A Benchmark for Systematic Generalization in Grounded Language Understanding
University of Amsterdam（阿姆斯特丹大学）；Massachusetts Institute of Technology（麻省理工学院）；ICREA（加泰罗尼亚高等研究院）；Facebook Artificial Intelligence Research（脸书人工智能研究院）；Facebook AI Research（脸书人工智能研究院）；New York University（纽约大学）
Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake
Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret novel compositions. In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding. Going beyond a related benchmark that focused on syntactic aspects of generalization, gSCAN defines a language grounded in the states of a grid world, facilitating novel evaluations of acquiring linguistically motivated rules. For example, agents must understand how adjectives such as 'small' are interpreted relative to the current world state or how adverbs such as 'cautiously' combine with new verbs. We test a strong multi-modal baseline model and a state-of-the-art compositional method finding that, in most cases, they fail dramatically when generalization requires systematic compositional rules.
I2R, A*STAR Singapore（新加坡科技研究局信息通信研究院）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；Microsoft Research India（微软印度研究院）
Humans can reason compositionally whilst grounding language utterances to the real world. Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess whether neural models exhibit similar capabilities. In this work, we present a simple transformer-based model that outperforms specialized architectures on ReaSCAN and a modified version of gSCAN. On analyzing the task, we find that identifying the target location in the grid world is the main challenge for the models. Furthermore, we show that a particular split in ReaSCAN, which tests depth generalization, is unfair. …
The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing. Do the state-of-the-art Transformers and LSTM architectures implicitly encode for these biases? To answer this, we propose ORCHARD, a diagnostic dataset for systematically evaluating hierarchical reasoning in state-of-the-art neural sequence models. While there have been prior evaluation frameworks such as ListOps or Logical Inference, our work presents a novel and more natural setting where our models learn to reason with multiple …
We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposed to study systematic generalization for grounded language understanding. First, we study which aspects of the original benchmark can be solved by commonly used methods in multi-modal research. We find that a general-purpose Transformer-based model with cross-modal attention achieves strong performance on a majority of the gSCAN splits, surprisingly outperforming more specialized approaches from prior work. Furthermore, our analysis suggests that many of the remaining errors reveal the same fundamental challenge in syste…
Grounded Image Text Matching with Mismatched Relation Reasoning
ShanghaiTech University（上海科技大学）；Alibaba Group（阿里巴巴集团）；ByteDance Inc（字节跳动公司）；Shanghai Engineering Research Center of Intelligent Vision Imaging（上海智能视觉成像工程技术研究中心）
Recently, many datasets have been proposed to test the systematic generalization ability of neural networks. The companion baseline Transformers, typically trained with default hyper-parameters from standard tasks, are shown to fail dramatically. Here we demonstrate that by revisiting model configurations as basic as scaling of embeddings, early stopping, relative positional embedding, and Universal Transformer variants, we can drastically improve the performance of Transformers on systematic generalization. We report improvements on five popular datasets: SCAN, CFQ, PCFG, COGS, and Mathematic…
UC Santa Barbara（圣巴巴拉大学）；UC Santa Cruz（圣克鲁斯大学）；Google（谷歌公司）
A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings. To do this, it is critical to ensure that our evaluation protocols are correct, and benchmarks are reliable. In this work, we set forth to design a set of experiments to understand an important but often ignored problem in visually grounded language generation: given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models' performance? Empirically, we study sever…
Humans acquire language continually with much more limited access to data samples at a time, as compared to contemporary NLP systems. To study this human-like language acquisition ability, we present VisCOLL, a visually grounded language learning task, which simulates the continual acquisition of compositional phrases from streaming visual scenes. In the task, models are trained on a paired image-caption stream which has shifting object distribution; while being constantly evaluated by a visually-grounded masked language prediction task on held-out test sets. VisCOLL compounds the challenges o…
Element AI（元素人工智能公司）；Quebec Artificial Intelligence Institute (Mila)（魁北克人工智能研究所（米拉））；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Stanford University（斯坦福大学）
The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very high accuracies of around 97-99%. In this work, we study how systematic the generalization of such models is, that is to which extent they are capable of handling novel combinations of known linguistic constructs. To this end, we test models' understanding of referring expressions based on matching object properties (such as e.g. "another cube that is the same size as the brown …
Tel-Aviv University（特拉维夫大学）；Allen Institute for AI（艾伦人工智能研究所）
Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that t…
Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinations of known inputs, but less work has focused on generating novel combinations of known outputs. Here we focus on this latter "decode-side" form of generalization in the context of gSCAN, a synthetic benchmark for compositional generalization in grounded language understanding. We present Recursive Decoding (RD), a novel procedure for training and using seq2seq models, targeted towards decode-side generalization. R…
Children acquire language subconsciously by observing the surrounding world and listening to descriptions. They can discover the meaning of words even without explicit language knowledge, and generalize to novel compositions effortlessly. In this paper, we bring this ability to AI, by studying the task of Visually grounded Language Acquisition (VLA). We propose a multimodal transformer model augmented with a novel mechanism for analogical reasoning, which approximates novel compositions by learning semantic mapping and reasoning operations from previously seen compositions. Our proposed method…
The ability to perceive and reason about social interactions in the context of physical environments is core to human social intelligence and human-machine cooperation. However, no prior dataset or benchmark has systematically evaluated physically grounded perception of complex social interactions that go beyond short actions, such as high-fiving, or simple group activities, such as gathering. In this work, we create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions by including social concepts such as helping another ag…
Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to more complex train-test splits. We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism. Grounding enables the model to …
We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The ou…
gComm is a step towards developing a robust platform to foster research in grounded language acquisition in a more challenging and realistic setting. It comprises a 2-d grid environment with a set of agents (a stationary speaker and a mobile listener connected via a communication channel) exposed to a continuous array of tasks in a partially observable setting. The key to solving these tasks lies in agents developing linguistic abilities and utilizing them for efficiently exploring the environment. The speaker and listener have access to information provided in different modalities, i.e. the s…
Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Applications（深度学习技术及应用国家工程实验室）
We build a virtual agent for learning language in a 2D maze-like world. The agent sees images of the surrounding environment, listens to a virtual teacher, and takes actions to receive rewards. It interactively learns the teacher's language from scratch based on two language use cases: sentence-directed navigation and question answering. It learns simultaneously the visual representations of the world, the language, and the action control. By disentangling language grounding from other computational routines and sharing a concept detection function between language grounding and prediction, th…
Tel-Aviv University（特拉维夫大学）；University of California Irvine（加州大学欧文分校）；Allen Institute for AI（艾伦人工智能研究所）
While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to synthetic images. In this work, we propose COVR, a new test-bed for visually-grounded compositional generalization with real images. To create COVR, we use real images annotated with scene graphs, and propose an almost fully automatic procedure for generating question-answer pairs along with a set of context images. COVR focuses on questions that require complex reasoning, including higher-order operations such as quant…
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitly measures how well an agent is able to interpret novel linguistic commands grounded in vision, e.g., no…
University College London（伦敦大学学院）；New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）
Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling principles -- modularity and data augmentation -- affect systematic generalization of neural networks in grounded language learning. We analyze how large the vocabulary needs to be to achieve systematic generalization and how similar the augmented data needs to be to the problem at hand. Our findings show that even in the controlled setting of a synthetic benchmark…
Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning models fail dramatically even on tasks for which they are designed when the test set is systematically different from the training data. We hypothesize that explicitly modeling the relations between objects in their contexts while learning their representations will help achieve systematic generalization. Therefore, we propose a novel method that learns obj…
Enhancing NLP Robustness and Generalization through LLM-Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training
College of Natural Sciences, The University of Texas at Austin（德克萨斯大学奥斯汀分校自然科学学院）
Dept. of Psychology and Center for Data Science, New York University（纽约大学心理学系和数据科学中心）；Facebook Artificial Intelligence Research（Facebook人工智能研究院）
Humans can understand and produce new utterances effortlessly, thanks to their compositional skills. Once a person learns the meaning of a new verb "dax," he or she can immediately understand the meaning of "dax twice" or "sing and dax." In this paper, we introduce the SCAN domain, consisting of a set of simple compositional navigation commands paired with the corresponding action sequences. We then test the zero-shot generalization capabilities of a variety of recurrent neural networks (RNNs) trained on SCAN with sequence-to-sequence methods. We find that RNNs can make successful zero-shot ge…
We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines; in particular, we explore the emergence of semantic generalization from unsupervised dense representations outside of synthetic environments. A grounding domain, a denotation function and a composition function are learned from user data only. We show how the resulting semantics for noun phrases exhibits compositional properties while being fully learnable without any explicit labelling. We benchmark our grounded…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Alibaba Group（阿里巴巴集团）；Shanghai Jiao Tong University（上海交通大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）
Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to optimistic results. We revisit this controversial topic from the perspective of meaningful learning, an exceptional capability of humans to learn novel concepts by connecting them with known ones. We reassess the compositional skills of sequence-to-sequence models conditioned on the semantic links between new and old concepts. Our observations suggest that mod…
Mila, Université de Montréal（米拉，蒙特利尔大学）；AdeptMind Scholar（AdeptMind学者）；Element AI；University of Oregon（俄勒冈大学）；CIFAR（加拿大高等研究院）
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require background knowledge to be instantiated. We compare both types of models in how much they lend themselves to a particular form of systematic generalization. Using a synthetic VQA test, we evaluate which models are capable of reasoning about all possible object pairs after training on only a small subset of them. Our findings show that the generalization of modular models is much more…
Semantic parsing is the task of producing structured meaning representations for natural language sentences. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings. In this work, we show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. To this end we propose LAGr (Label Aligned Graphs), a general framework to produce semantic parses by inde…
Polytechnique Montréal（蒙特利尔综合理工学院）；McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）；ElementAI（元素人工智能公司）
We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization abilities on a logical reasoning task in natural language, which involves reasoning over relationships between entities grounded in first-order logical proofs. Specifically, we perform soft theorem-proving by leveraging TLMs to generate natural language proofs. We test the generated proofs for logical consistency, along with the accuracy of the final inference. We observe leng…
Facebook AI Research（脸书人工智能研究院）；New York University（纽约大学）
Systematic compositionality is the ability to recombine meaningful units with regular and predictable outcomes, and it's seen as key to humans' capacity for generalization in language. Recent work has studied systematic compositionality in modern seq2seq models using generalization to novel navigation instructions in a grounded environment as a probing tool, requiring models to quickly bootstrap the meaning of new words. We extend this framework here to settings where the model needs only to recombine well-trained functional words (such as "around" and "right") in novel contexts. Our findings …
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；University of Pennsylvania（宾夕法尼亚大学）
We introduce and implement a cognitively plausible model for learning from generic language, statements that express generalizations about members of a category and are an important aspect of concept development in language acquisition (Carlson & Pelletier, 1995; Gelman, 2009). We extend a computational framework designed to model grounded language acquisition by introducing the concept network. This new layer of abstraction enables the system to encode knowledge learned from generic statements and represent the associations between concepts learned by the system. Through three tasks that util…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；ServiceNow Research（ServiceNow研究院）
Semantic parsing is the task of producing a structured meaning representation for natural language utterances or questions. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings. In this work, we show that better systematic generalization can be achieved by producing the meaning representation (MR) directly as a graph and not as a sequence. To this end we propose LAGr, the Labeling Aligned Graphs algorithm that produces seman…
University of California, San Diego（加利福尼亚大学圣迭戈分校）；McGill University（麦吉尔大学）；Quebec Artificial Intelligence Institute (Mila)（魁北克人工智能研究所）；Element AI, a ServiceNow company（Element AI，ServiceNow旗下公司）
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. The first key idea in Edge Transformers is to associate vector states with every edge, that is, with every pair of input nodes -- as opposed to just every node, as it is done in the Transformer model. The second major innovation is a triangular attention mechanism tha…
My doctoral research focuses on understanding semantic knowledge in neural network models trained solely to predict natural language (referred to as language models, or LMs), by drawing on insights from the study of concepts and categories grounded in cognitive science. I propose a framework inspired by 'inductive reasoning,' a phenomenon that sheds light on how humans utilize background knowledge to make inductive leaps and generalize from new pieces of information about concepts and their properties. Drawing from experiments that study inductive reasoning, I propose to analyze semantic induc…
From Words to Worlds: Benchmarking Cross-Cultural Cultural Understanding in Machine Translation
Xinjiang Technical Institute of Physics \& Chemistry, Chinese Academy of Sciences Urumqi China；Xinjiang Technical Institute of Physics \& Chemistry, Chinese Academy of Sciences
Neural-Symbolic Recursive Machine for Systematic Generalization
National Key Laboratory of General Artificial Intelligence, BIGAI（北京智源人工智能研究院通用人工智能国家重点实验室）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；UCLA（加州大学洛杉矶分校）
University of Maryland, College Park（马里兰大学帕克分校）；Microsoft Research（微软研究院）
NLP models trained on text have been shown to reproduce human stereotypes, which can magnify harms to marginalized groups when systems are deployed at scale. We adapt the Agency-Belief-Communion (ABC) stereotype model of Koch et al. (2016) from social psychology as a framework for the systematic study and discovery of stereotypic group-trait associations in language models (LMs). We introduce the sensitivity test (SeT) for measuring stereotypical associations from language models. To evaluate SeT and other measures using the ABC model, we collect group-trait judgments from U.S.-based subjects …
Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework
Mila - Quebec AI Institute（魁北克人工智能研究所）；McGill University（麦吉尔大学）；University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）；Université de Sherbrooke（舍布鲁克大学）；Université de Montréal（蒙特利尔大学）
Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）
While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantia…
The University of Tokyo（东京大学）；RIKEN（理化学研究所）；Keio University（庆应义塾大学）；Tohoku University（东北大学）
Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in formal semantics. To investigate this issue, we propose a Systematic Generalization testbed based on Natural language Semantics (SyGNS), whose challenge is to map natural language sentences to multiple forms of scoped meaning representations, designed to account for various semantic phenomena. Using SyGNS, we test whether neural networks can systematically pa…
