Netherlands

Word Sense Disambiguation (WSD) has been a fundamental task for human language understanding. In specific contexts, a word may have different meanings. For rarely seen word senses, the disambiguation becomes challenging with limited examples. Meta-learning, as a widely adopted machine learning method for few-shot learning, addresses this by extracting metacognitive knowledge from training data, aiding models in &quot;learning to learn&quot;. Hence, the advancement of meta-learning hinges on leveraging high-quality metacognitive knowledge. In light of this, we propose a Bi-Branch Meta-Learning method for WSD to enrich and accumulate metacognitive insights. Our method employs two branches during training and testing. During training, we use a bi-branch loss with original and augmented data from large language models to compensate for data scarcity. In testing, information from base classes generates bi-branch scores to refine predictions. Experiments show our method achieves a 74.3 F1 score in few-shot scenarios, demonstrating its potential for few-shot WSD.

**Authors:**

Qingying Chen: Tianjin University; Jing Zhang: Tianjin University; Peng Zhang: Tianjin University; Hui Gao: Tianjin University

CogSci 2024

Bi-Branch Meta-Learning for Few-Shot Word Sense Disambiguation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

Word Sense Disambiguation (WSD) has been a fundamental task for human language understanding. In specific contexts, a word may have different meanings. For rarely seen word senses, the disambiguation becomes challenging with limited examples. Meta-learning, as a widely adopted machine learning method for few-shot learning, addresses this by extracting metacognitive knowledge from training data, aiding models in "learning to learn". Hence, the advancement of meta-learning hinges on leveraging high-quality metacognitive knowledge. In light of this, we propose a Bi-Branch Meta-Learning method for WSD to enrich and accumulate metacognitive insights. Our method employs two branches during training and testing. During training, we use a bi-branch loss with original and augmented data from large language models to compensate for data scarcity. In testing, information from base classes generates bi-branch scores to refine predictions. Experiments show our method achieves a 74.3 F1 score in few-shot scenarios, demonstrating its potential for few-shot WSD.

**Authors:**

Qingying Chen: Tianjin University; Jing Zhang: Tianjin University; Peng Zhang: Tianjin University; Hui Gao: Tianjin University

poster

The 46th Annual Meeting of the Cognitive Science Society was an in-person meeting held in Rotterdam, The Netherlands at the Postillion Hotel & Conference Centre.

**ON-DEMAND PROGRAM ACCESS AFTER THE CONFERENCE** 
Recordings of the invited program are now available. You can access them by clicking on the 'Schedule' icon on the left. Select view by week and navigate to the day and time slot of the recording you wish to view. Click on the time slot to access the recording.

Recordings available (click on each recording to view):

**Thursday, July 25** 
0900: [Keynote Speaker Morgan Barense on Enhancing real-world event memory](https://underline.io/events/465/sessions/17997/lecture/99084-dynamics-between-minds-and-the-environment) 
1000: [Gleitman Award Winner Isabelle Dautriche on Language Foundations: Insights from acquisition, communication, cognition, and more](https://underline.io/events/465/sessions/18000/lecture/99085-gleitman-talk) 
1415: [Invited Symposium: Dynamics between minds and the environment](https://underline.io/events/465/sessions?eventSessionId=18016&searchGroup=lecture) 
1700: [Rumelhart Prize Presentation Speaker Alison Gopnik on Exploit, explore, empower: Three ages and three intelligences](https://underline.io/events/465/sessions/18028/lecture/99161-rp1-rumelhart-prize-presentation) 

**Friday, July 26** 
0900: [C.L. de Carvalho-Heineken Prize Keynote Speaker Kia Nobre on Focusing in memory](https://underline.io/events/465/sessions/18035/lecture/99162-hp1-c-l-de-carvalho-heineken-prize-keynote-address) 
1030: [Rumelhart Symposium: Childhood as exploration](https://underline.io/events/465/sessions/18038/lecture/100346-childhood-as-exploration) 
1415: [Elman Prize Symposium](https://underline.io/events/465/sessions?eventSessionId=18053&searchGroup=lecture) 
1600: [Invited Symposium: Dynamics between minds](https://underline.io/events/465/sessions?eventSessionId=18065&searchGroup=lecture) 
1745: [Keynote Speaker Andrea E. Martin on Neural dynamics encode the structure and statistics of language](https://underline.io/events/465/sessions/18077/lecture/99271-neural-dynamics-encode-the-structure-and-statistics-of-language) 

**Saturday, July 27** 
0900: [Keynote Speaker Gregor Schöner on How higher cognition emerges from the dynamics of strongly interacting neural populations](https://underline.io/events/465/sessions/18083/lecture/99273-dynamics-within-the-mind) 
1000: [Glushko Talks](https://underline.io/events/465/sessions?eventSessionId=18086&searchGroup=lecture) 
1500: [Invited Symposium: Dynamics within minds](https://underline.io/events/465/sessions?eventSessionId=18100&searchGroup=lecture) 


#### **CogSci 2024 Program Book**
<div style="position:relative;padding-top:0;width:900px;height:500px;"><iframe style="position:absolute;border:none;width:100%;height:100%;left:0;top:0;" src="https://online.fliphtml5.com/ebtyf/cble/" seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe></div>


**The Program Book can be downloaded [here](https://drive.google.com/file/d/1yRVp1cBqRnAbdYi4GXWV_pZeyWNsRquv/view?usp=sharing).**

#### **Letter from the President**

Welcome to the 2024 Meeting of the Cognitive Science Society in Rotterdam! CogSci 2024 brings together a large community of cognitive scientists who have traveled here from around the world, as well as a smaller group of remote presenters. I would like to extend an especially warm welcome to our first-time CogSci meeting attendees, and hope that 
their experience inspires them to join our future meetings for many years to come.

I want to thank this year’s conference co-chairs, Larissa K Samuelson, Stefan Frank, Mariya Toneva, Allyson Mackey, and Eliot Hazeltine, for putting together an amazing series of invited talks and symposia around the theme of Dynamics of Cognition. The co-chairs also deserve credit for handling a record-breaking number of submissions and producing a truly exciting conference program 

Beyond the invited talks and symposia dedicated to this year’s conference theme, I would like to highlight the presentations and events honoring the 
Rumelhart, Elman, Gleitman and C .L . de Carvalho Heineken prize winners, including the Rumelhart reception on Thursday. As you may know, we are recording all of the invited talks and symposia, and all prize-winners’ talks, and will be making this content available after the conference. 

The Cognitive Science Society relies on the volunteer efforts of our Governing Board members who work on matters related to our membership; conference policies; diversity and inclusion, international, and outreach initiatives; prizes and much more. We welcome interest from Society members who would like to become more involved in what we do. The 
Society is deeply grateful to Rick Dale and Andrea Bender, who serve as editors of the two Society journals, Cognitive Science and Topics in Cognitive Science respectively. We especially acknowledge our editors’ generosity in donating their stipends each year to D&I and outreach efforts. 

This year’s Annual Meeting depends critically on the support of Marischal De Armond and his team at Podium Conference Specialists: Sharon Zwack, Cendrine De Vis, Sarah-Kate Burke, and Rachel Waller worked tirelessly to secure the venue and handled a multitude of logistical and organizational issues, from arranging coffee breaks and receptions to making sure that a huge number of posters fits comfortably into the available space. Finally, and importantly, I would like to acknowledge the Cognitive Science Society Executive Officer, Erica Wojcik, for managing the complex and ever expanding sphere of our Society’s activities.

I hope you enjoy this year’s meeting and the many different opportunities to engage with the vibrant community of cognitive scientists gathered here. I also hope you get a chance to explore the great city of Rotterdam with its many attractions, museums, restaurants and scenic views. If you’d like to talk more about our Society, or simply want to say hello, please stop by!

![](https://assets.underline.io/markdown_image/1/image/3c66d0e21fff30e204df1138ffd15173.jpeg)

**Anna Papafragou** 
President, Cognitive Science 
Society 2023-2024

**CODE OF CONDUCT** 
By attending the CogSci 2024 Conference, you are required to adhere to the society’s [Code of Conduct](https://drive.google.com/file/d/16-6KkptF0Gn3ZYGJDlpqpwTdImw45Ng0/view?usp=drive_link).

**ABOUT THE COGNITIVE SCIENCE SOCIETY** 
The Cognitive Science Society brings together researchers from around the world who hold a common goal: understanding the nature of the human mind. The mission of the Society is to promote Cognitive Science as a discipline, and to foster scientific interchange among researchers in various areas of study, including Artificial Intelligence, Linguistics, Anthropology, Psychology, Neuroscience, Philosophy, and Education.

The Society is a non-profit professional organization and its activities include sponsoring an annual conference and publishing the journals Cognitive Science and TopiCS.

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

It looks like you are not registered for this event. 

To access the site please register [**here**](https://cognitivesciencesociety.org/registration/). 

Please register!

The 46th Annual Meeting of the Cognitive Science Society presents the latest research across cognitive science and highlights the theme of Cognition in Context.

In studies of song corpora, longer vowels have been shown to be preferentially aligned with longer notes in textsetting. Here we test this alignment preference in English in an experimental setting and replicate the finding for duration in a task where participants constructed a textsetting by placing target words in appropriate slots. We test two types of vowel duration: intrinsic duration and vowel duration that is contextually determined by the voicing of the following consonant. We show that both of these types of duration have an effect on textsetting preferences.

**Authors:**

Nicole Gilroy: Carleton University; Lev Blumenfeld: Carleton University; Ida Toivonen: Carleton University

Both intrinsic and allophonic vowel duration matter in textsetting

The effect of syntactic priming exhibits three well-documented empirical properties: the lexical boost, the inverse frequency effect, and the asymmetrical decay. We aim to show how these three empirical phenomena can be reconciled in a general learning framework, the hierarchical Bayesian model (HBM). The model represents syntactic knowledge in a hierarchical structure of syntactic statistics, where a lower level represents the verb-specific biases of syntactic decisions, and a higher level represents the abstract bias as an aggregation of verb-specific biases. This knowledge is updated in response to experience by Bayesian inference. In simulations, we show that the HBM captures the above-mentioned properties of syntactic priming. The results indicate that some properties of priming which are usually explained by a residual activation account can also be explained by an implicit learning account. We also discuss the model's implications for the lexical basis of syntactic priming.

**Authors:**

Weijie Xu: University of California, Irvine; Richard Futrell: UC Irvine

A hierarchical Bayesian model for syntactic priming

The "shape bias" -- the bias to generalize new nouns by their shape rather than other features such as color or texture -- has been argued to facilitate early noun learning for children. However, there is conflicting evidence about the magnitude and nature of this bias, as well as how it changes developmentally and how it varies across cultures. In this paper, we synthesize evidence about the shape bias using meta-analysis and meta-regression. We find strong overall evidence for the shape bias, but the literature is dominated by studies of English-speaking children, making it difficult to assess cross-cultural differences. Large between-study heterogeneity also highlights procedural variation in the literature. Overall, publication bias, heterogeneity, and data sparsity may limit the ability to distinguish theoretical accounts of the shape bias.

**Authors:**

Samah O Abdelrahim: Stanford University; Michael C. Frank: Stanford University

Examining the robustness and generalizability of the shape bias: a meta-analysis

This study compared the influence of visuospatial experience and both immediate and long-term effects of spatial-temporal metaphors on temporal cognition through spontaneous gesture tasks with categorized Chinese temporal words. Native Mandarin speakers and Mandarin learners of near-native proficiency behaved similarly: (1) Both groups produced horizontal, vertical, sagittal, fused horizontal and vertical, and fused horizontal and sagittal gestures for all kinds of Chinese temporal words, showing a strong preference for horizontal over vertical gestures. This preference was influenced by visuosaptial experience than by metaphors, underscoring the greater influence of the former. (2) Negligible correlations between immediate spatial-temporal metaphors and the mental timelines were observed, with an almost non-existent difference in gesture distribution across metaphorical types between the two groups. This implies that gestures formed by long-term effect of language, such as vertical dimensions, may operate beyond the immediate metaphors，similar to the horizontal gestures. The similarity in temporal cognition between two groups further highlights the powerful long-term influence of metaphors. Accordingly，A unified model proposing embodied experience as the mechanism for activating mental timelines is presented.

**Authors:**

Chunying Wu: Peking University; Lingyue Kong: Peking university; Xiao Ke: Lancaster University

Surpassing Immediate Spatio-temporal Metaphors: The Enduring Impact of Language and Visuospatial Experience on Temporal Cognition in Native and Near-Native Mandarin Speakers

Are people who agree on something more likely to be right and competent? Evidence suggests that people tend to make this inference. However, standard wisdom of crowds approaches only provide limited normative grounds. Using simulations, we argue that when individuals make independent and unbiased estimates, under a wide range of parameters, individuals whose answers converge with each other tend to have more accurate answers and to be more competent. In 2 experiments (UK participants, total N = 399), we show that participants infer that informants who agree have more accurate answers and are more competent, even when they have no priors, and that these inferences are weakened when the informants are systematically biased. In conclusion, we speculate that inferences from convergence to accuracy and competence might help explain why people deem scientists competent, even if they have little understanding of science.

**Authors:**

Jan Pfänder: Institut Jean Nicod, ENS-PSL, CNRS; Benoît de Courson: Max Planck Institute for the Study of Crime, Security and Law; Hugo Mercier: CNRS

How wise is the crowd: Can we infer people are accurate and competent merely because they agree with each other?

Metaphor comprehension studies have investigated how we process metaphors by pitting conventional metaphors against novel ones. Although these studies have yielded much data on how we comprehend metaphors, no research has examined how we process novel spatial metaphors of time. 
We constructed a stimuli pool of 80 spatial metaphors of time, 40 were conventional time metaphors, whereas the other 40 were novel spatial metaphors of time evenly distributed among Moving-Ego or Moving-Time perspectives and Path or Manner metaphorical motion in the main verb. Ratings by 40 participants showed that the novel metaphors had more possible interpretations, were more ambiguous, difficult to interpret, less apt, and less conventional. A pilot study with 10 participants showed that these properties of metaphors were linked to metaphor interpretation and temporal gesture production in various ways. This study will continue to investigate how we process and represent novel spatial metaphors of time with more participants.

**Authors:**

Emir Akbuga: Koç University; Tilbe Göksun: Koç University

What makes a novel spatial metaphor of time?

Joint improvisation is central to how we navigate the social world, engage and maintain social interactions, and perceive interactions between other people. This project investigates people’s ability to distinguish between joint and individual actions (contemporary joint vs. solo dance improvisation) and the information they use to make this determination. In Experiment 1, participants were asked to identify whether two people were improvising dance movements together or alone. Experiment 2 explored how much people’s decision-making relies on information about the dancers’ facial expressions and gaze direction. Overall, results showed we can accurately identify improvised joint actions, even when the actors’ faces and gaze direction are occluded.

**Authors:**

Trinidad Belén Speranza: National Scientific and Technical Research Council; Ivonnia M Flores Bravo: Pontificia Universidad Católica Argentina; Verónica Ramenzoni: National Scientific and Technological Council of Argentina

Joint Improvisation; Perception of Togetherness in Contemporary Dance Performance

Language-specific accounts of bilingual learning advantages suggest that advantages in language learning are tied to an individual’s linguistic experience, with learning advantages stemming from transfer effects between known and to-be-learnt language features. To test this hypothesis, we trained Singapore English-Mandarin bilinguals on a synthesised alveolar-retroflex [tsʰuə́n]-[ʈʂʰuə́n] contrast with a bimodal distributional learning paradigm. We reasoned that participants with higher Mandarin understanding proficiencies would show larger distributional learning effects due to transfer between real-world Mandarin experience and the training stimuli. We examined overall learning effects in a pilot study (N = 20) and a preregistered main study (N = 50). We found evidence of learning in both the pilot and the main study. We also found evidence of a transfer effect tied to individual Mandarin skills, with larger learning effects linked to higher Mandarin understanding proficiencies. This study demonstrates specific advantages of language background on perceptual learning at the individual level.

**Authors:**

Hannah L. Goh: Nanyang Technological University; Suzy J. Styles: Nanyang Technological University

A preregistered investigation of language-specific distributional learning advantages in English-Mandarin bilingual adults

The Green IT approach questions the environmental, social and economic impact of digital technology. Design fiction is a discipline that can guide behaviors in favor of Green IT by building new imaginaries. However, to our knowledge, few studies assess the impact of narratives of possible future on behavioral intentions. To answer this question, we conducted a study with 388 participants, examining the impact of 14 different scenarios of possible digital futures on individual perceptions. The results showed that, for individuals with already a high level of Green IT practices, the fear dimension of scenarios has a preeminent impact on their intention to further increase these behaviors, whereas people with little practice of Green IT are more sensitive to confidence and the presence of solutions. These results pave the way for the integration of specific technological narratives within the construction of future public policies in favor of Green IT.

**Authors:**

Julie Rochat: b<>com; Martin Ragot: b<>com; Jean-Marc Josset: b<>com

Design fiction and Green IT: Impact of foresight scenarios on behavioral intention

Reading acquisition primarily relies on orthographic learning.
Behavioral studies show that familiarity with a novel word’s
pronunciation facilitates learning, particularly in semantically
meaningful contexts. Two main components of orthographic
learning are commonly described: perceptual processing of
the visual stimulus, to infer corresponding phonological rep-
resentations, and “pronunciation correction”, to correct errors
from perceptual processing. Currently, pronunciation correc-
tion has not been featured in reading acquisition computa-
tional models. This study uses BRAID-Acq, a reading ac-
quisition model, to implement and compare two pronunciation
correction mechanisms (an “online” and a “post-processing”
variant). We simulated learning of words with and without
prior phonological knowledge and explored the impact of con-
text strength and size on learning. Results indicate that both
mechanisms improve decoding. However, the post-processing
mechanism induced implausible lexicalization for words with-
out prior phonological knowledge, while the online mecha-
nism did not. Overall, our simulation results suggest that pro-
nunciation correction could be construed as an online process.

**Authors:**

Alexandra Steinhilber: Laboratoire de Psychologie et NeuroCognition; Sylviane Valdois: CNRS et Université Grenoble Alpes; Julien Diard: CNRS - Université Grenoble Alpes

Premium content

Downloads

Next from CogSci 2024

Both intrinsic and allophonic vowel duration matter in textsetting

Similar lecture

Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES