8 citations · 25 across the 24 of their papers we have counts for
46 papers
TokEval: A Tokenizer Evaluation Suite
Clara Meister
Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attribut…
Explicit Boundary Markers for Subword Vocabularies
Sander Land, Clara Meister
Subword tokenizers represent many common words twice in space-using writing systems, once with a leading space and once without. The two entries have separate embeddings in models,…
LangMAP: A Language-Adaptive Approach to Tokenization
Clara Meister, Suchir Salhan, Andrzej Szablewski +3
Language-specific tokenizers improve tokenization quality and the downstream performance of models on those languages. However, using such a tokenizer comes at a cost: either a new…
What Language is This? Ask Your Tokenizer
Clara Meister, Ahmetcan Yavuz, Pietro Lesci +1
Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, an…
Back to Bytes: Revisiting Tokenization Through UTF-8
Amit Moryossef, Clara Meister, Pavel Stepachev +1
We present UTF8Tokenizer, a minimalist byte-level tokenizer that maps text exactly to IDs corresponding to the bytes underlying the text's UTF-8 encoding (e.g., byte x09 is token I…
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
Negar Foroutan, Clara Meister, Debjit Paul +4
Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor…
Causal Estimation of Tokenisation Bias
Pietro Lesci, Clara Meister, Thomas Hofmann +2
Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps…
Uncertainty-Aware Decoding with Minimum Bayes Risk
Nico Daheim, Clara Meister, Thomas Möllenhoff +1
Despite their outstanding performance in the majority of scenarios, contemporary language models still occasionally generate undesirable outputs, for example, hallucinated text. Wh…
Towards a Similarity-adjusted Surprisal Theory
Clara Meister, Mario Giulianelli, Tiago Pimentel
Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified as surprisal. Traditionally, surprisal th…
Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing?
Josef Jon
This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and pr…
Causal Estimation of Memorisation Profiles
Pietro Lesci, Clara Meister, Thomas Hofmann +2
Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work de…
How to Compute the Probability of a Word
Tiago Pimentel, Clara Meister
Language models (LMs) estimate a probability distribution over strings in a natural language; these distributions are crucial for computing perplexity and surprisal in linguistics…
The Role of -gram Smoothing in the Age of Neural Networks
Luca Malagutti, Andrius Buinovskij, Anej Svete +3
For nearly three decades, language models derived from the -gram assumption held the state of the art on the task. The key to their success lay in the application of various smo…
Revisiting the Optimality of Word Lengths
Tiago Pimentel, Clara Meister, Ethan Gotlieb Wilcox +2
Zipf (1935) posited that wordforms are optimized to minimize utterances' communicative costs. Under the assumption that cost is given by an utterance's length, he supported this cl…
Formal Aspects of Language Modeling
Ryan Cotterell, Anej Svete, Clara Meister +2
Large language models have become one of the most commonly deployed NLP inventions. In the past half-decade, their integration into core natural language processing tools has drama…
A Cross-Linguistic Pressure for Uniform Information Density in Word Order
Thomas Hikaru Clark, Clara Meister, Tiago Pimentel +4
While natural languages differ widely in both canonical word order and word order flexibility, their word orders still follow shared cross-linguistic statistical patterns, often at…
On the Efficacy of Sampling Adapters
Clara Meister, Tiago Pimentel, Luca Malagutti +2
Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate…
Testing the Predictions of Surprisal Theory in 11 Languages
Ethan Gotlieb Wilcox, Tiago Pimentel, Clara Meister +2
A fundamental result in psycholinguistics is that less predictable words take a longer time to process. One theoretical explanation for this finding is Surprisal Theory (Hale, 2001…
Tokenization and the Noiseless Channel
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi +3
Subword tokenization is a key part of many NLP pipelines. However, little is known about why some tokenizer and hyperparameter combinations lead to better downstream model performa…
A Formal Perspective on Byte-Pair Encoding
Vilém Zouhar, Clara Meister, Juan Luis Gastaldi +4
Byte-Pair Encoding (BPE) is a popular algorithm used for tokenizing data in NLP, despite being devised initially as a compression method. BPE appears to be a greedy algorithm at fa…
A Measure-Theoretic Characterization of Tight Language Models
Li Du, Lucas Torroba Hennigen, Tiago Pimentel +3
Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 o…
A Natural Bias for Language Generation Models
Clara Meister, Wojciech Stokowiec, Tiago Pimentel +3
After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, ma…
On the Effect of Anticipation on Reading Times
Tiago Pimentel, Clara Meister, Ethan G. Wilcox +2
Over the past two decades, numerous studies have demonstrated how less predictable (i.e., higher surprisal) words take more time to read. In general, these studies have implicitly…
Mutual Information Alleviates Hallucinations in Abstractive Summarization
Liam van der Poel, Ryan Cotterell, Clara Meister
Despite significant progress in the quality of language generated from abstractive summarization models, these models still exhibit the tendency to hallucinate, i.e., output conten…