Program 2023


Day 1:

09:00 – 09:10: opening
09:10 – 10:30: keynote 1: Preslav Nakov
10:30 – 11:00: coffee break
11:00 – 12:30: oral session 1 (4 papers)
12:30 – 13:45: lunch
13:45 – 15:15: poster session 1 (14 papers)
15:15 – 15:30: coffee break
15:30 – 17:00: Oral Session 2 (4 papers)

Day 2:

09:10 – 10:30: keynote 2: Mohit Bansal
10:30 – 11:00: coffee break
11:00 – 12:30: oral session 3 (4 paper)
12:30 – 13:45: lunch
13:45 – 15:15: poster session 2 (13 papers)
15:15 – 15:30: coffee break
15:30 – 17:20: BabyLM Challenge
17:20 – 17:35: best paper awards and closing

Keynote sessions:

Preslav Nakov - Factuality Challenges in the Era of Large Language Models
Mohit Bansal - Multimodal Generative LLMs: Unification, Interpretability, Evaluation

Oral session 1:

Title Authors Topic
Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics Yuhan Zhang, Edward Gibson and Forrest Davis Computational Psycholinguistics, Cognition and Linguistics
ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind Xiaomeng Ma, Lingyu Gao and Qihui Xu Computational Psycholinguistics, Cognition and Linguistics
The Zipfian Challenge: Learning the statistical fingerprint of natural languages Christian Bentz Computational Psycholinguistics, Cognition and Linguistics
On the Effects of Structural Modeling for Neural Semantic Parsing Xiang Zhang, Shizhu He, Kang Liu and Jun Zhao Lexical, Compositional and Discourse Semantics

Oral session 2:

Title Authors Topic
The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks Kaiser Sun, Adina Williams and Dieuwke Hupkes Theoretical Analysis and Interpretation of ML Models for NLP
Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning Lucas Weber, Elia Bruni and Dieuwke Hupkes Theoretical Analysis and Interpretation of ML Models for NLP
Med-HALT: Medical Domain Hallucination Test for Large Language Models Ankit pal, Logesh Kumar Umapathi and Malaikannan Sankarasubbu Resources and Tools for Scientifically Motivated Research
Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing Brielen Madureira, Pelin Çelikkol and David Schlangen Theoretical Analysis and Interpretation of ML Models for NLP

Oral session 3:

Title Authors Topic
ChiSCor: A Corpus of Freely-Told Fantasy Stories by Dutch Children for Computational Linguistics and Cognitive Science Bram van Dijk, Max van Duijn, Suzan Verberne and Marco Spruit Resources and Tools for Scientifically Motivated Research
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities Esra Dönmez, Pascal Tilli, Hsiu-Yu Yang, Ngoc Thang Vu and Carina Silberer Interaction and Grounded Language Learning
Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests Max van Duijn, Bram van Dijk, Tom Kouwenhoven, Werner de Valk, Marco Spruit and Peter vander Putten Computational Psycholinguistics, Cognition and Linguistics
A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation Jarad Forristal, Fatemehsadat Mireshghallah, Greg Durrett and Taylor Berg-Kirkpatrick Natural Language Generation

BabyLM oral session:

Title Authors
Not all layers are equally as important: Every Layer Counts BERT Lucas Georges Gabriel Charpentier and David Samuel
Towards more Human-like Language Models based on Contextualizer Pretraining Strategy Chenghao Xiao, G Thomas Hudson and Noura Al Moubayed
Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures Julius Steuer, Marius Mosbach and Dietrich Klakow
CLIMB – Curriculum Learning for Infant-inspired Model Building Richard Diehl Martinez, Hope McGovern, Zebulon Goriely, Christopher Davis, Andrew Caines, Paula Buttery and Lisa Beinborn

Poster session 1:

Computational Psycholinguistics, Cognition and Linguistics; Interaction and Grounded Language Learning; Lexical, Compositional and Discourse Semantics; Multilingual Work and Translation; Natural Language Generation

Title Authors
Humans and language models diverge when predicting repeating text Aditya Vaidya, Javier Turek and Alexander Huth
Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum Urban Knuples, Diego Frassinelli and Sabine Schulte im Walde
ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian, Amin Banitalebi-Dehkordi and Yong Zhang
A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models Karin de Langis and Dongyeop Kang
PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments Daiki Asami and Saku Sugawara
A Minimal Approach for Natural Language Action Space in Text-based Games Dongwon Ryu, Meng Fang, Gholamreza Haffari, Shirui Pan and Ehsan Shareghi
Structural Ambiguity and its Disambiguation in Language Model Based Parsers: the Case of Dutch Clause Relativization Gijs Wijnholds and Michael Moortgat
Quirk or Palmer: A Comparative Study of Modal Verb Frameworks with Annotated Datasets Risako Owan, Maria Gini and Dongyeop Kang
Quantifying Information of Tokens for Simple and Flexible Simultaneous Machine Translation DongHyun Lee, Minkyung Park and Byung-Jun Lee
Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation Dama Sravani and Radhika Mamidi
Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization Ondrej Skopek, Rahul Aralikatte, Sian Gooding and Victor Carbune
Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages? Luke Gessler and Nathan Schneider
Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue Aron Molnar, Jaap Jumelet, Mario Giulianelli and Arabella Sinclair
On the utility of enhancing BERT syntactic bias with Token Reordering Pretraining Yassir El Mesbahi, Atif Mahmud, Abbas Ghaddar, Mehdi Rezagholizadeh, Phillippe Langlais and Prasanna Parthasarathi
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty Inar Timiryasov and Jean-Loup Tastet
BabyLM Challenge: Curriculum learning based on sentence complexity approximating language acquisition Miyu Oba, Akari Haga, Akiyo Fukatsu andYohei Oseki
Can training neural language models on a curriculum with developmentally plausible data improve alignment with human reading behavior? Aryaman Chobey, Oliver Smith, Anzi Wang and Grusha Prasad
CogMemLM: Human-Like Memory Mechanisms Improve Performance and Cognitive Plausibility of LLMs Lukas Thoma, Ivonne Weyers, Erion Çano, Stefan Schweter, Jutta L Mueller and Benjamin Roth
McGill BabyLM Shared Task Submission: The Effects of Data Formatting and Structural Biases Ziling Cheng, Rahul Aralikatte, Ian Porada, Cesare Spinoso-Di Piano and Jackie CK Cheung
On the effect of curriculum learning with developmental data for grammar acquisition Mattia Opper, J Morrison and Siddharth N
ToddlerBERTa: Exploiting BabyBERTa for Grammar Learning and Language Understanding Ömer Veysel Çağatan

Poster session 2:

Resources and Tools for Scientifically Motivated Research; Speech and Phonology; Syntax and Morphology; Theoretical Analysis and Interpretation of ML Models for NLP

Title Authors
How Fragile is Relation Extraction under Entity Replacements? Yiwei Wang, Bryan Hooi, Fei Wang, Yujun Cai, Yuxuan Liang, Wenxuan Zhou, Jing Tang, Manjuan Duan and Muhao Chen
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models Yuiga Wada, Kanta Kaneda and Komei Sugiura
MuLER: Detailed and Scalable Reference-based Evaluation Taelin Karidi, Leshem Choshen, Gal Patel and Omri Abend
The Impact of Familiarity on Naming Variation: A Study on Object Naming in Mandarin Chinese Yunke He, Xixian Liao, Jialing Liang and Gemma Boleda
PSST! Prosodic Speech Segmentation with Transformers Nathan Roll, Calbert Graham and Simon Todd
Alignment via Mutual Information Shinjini Ghosh, Yoon Kim, Ramon Fernandez Astudillo, Tahira Naseem and Jacob Andreas
Challenging the "One Single Vector per Token" Assumption Mathieu Dehouck
Strategies to Improve Low-Resource Agglutinative Languages Morphological Inflection Gulinigeer Abudouwaili, Wayit Ablez, Kahaerjiang Abiderexiti, Aishan Wumaier and Nian Yi
Exploring Transformers as Compact, Data-efficient Language Models Clayton Fields and Casey Kennington
Tree-shape Uncertainty for Analyzing the Inherent Branching Bias of Unsupervised Parsing Models Taiga Ishii and Yusuke Miyao
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State Koyena Pal, Jiuding Sun, Andrew Yuan, Byron Wallace and David Bau
Cross-Document Event Coreference Resolution: Instruct Humans or Instruct GPT? Jin Zhao, Nianwen Xue and Bonan Min
Implications of Annotation Artifacts in Edge Probing Test Datasets Sagnik Ray Choudhury and Jushaan Kalra
REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization MohammadReza GhasemiMadani and Pasquale Minervini
A surprisal oracle for active curriculum language modeling Xudong Hong, Sharid Loáiciga and Asad B. Sayeed
Baby’s CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models Zheyu Zhang, Han Yang, Bolei Ma, David Rügamer and Ercong Nie
Byte-ranked Curriculum Learning for BabyLM Strict-small Shared Task 2023 Justin DeBenedetto
ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation Jaap Jumelet, Michael Hanna, Marianne De Heer Kloots, Anna Langedijk, Charlotte Pouw and Oskar van der Wal
GPT-wee: How Small Can a Small Language Model Really Get? Bastian Bunzeck and Sina Zarrieß
Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings David Samuel
Tiny Language Models Enriched with Multimodal Knowledge from Multiplex Networks Clayton Fields, Osama Natouf, Andrew McMains, Catherine Henry and Casey Kennington