Canada

It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition (a prompt and a few shot of example entity pairs), the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge of the desired relation. We develop an effective search-and-rescore mechanism for improved efficiency and accuracy. We deploy the approach to harvest KGs of over 400 new relations, from LMs of varying capacities such as RoBERTaNet. Extensive human and automatic evaluations show our approach manages to extract diverse accurate knowledge, including tuples of complex relations (e.g., &quot;A is capable of but not good at B&quot;). The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs&#39; knowledge capacities.

&lt;iframe src=&quot;https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2ce9db84-7a4f-469c-b0e4-a7ccab400fe5&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models

knowledge base

language model

knowledge graph

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair:<br>
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for  Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025.  ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am  deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.*<br>
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)<br><br><br>



To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition (a prompt and a few shot of example entity pairs), the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge of the desired relation. We develop an effective search-and-rescore mechanism for improved efficiency and accuracy. We deploy the approach to harvest KGs of over 400 new relations, from LMs of varying capacities such as RoBERTaNet. Extensive human and automatic evaluations show our approach manages to extract diverse accurate knowledge, including tuples of complex relations (e.g., "A is capable of but not good at B"). The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs' knowledge capacities.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2ce9db84-7a4f-469c-b0e4-a7ccab400fe5" 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.

Applying neural models injected with in-domain user and product information to learn review representations of unseen or anonymous users incurs an obvious obstacle in content-based recommender systems. For the generalization of the in-domain classifier, most existing models train an extra plain-text model for the unseen domain. Without incorporating historical user and product information, such a schema makes unseen and anonymous users dissociate from the recommender system. To simultaneously learn the review representation of both existing and unseen users, this study proposed a switch knowledge distillation for domain generalization. A generalization-switch (GSwitch) model was initially applied to inject user and product information by flexibly encoding both domain-invariant and domain-specific features. By turning the status ON or OFF, the model introduced a switch knowledge distillation to learn a robust review representation that performed well for either existing or anonymous unseen users. The empirical experiments were conducted on IMDB, Yelp-2013, and Yelp-2014 by masking out users in test data as unseen and anonymous users. The comparative results indicate that the proposed method enhances the generalization capability of several existing baseline models. For reproducibility, the code for this paper is available at: https://github.com/yoyo-yun/DG_RRR.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/976c65d1-6ae3-45ab-af83-2357efb8a836" width="300" height="400"></iframe>

Domain Generalization via Switch Knowledge Distillation for Robust Review Representation

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizes all history information, the dialogue state in the previous turn is typically adopted as the input for predicting the current state by DST models. However, these models tend to keep the predicted slot values unchanged, which is defined as state momentum in this paper. Specifically, the models struggle to update slot values that need to be changed and correct wrongly predicted slot values in the previous turn. To this end, we propose MoNET to tackle state momentum via noise-enhanced training. First, the previous state of each turn in the training data is noised via replacing some of its slot values. Then, the noised previous state is used as the input to learn to predict the current state, improving the model's ability to update and correct slot values. Furthermore, a contrastive contextmatching framework is designed to narrow the representation distance between a state and itscorresponding noised variant, which reduces the impact of noised state and makes the model better understand the dialogue history. Experimental results on MultiWOZ datasets show that MoNET outperforms previous DST methods. Ablations and analysis verify the effectiveness of MoNET in alleviating state momentum issues and improving the anti-noise ability.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/aad98e20-be39-4c95-9c76-5dcc72140dfb" width="300" height="400"></iframe>

MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking

Entity Alignment, which aims to identify equivalent entities from various Knowledge Graphs (KGs), is a fundamental and crucial task in knowledge graph fusion. Existing methods typically use triple or neighbor information to represent entities, and then align those entities using similarity matching. Most of them, however, fail to account for the heterogeneity among KGs and the distinction between KG entities and relations. To better solve these problems, we propose a Relation-gated Heterogeneous Graph Network (RHGN) for entity alignment. Specifically, RHGN contains a relation-gated convolutional layer to distinguish relations and entities in the KG. In addition, RHGN adopts a cross-graph embedding exchange module and a soft relation alignment module to address the neighbor heterogeneity and relation heterogeneity between different KGs, respectively. Extensive experiments on four benchmark datasets demonstrate that RHGN is superior to existing state-of-the-art entity alignment methods.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/47822d19-6a4c-4ec3-8a1d-0ca0d5c63d67" width="300" height="400"></iframe>

RHGN: Relation-gated Heterogeneous Graph Network for Entity Alignment in Knowledge Graphs

Recent research has shown that large-scale pretrained language models, specifically transformers, tend to exhibit issues relating to racism, sexism, religion bias, and toxicity in general. Unfortunately, these pretrained language models are used almost universally in downstream tasks, and natural language processing is often applied to make real-world predictions. Thus, debiasing these language models as early in development as possible is increasingly crucial for preventing unintentional harms caused by natural language systems. To this end, we propose a new technique called partitioned contrastive gradient unlearning (PCGU), a gray-box method for debiasing pretrained masked language models. PCGU aims to optimize only the weights that contribute most to a specific domain of bias, doing so by computing a first-order approximation based on the gradients of contrastive sentence pairs. Our experiments show that PCGU is both low-cost and seems particularly effective at pinpointing the sources of implicit social bias in large pretrained transformers. Although we train using PCGU in the gender-profession domain only, we find that doing so can also partially mitigate bias across other domains. All code for our implementation and experiments can be found at https://github.com/CharlesYu2000/PCGU-UnlearningBias.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/2d38aa07-1db3-45d9-b33b-6c2234bef866" width="300" height="400"></iframe>

Unlearning Bias in Language Models by Partitioning Gradients

While impressive performance has been achieved on the task of Answer Sentence Selection (AS2) for English, the same does not hold for languages that lack large labeled datasets. In this work, we propose Cross-Lingual Knowledge Distillation (CLKD) from a strong English AS2 teacher as a method to train AS2 models for low-resource languages in the tasks without the need of labeled data for the target language. To evaluate our method, we introduce 1) Xtr-WikiQA, a translation-based WikiQA dataset for 9 additional languages, and 2) TyDi-AS2, a multilingual AS2 dataset with over 70K questions spanning 8 typologically diverse languages. We conduct extensive experiments on Xtr-WikiQA and TyDi-AS2 with multiple teachers, diverse monolingual and multilingual pretrained language models (PLMs) as students, and both monolingual and multilingual training. The results demonstrate that CLKD either outperforms or rivals even supervised fine-tuning with the same amount of labeled data and a combination of machine translation and the teacher model. Our method can potentially enable stronger AS2 models for low-resource languages, while TyDi-AS2 can serve as the largest multilingual AS2 dataset for further studies in the research community.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/4cb867bf-259b-4b46-82ce-2c0e0a06611a" width="300" height="400"></iframe>

Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages

How-to Guides for Specific Audiences: A Corpus and Initial Findings

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/271704b0-511b-4682-be92-c67bdd22bae8" width="300" height="400"></iframe>

How-to Guides for Specific Audiences: A Corpus and Initial Findings

Chain-of-thought (CoT) prompting, i.e., step-by-step reasoning instruction, enhances the performance of large language models (LLMs) in various tasks. Nevertheless, whether this gain suggests that LLMs have robust reasoning abilities remains unclear. In this study, we inspect the LLMs' step-by-step reasoning ability under controlled settings, with a particular focus on negation. Our results indicate that all tested LLMs were not robust against lexical negation (e.g., plausible -> implausible) when performing the CoT reasoning. Furthermore, our experiments with varying levels revealed that different LLMs exhibit different difficulties and output biases against lexical negation.

Assessing Chain-of-Thought Reasoning against Lexical Negation: A Case Study on Syllogism

Recently, dynamic early exiting has attracted much attention since it can accelerate the inference speed of pre-trained models (PTMs). However, previous work on early exiting has neglected the intermediate exits' architectural designs. In this work, we propose a novel framework, \underline{L}earned \underline{E}xits and \underline{CO}mparison-based early exiting (LECO) to improve PTMs' early exiting performances. First, to fully uncover the potentials of multi-exit BERT, we design a novel search space for intermediate exits and employ the idea of differentiable neural architecture search (DNAS) to design proper exit architectures for different intermediate layers automatically. Second, we propose a simple-yet-effective comparison-based early exiting mechanism (COBEE), which can help PTMs achieve better performance and speedup tradeoffs. Extensive experiments show that our LECO achieves the SOTA performances for multi-exit BERT training and dynamic early exiting.

LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism

Currently, most knowledge-grounded dialogue response generation models focus on reflecting given external knowledge. However, even when conveying external knowledge, humans integrate their own knowledge, experiences, and opinions with external knowledge to make their utterances engaging. In this study, we analyze such human behavior by annotating the utterances in an existing knowledge-grounded dialogue corpus. Each entity in the corpus is annotated with its information source, either derived from external knowledge (database-derived) or the speaker's own knowledge, experiences, and opinions (speaker-derived). Our analysis shows that the presence of speaker-derived information in the utterance improves dialogue engagingness. We also confirm that responses generated by an existing model, which is trained to reflect the given knowledge, cannot include speaker-derived information in responses as often as humans do.

Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation

We introduce our work submitted to SemEval-2023 Task 12: "Sentiment Analysis for Low-resource African Languages using Twitter dataset". In our system, we leverage adaptive pretraining on African texts and study transfer learning with source language selection. Our system wins 2 of 3 subtasks and performs best in 7 out of 14 languages in the shared task.

Downloads

Next from ACL 2023

Domain Generalization via Switch Knowledge Distillation for Robust Review Representation

Similar lecture

Generating Domain-Specific Knowledge Graphs from Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2023

Domain Generalization via Switch Knowledge Distillation for Robust Review Representation

Similar lecture

Generating Domain-Specific Knowledge Graphs from Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads