Michael Hahn


2024

pdf bib
Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
Michael Hahn | Alexey Sorokin | Ritesh Kumar | Andreas Shcherbakov | Yulia Otmakhova | Jinrui Yang | Oleg Serikov | Priya Rani | Edoardo M. Ponti | Saliha Muradoğlu | Rena Gao | Ryan Cotterell | Ekaterina Vylomova
Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

pdf bib
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface
Siyu Tao | Lucia Donatelli | Michael Hahn
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

A substantial body of work has provided evidence that the lexicons of natural languages are organized to support efficient communication. However, existing work has largely focused on word-internal properties, such as Zipf’s observation that more frequent words are optimized in form to minimize communicative cost. Here, we investigate the hypothesis that efficient lexicon organization is also reflected in valency, or the combinations and orders of additional words and phrases a verb selects for in a sentence. We consider two measures of valency diversity for verbs: valency frame count (VFC), the number of distinct frames associated with a verb, and valency frame entropy (VFE), the average information content of frame selection associated with a verb. Using data from 79 languages, we provide evidence that more frequent verbs are associated with a greater diversity of valency frames, suggesting that the organization of valency is consistent with communicative efficiency principles. We discuss our findings in relation to classical findings such as Zipf’s meaning-frequency law and the principle of least effort, as well as implications for theories of valency and communicative efficiency principles.

pdf bib
Why are Sensitive Functions Hard for Transformers?
Michael Hahn | Mark Rofin
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Empirical studies have identified a range of learnability biases and limitations of transformers, such as a persistent difficulty in learning to compute simple formal languages such as PARITY, and a bias towards low-degree functions. However, theoretical understanding remains limited, with existing expressiveness theory either overpredicting or underpredicting realistic learning abilities. We prove that, under the transformer architecture, the loss landscape is constrained by the input-space sensitivity: Transformers whose output is sensitive to many parts of the input string inhabit isolated points in parameter space, leading to a low-sensitivity bias in generalization. We show theoretically and empirically that this theory unifies a broad array of empirical observations about the learning abilities and biases of transformers, such as their generalization bias towards low sensitivity and low degree, and difficulty in length generalization for PARITY. This shows that understanding transformers’ inductive biases requires studying not just their in-principle expressivity, but also their loss landscape.

2023

pdf bib
A Cross-Linguistic Pressure for Uniform Information Density in Word Order
Thomas Hikaru Clark | Clara Meister | Tiago Pimentel | Michael Hahn | Ryan Cotterell | Richard Futrell | Roger Levy
Transactions of the Association for Computational Linguistics, Volume 11

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 attributed to functional pressures. In the effort to identify these pressures, prior work has compared real and counterfactual word orders. Yet one functional pressure has been overlooked in such investigations: The uniform information density (UID) hypothesis, which holds that information should be spread evenly throughout an utterance. Here, we ask whether a pressure for UID may have influenced word order patterns cross-linguistically. To this end, we use computational models to test whether real orders lead to greater information uniformity than counterfactual orders. In our empirical study of 10 typologically diverse languages, we find that: (i) among SVO languages, real word orders consistently have greater uniformity than reverse word orders, and (ii) only linguistically implausible counterfactual orders consistently exceed the uniformity of real orders. These findings are compatible with a pressure for information uniformity in the development and usage of natural languages.1

2021

pdf bib
Sensitivity as a Complexity Measure for Sequence Classification Tasks
Michael Hahn | Dan Jurafsky | Richard Futrell
Transactions of the Association for Computational Linguistics, Volume 9

We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sensitivity. The sensitivity of a function, given a distribution over input sequences, quantifies the number of disjoint subsets of the input sequence that can each be individually changed to change the output. We argue that standard sequence classification methods are biased towards learning low-sensitivity functions, so that tasks requiring high sensitivity are more difficult. To that end, we show analytically that simple lexical classifiers can only express functions of bounded sensitivity, and we show empirically that low-sensitivity functions are easier to learn for LSTMs. We then estimate sensitivity on 15 NLP tasks, finding that sensitivity is higher on challenging tasks collected in GLUE than on simple text classification tasks, and that sensitivity predicts the performance both of simple lexical classifiers and of vanilla BiLSTMs without pretrained contextualized embeddings. Within a task, sensitivity predicts which inputs are hard for such simple models. Our results suggest that the success of massively pretrained contextual representations stems in part because they provide representations from which information can be extracted by low-sensitivity decoders.

pdf bib
An Information-Theoretic Characterization of Morphological Fusion
Neil Rathi | Michael Hahn | Richard Futrell
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Linguistic typology generally divides synthetic languages into groups based on their morphological fusion. However, this measure has long been thought to be best considered a matter of degree. We present an information-theoretic measure, called informational fusion, to quantify the degree of fusion of a given set of morphological features in a surface form, which naturally provides such a graded scale. Informational fusion is able to encapsulate not only concatenative, but also nonconcatenative morphological systems (e.g. Arabic), abstracting away from any notions of morpheme segmentation. We then show, on a sample of twenty-one languages, that our measure recapitulates the usual linguistic classifications for concatenative systems, and provides new measures for nonconcatenative ones. We also evaluate the long-standing hypotheses that more frequent forms are more fusional, and that paradigm size anticorrelates with degree of fusion. We do not find evidence for the idea that languages have characteristic levels of fusion; rather, the degree of fusion varies across part-of-speech within languages.

2020

pdf bib
Crosslinguistic Word Orders Enable an Efficient Tradeoff of Memory and Surprisal
Michael Hahn | Richard Futrell
Proceedings of the Society for Computation in Linguistics 2020

pdf bib
Theoretical Limitations of Self-Attention in Neural Sequence Models
Michael Hahn
Transactions of the Association for Computational Linguistics, Volume 8

Transformers are emerging as the new workhorse of NLP, showing great success across tasks. Unlike LSTMs, transformers process input sequences entirely through self-attention. Previous work has suggested that the computational capabilities of self-attention to process hierarchical structures are limited. In this work, we mathematically investigate the computational power of self-attention to model formal languages. Across both soft and hard attention, we show strong theoretical limitations of the computational abilities of self-attention, finding that it cannot model periodic finite-state languages, nor hierarchical structure, unless the number of layers or heads increases with input length. These limitations seem surprising given the practical success of self-attention and the prominent role assigned to hierarchical structure in linguistics, suggesting that natural language can be approximated well with models that are too weak for the formal languages typically assumed in theoretical linguistics.

pdf bib
RNNs can generate bounded hierarchical languages with optimal memory
John Hewitt | Michael Hahn | Surya Ganguli | Percy Liang | Christopher D. Manning
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Recurrent neural networks empirically generate natural language with high syntactic fidelity. However, their success is not well-understood theoretically. We provide theoretical insight into this success, proving in a finite-precision setting that RNNs can efficiently generate bounded hierarchical languages that reflect the scaffolding of natural language syntax. We introduce Dyck-(k,m), the language of well-nested brackets (of k types) and m-bounded nesting depth, reflecting the bounded memory needs and long-distance dependencies of natural language syntax. The best known results use O(km2) memory (hidden units) to generate these languages. We prove that an RNN with O(m log k) hidden units suffices, an exponential reduction in memory, by an explicit construction. Finally, we show that no algorithm, even with unbounded computation, can suffice with o(m log k) hidden units.

2019

pdf bib
Tabula Nearly Rasa: Probing the Linguistic Knowledge of Character-level Neural Language Models Trained on Unsegmented Text
Michael Hahn | Marco Baroni
Transactions of the Association for Computational Linguistics, Volume 7

Recurrent neural networks (RNNs) have reached striking performance in many natural language processing tasks. This has renewed interest in whether these generic sequence processing devices are inducing genuine linguistic knowledge. Nearly all current analytical studies, however, initialize the RNNs with a vocabulary of known words, and feed them tokenized input during training. We present a multi-lingual study of the linguistic knowledge encoded in RNNs trained as character-level language models, on input data with word boundaries removed. These networks face a tougher and more cognitively realistic task, having to discover any useful linguistic unit from scratch based on input statistics. The results show that our “near tabula rasa” RNNs are mostly able to solve morphological, syntactic and semantic tasks that intuitively presuppose word-level knowledge, and indeed they learned, to some extent, to track word boundaries. Our study opens the door to speculations about the necessity of an explicit, rigid word lexicon in language learning and usage.

2016

pdf bib
Modeling Human Reading with Neural Attention
Michael Hahn | Frank Keller
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2013

pdf bib
CoMeT: Integrating different levels of linguistic modeling for meaning assessment
Niels Ott | Ramon Ziai | Michael Hahn | Detmar Meurers
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

2012

pdf bib
Evaluating the Meaning of Answers to Reading Comprehension Questions: A Semantics-Based Approach
Michael Hahn | Detmar Meurers
Proceedings of the Seventh Workshop on Building Educational Applications Using NLP