonly utilized to infer the missing facts and facilitate reasoning and decision-making in temporal knowledge graph based systems. However, existing methods fuse temporal information into entities, potentially leading to the evolution of entity information and limiting the link prediction performance of TKG. Meanwhile, current TKGE models often lack the ability to simultaneously model important relation patterns and provide interpretability, which hinders their effectiveness and potential applications. To address these limitations, we propose a novel TKGE model which encodes \textbf{T}emporal knowledge graph \textbf{e}mbeddings via \textbf{A}rchimedean \textbf{S}piral \textbf{T}imeline (TeAST), which maps relations onto the corresponding Archimedean spiral timeline and transforms the quadruples completion to 3th-order tensor completion problem. Specifically, the Archimedean spiral timeline ensures that relations that occur simultaneously are placed on the same timeline, and all relations evolve over time. Meanwhile, we present a novel temporal spiral regularizer to make the spiral timeline orderly. In addition, we provide mathematical proofs to demonstrate the ability of TeAST to encode various relation patterns. Experimental results show that our proposed model significantly outperforms existing TKGE methods. Our code is available at \url{https://github.com/IMU-MachineLearningSXD/TeAST}.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/19e149d1-b43a-487c-b680-0c420cd3f86d" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

Similar lecture

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection