Canada

Arguments often do not make explicit how a conclusion follows from its premises. To compensate for this lack, we enrich arguments with structured background knowledge to support knowledge-intense argumentation tasks. We present a new unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) that selects contextually relevant knowledge from large knowledge graphs (KGs) efficiently and at high quality. Our work goes beyond context-insensitive knowledge extraction heuristics by computing semantic similarity between KG triplets and textual arguments. Using these triplet similarities as weights, we extract contextualized knowledge paths that connect a conclusion to its premise, while maximizing similarity to the argument. We combine multiple paths into a CCKG that we optionally prune to reduce noise and raise precision. Intrinsic evaluation of the quality of our graphs shows that our method is effective for (re)constructing human explanation graphs. Manual evaluations in a large-scale knowledge selection setup verify high recall and precision of implicit CSK in the CCKGs. Finally, we demonstrate the effectiveness of CCKGs in a knowledge-insensitive argument quality rating task, outperforming strong baselines and rivaling a GPT-3 based system.

&lt;iframe src=&quot;https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/db0612ce-8fed-47fe-9e71-4a7c7c75a36b&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks

graph construction

implicit csk

argument

graph

extraction

commonsense knowledge

knowledge graph

argumentation

information extraction

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.<br><br>
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*<br><br><br><br>

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

EACL 2024

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Arguments often do not make explicit how a conclusion follows from its premises. To compensate for this lack, we enrich arguments with structured background knowledge to support knowledge-intense argumentation tasks. We present a new unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) that selects contextually relevant knowledge from large knowledge graphs (KGs) efficiently and at high quality. Our work goes beyond context-insensitive knowledge extraction heuristics by computing semantic similarity between KG triplets and textual arguments. Using these triplet similarities as weights, we extract contextualized knowledge paths that connect a conclusion to its premise, while maximizing similarity to the argument. We combine multiple paths into a CCKG that we optionally prune to reduce noise and raise precision. Intrinsic evaluation of the quality of our graphs shows that our method is effective for (re)constructing human explanation graphs. Manual evaluations in a large-scale knowledge selection setup verify high recall and precision of implicit CSK in the CCKGs. Finally, we demonstrate the effectiveness of CCKGs in a knowledge-insensitive argument quality rating task, outperforming strong baselines and rivaling a GPT-3 based system.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/db0612ce-8fed-47fe-9e71-4a7c7c75a36b" 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.

Anxiety disorders are the most common of mental illnesses, but relatively little is known about how to detect them from language. The primary clinical manifestation of anxiety is worry associated cognitive distortions, which are likely expressed at the discourse-level of semantics. Here, we investigate the development of a modern linguistic assessment for degree of anxiety, specifically evaluating the utility of discourse-level information in addition to lexical-level large language model embeddings. We find that a combined lexico-discourse model outperforms models based solely on state-of-the-art contextual embeddings (RoBERTa), with discourse-level representations derived from Sentence-BERT and DiscRE both providing additional predictive power not captured by lexical-level representations. Interpreting the model, we find that discourse patterns of causal explanations, among others, were used significantly more by those scoring high in anxiety, dovetailing with psychological literature.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/10338705-e8f1-459c-81ec-d227428b010c" width="300" height="400"></iframe>

Discourse-Level Representations can Improve Prediction of Degree of Anxiety

We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine translation on natural language, mathematical formulae have a much smaller vocabulary and much longer sequences of symbols, while their translation requires extreme precision to satisfy mathematical information needs. In this work, we perform the tasks of translating from LaTeX to Mathematica as well as from LaTeX to semantic LaTeX. While recurrent, recursive, and transformer networks struggle with preserving all contained information, we find that convolutional sequence-to-sequence networks achieve 95.1% and 90.7% exact matches, respectively.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/682cd973-5d5c-4c16-a76c-54593e6dc3ab" width="300" height="400"></iframe>

Neural Machine Translation for Mathematical Formulae

State-of-the-art models can perform well in controlled environments, but they often struggle when presented with out-of-distribution (OOD) examples, making OOD detection a critical component of NLP systems. In this paper, we focus on highlighting the limitations of existing approaches to OOD detection in NLP. Specifically, we evaluated eight OOD detection methods that are easily integrable into existing NLP systems and require no additional OOD data or model modifications. One of our contributions is providing a well-structured research environment that allows for full reproducibility of the results. Additionally, our analysis shows that existing OOD detection methods for NLP tasks are not yet sufficiently sensitive to capture all samples characterized by various types of distributional shifts. Particularly challenging testing scenarios arise in cases of background shift and randomly shuffled word order within in domain texts. This highlights the need for future work to develop more effective OOD detection approaches for the NLP problems, and our work provides a well-defined foundation for further research in this area.

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

Argument Clustering with Deep Metric Learning for Semantic Frame Induction

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/980da88c-3a61-4fa4-be43-69feb30465c9" width="300" height="400"></iframe>

Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction

Multi-Dialectal Representation Learning of Sinitic Phonology

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/bc4cc57b-b532-4ac5-862c-50f52a6ecb76" width="300" height="400"></iframe>

Multi-Dialectal Representation Learning of Sinitic Phonology

A State-Vector Framework For Dataset Effects

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/cee70547-25cc-494e-8024-f5e22f5b412c" width="300" height="400"></iframe>

A State-Vector Framework For Dataset Effects

Probing for Hyperbole in Pre-Trained Language Models

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/5d30ef99-31f6-494b-b7ad-3556906236f6" width="300" height="400"></iframe>

Probing for Hyperbole in Pre-Trained Language Models

We present Visual Knowledge oriented Programming platform (<b>VisKoP</b>), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program induction module, which converts natural language questions into knowledge oriented program language (KoPL), but also maps KoPL programs into graphical elements. KoPL programs can be edited with simple graphical operators, such as <i>''dragging''</i> to add knowledge operators and <i>''slot filling''</i> to designate operator arguments. Moreover, VisKoP provides auto-completion for its knowledge base schema and users can easily debug the KoPL program by checking its intermediate results. To facilitate the practical KBQA on a million-entity-level KB, we design a highly efficient KoPL execution engine for the back-end. Experiment results show that VisKoP is highly efficient and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. The VisKoP online demo, highly efficient KoPL engine, and screencast video are now publicly available.

VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering

Neuron analysis provides insights into how knowledge is structured in representations and discovers the role of neurons in the network. In addition to developing an understanding of our models, neuron analysis enables various applications such as debiasing, domain adaptation and architectural search. We present NeuroX, a comprehensive open-source toolkit to conduct neuron analysis of natural language processing models. It implements various interpretation methods under a unified API, and provides a framework for data processing and evaluation, thus making it easier for researchers and practitioners to perform neuron analysis. The Python toolkit is available at https://www.github.com/fdalvi/NeuroX.

Demo Video available at: https://youtu.be/mLhs2YMx4u8

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/8ff32c30-2c3e-4ad7-8c95-8d8b44e94ce5" width="300" height="400"></iframe>

NeuroX Library for Neuron Analysis of Deep NLP Models

Information extraction systems often produce
hundreds to thousands of strings on a specific
topic. We present a method that facilitates
better consumption of these strings, in an ex-
ploratory setting in which a user wants to both
get a broad overview of what's available, and a
chance to dive deeper on some aspects. The sys-
tem works by grouping similar items together,
and arranging the remaining items into a hierar-
chical navigable DAG structure. We apply the
method to medical information extraction.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/2a9aa61f-2a2b-4873-a116-05577dc17666" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Discourse-Level Representations can Improve Prediction of Degree of Anxiety

Similar lecture

Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks