How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive biases to a neural network model; such a model can then be used to empirically explore the effects of those inductive biases. This framework disentangles universal inductive biases, which are encoded in the initial values of a neural network's parameters, from non-universal factors, which the neural network must learn from data in a given language. The initial state that encodes the inductive biases is found with meta-learning, a technique through which a model discovers how to acquire new languages more easily via exposure to many possible languages. By controlling the properties of the languages that are used during meta-learning, we can control the inductive biases that meta-learning imparts. We demonstrate this framework with a case study based on syllable structure. First, we specify the inductive biases that we intend to give our model, and then we translate those inductive biases into a space of languages from which a model can meta-learn. Finally, using existing analysis techniques, we verify that our approach has imparted the linguistic inductive biases that it was intended to impart.
Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain. However, further works revealed severe inadequacies between theory and practice: we consolidate this analysis and confirm that imposing domain invariance on features is neither necessary nor sufficient to obtain low target risk. We instead argue that successful deep domain adaptation rely largely on hidden inductive biases found in the common practice, such as model pre-training or design of …
MIT（麻省理工学院）；Stanford University（斯坦福大学）；National University of Singapore（新加坡国立大学）
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatically discovering these useful symmetries holds the potential to greatly improve the performance of ML systems, but still remains a challenge. In this work, we focus on sequential prediction problems and take inspiration from Noether's theorem to reduce the problem of finding inductive biases to meta-l…
Learning with limited data is one of the biggest problems of machine learning. Current approaches to this issue consist in learning general representations from huge amounts of data before fine-tuning the model on a small dataset of interest. While such technique, coined transfer learning, is very effective in domains such as computer vision or natural langage processing, it does not yet solve common problems of deep learning such as model interpretability or the overall need for data. This thesis explores a different answer to the problem of learning expressive models in data constrained sett…
New York University（纽约大学）；UC San Diego（加州大学圣迭戈分校）；Amazon, Cambridge（亚马逊剑桥）
The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings. We study the inductive biases of linearizations of neural networks, which we show to be surprisingly good summaries of the full network functions. Inspired by this finding, we propose a technique for embedding these inductive biases into Gaussian processes through a kernel designed from the Jacobian of the network. In this setting, domain adaptation takes the form of interpretable posterior inference, with accompanying uncertainty estimation. This inference is analytic and f…
The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
East China Normal University（东华大学）；Information Engineering University（信息工程大学）；Zhengzhou University（郑州大学）
Pre-trained contextual representations have led to dramatic performance improvements on a range of downstream tasks. Such performance improvements have motivated researchers to quantify and understand the linguistic information encoded in these representations. In general, researchers quantify the amount of linguistic information through probing, an endeavor which consists of training a supervised model to predict a linguistic property directly from the contextual representations. Unfortunately, this definition of probing has been subject to extensive criticism in the literature, and has been …
People use rich prior knowledge about the world in order to efficiently learn new concepts. These priors - also known as "inductive biases" - pertain to the space of internal models considered by a learner, and they help the learner make inferences that go beyond the observed data. A recent study found that deep neural networks optimized for object recognition develop the shape bias (Ritter et al., 2017), an inductive bias possessed by children that plays an important role in early word learning. However, these networks use unrealistically large quantities of training data, and the conditions …
Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication
Leiden Institute of Advanced Computer Science, Leiden University, Netherlands（莱顿高级计算机科学研究所，莱顿大学，荷兰）；School of Computing, University of Kent, United Kingdom（计算学院，肯特大学，英国）；Cognitive Psychology Unit, Institute of Psychology, Leiden, the Netherlands（认知心理学单元，心理学研究所，莱顿，荷兰）
University of Cambridge（剑桥大学）；MILA（蒙特利尔学习算法研究所）；McGill University（麦吉尔大学）；Polytechnique Montréal（蒙特利尔综合理工学院）；ServiceNow（ServiceNow公司）
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investigate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.
Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by investigating how popular seq2seq learners generalize in tasks that have high ambiguity in the training data. We use SCAN and three new tasks to study learners' preferences for memorization, arithmetic, hierarchical, and compositional reasoning. Further, we connect to Solomonoff's theory of induction and propose to use description length as a principled and sensitive measure of inductive biases. In our experimental study…
Carnegie Mellon University（卡内基梅隆大学）；University of Haifa（海法大学）；University of Pittsburgh（匹兹堡大学）；University of Washington（华盛顿大学）
Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models with speaker information in a controlled, educated way can guide them to pick up on relevant inductive biases. For the speaker-driven task of predicting code-switching points in English--Spanish bilingual dialogues, we show that adding sociolinguistically-grounded speaker features as prepended prompts significantly improves accuracy. We find that by adding i…
University of Cambridge（剑桥大学）；ETH Zürich（苏黎世联邦理工学院）
Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases has proved complicated due to the many variables that appear in the experimental setup. Languages vary in many typological dimensions, and it is difficult to single out one or two to investigate without the others acting as confounders. We propose a novel method for investigating the inductive biases of language models using artificial languages. These lang…
We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended envir…
Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate which architectural factors affect the generalization behavior of neural sequence-to-sequence models trained on two syntactic tasks, English question formation and English tense reinflection. For both tasks, the training set is consistent with a generalization based on hierarchical structure and a generalization based on linear order. All architectural factor…
The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult speaker. To apply a similar approach to analyze neural language models (NLM), it is first necessary to establish that different models are similar enough in the generalizations they make. In this paper, we show that NLMs with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. These findings suggest that there is some mutual i…
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented through a special attention mask and deterministic transformation of the linearized tree. We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics. Additionally, we find that the recursive syntactic composition bottleneck which repr…
CENIDET（墨西哥国家数字教育技术中心）；COLMEX（墨西哥学院）；IIM（印度管理研究所）；Université de Montréal（蒙特利尔大学）；EBSI（图书馆与信息科学学院）；Université d’Avignon（阿维尼翁大学）；LIA（阿维尼翁计算机科学实验室）
This work aims to evaluate the ability that both probabilistic and state-of-the-art vector space modeling (VSM) methods provide to well known machine learning algorithms to identify social network documents to be classified as aggressive, gender biased or communally charged. To this end, an exploratory stage was performed first in order to find relevant settings to test, i.e. by using training and development samples, we trained multiple algorithms using multiple vector space modeling and probabilistic methods and discarded the less informative configurations. These systems were submitted to t…
Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Mila & Université de Montréal（Mila与蒙特利尔大学）；Noah’s Ark Lab（Noah’s Ark实验室）；Advanced Micro Devices；Chandar Research Lab（Chandar研究实验室）；Polytechnique Montréal（蒙特利尔理工学院）；CIFAR AI Chair（CIFAR人工智能主席）
A Predictive Model of Digital Information Engagement: Forecasting User Engagement With English Words by Incorporating Cognitive Biases, Computational Linguistics and Natural Language Processing
State University of New York at Albany（纽约州立大学奥尔巴尼分校）；Google（谷歌公司）
We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains. Recent theories have suggested that pretrained language models acquire useful inductive biases through masks that implicitly act as cloze reductions for downstream tasks. While appealing, we show that the success of the random masking strategy used in practice cannot be explained by such cloze-like masks alone. We construct cloze-like masks using task-specific lexicons for three different classification datasets and show that the majority of pretrained …
A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic generalizations. We hypothesized that competing linguistic processes within a language, rather than just non-linguistic model biases, could obscure underlying linguistic knowledge. We tested this claim by exploring a single phenomenon in four languages: English, Chinese, Spanish, and Italian. While human behavior has been found to be similar across languages, we fi…
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）
How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on subject-verb agreement prediction) are complicated by the fact that any two languages differ in multiple typological properties, as well as by differences in training corpus. We propose a paradigm that addresses these issues: we create synthetic versions of English, which differ from English in one or more typological parameters, and generate corpora for those langu…
University of Cambridge（剑桥大学）；Google（谷歌）；Kazan Federal University（喀山联邦大学）；ETH Zürich（苏黎世联邦理工学院）；Harvard University（哈佛大学）；MPI for Evolutionary Anthropology（马克斯·普朗克进化人类学研究所）；HSE University（高等经济大学）
This work presents an information-theoretic operationalisation of cross-linguistic non-arbitrariness. It is not a new idea that there are small, cross-linguistic associations between the forms and meanings of words. For instance, it has been claimed (Blasi et al., 2016) that the word for "tongue" is more likely than chance to contain the phone [l]. By controlling for the influence of language family and geographic proximity within a very large concept-aligned, cross-lingual lexicon, we extend methods previously used to detect within language non-arbitrariness (Pimentel et al., 2019) to measure…
Kempelen Institute of Intelligent Technologies（凯姆佩伦智能技术研究所）
This position paper discusses the problem of multilingual evaluation. Using simple statistics, such as average language performance, might inject linguistic biases in favor of dominant language families into evaluation methodology. We argue that a qualitative analysis informed by comparative linguistics is needed for multilingual results to detect this kind of bias. We show in our case study that results in published works can indeed be linguistically biased and we demonstrate that visualization based on URIEL typological database can detect it.
Large language models (LMs) have rapidly become a mainstay in Natural Language Processing. These models are known to acquire rich linguistic knowledge from training on large amounts of text. In this paper, we investigate if pre-training on text also confers these models with helpful `inductive biases' for non-linguistic reasoning. On a set of 19 diverse non-linguistic tasks involving quantitative computations, recognizing regular expressions and reasoning over strings. We find that pretrained models significantly outperform comparable non-pretrained neural models. This remains true also in exp…
Despite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and especially towards the development of universal sentence encoders that could provide inductive transfer to a wide variety of downstream tasks. In this work, we perform a comprehensive evaluation of recent methods using a wide variety of downstream and linguistic feature probing tasks. We show that a simple approach using bag-of-words with a recent…
Tilburg University（蒂尔堡大学）；University of Maryland, College Park（马里兰大学帕克分校）
Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been examined with respect to specific phenomena, such as gender bias. In this work, we go beyond the study of gender in MT and investigate how bias amplification might affect language in a broader sense. We hypothesize that the 'algorithmic bias', i.e. an exacerbation of frequently observed patterns in combination with a loss of less frequent ones, not only exace…
One reason pretraining on self-supervised linguistic tasks is effective is that it teaches models features that are helpful for language understanding. However, we want pretrained models to learn not only to represent linguistic features, but also to use those features preferentially during fine-turning. With this goal in mind, we introduce a new English-language diagnostic set called MSGS (the Mixed Signals Generalization Set), which consists of 20 ambiguous binary classification tasks that we use to test whether a pretrained model prefers linguistic or surface generalizations during fine-tun…
Morphological analysis is an important subtask in text-to-speech conversion, hyphenation, and other language engineering tasks. The traditional approach to performing morphological analysis is to combine a morpheme lexicon, sets of (linguistic) rules, and heuristics to find a most probable analysis. In contrast we present an inductive learning approach in which morphological analysis is reformulated as a segmentation task. We report on a number of experiments in which five inductive learning algorithms are applied to three variations of the task of morphological analysis. Results show (i) that…
Facebook AI Research（Facebook AI研究院）；Université de Paris（巴黎大学）；CoML, ENS/CNRS/EHESS/INRIA/PSL University（计算语言学实验室，巴黎高等师范学院/法国国家科学研究中心/法国社会科学高等研究院/法国国家信息与自动化研究所/巴黎文理研究大学）；CRI, Département Frontières du Vivant et de l’Apprendre, IIFR, Université de Paris（认知研究所，生命与学习前沿系，法国医学研究院，巴黎大学）；École normale supérieure, PSL University, CNRS（巴黎高等师范学院，巴黎文理研究大学，法国国家科学研究中心）
Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for speech-specific processes. To test this hypothesis, we compare i) five types of deep neural networks to ii) human brain responses elicited by spoken sentences and recorded in 102 Dutch subjects using functional Magnetic Resonance Imaging (fMRI). Each network was either trained on an acoustics scene classification, a speech-to-text task (based on Bengali, English, or Dutch), or not trained. The similarity between eac…
