We explore the utilities of explicit negative examples in training neural language models. Negative examples here are incorrect words in a sentence, such as "barks" in "*The dogs barks". Neural language models are commonly trained only on positive examples, a set of sentences in the training data, but recent studies suggest that the models trained in this way are not capable of robustly handling complex syntactic constructions, such as long-distance agreement. In this paper, using English data, we first demonstrate that appropriately using negative examples about particular constructions (e.g., subject-verb agreement) will boost the model's robustness on them, with a negligible loss of perplexity. The key to our success is an additional margin loss between the log-likelihoods of a correct word and an incorrect word. We then provide a detailed analysis of the trained models. One of our findings is the difficulty of object-relative clauses for RNNs. We find that even with our direct learning signals the models still suffer from resolving agreement across an object-relative clause. Augmentation of training sentences involving the constructions somewhat helps, but the accuracy still does not reach the level of subject-relative clauses. Although not directly cognitively appealing, our method can be a tool to analyze the true architectural limitation of neural models on challenging linguistic constructions.
Computer Science Department, Bar Ilan University（巴伊兰大学计算机科学系）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
I assess the extent to which the recently introduced BERT model captures English syntactic phenomena, using (1) naturally-occurring subject-verb agreement stimuli; (2) "coloreless green ideas" subject-verb agreement stimuli, in which content words in natural sentences are randomly replaced with words sharing the same part-of-speech and inflection; and (3) manually crafted stimuli for subject-verb agreement and reflexive anaphora phenomena. The BERT model performs remarkably well on all cases.
PSL Research University（巴黎文理研究大学）；Bar Ilan University（巴伊兰大学）；CNRS（法国国家科学研究中心）；EHESS（法国社会科学高等研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered in complex sentences (Linzen et al., 2016). We test whether these errors are due to inherent limitations of the architecture or to the relatively indirect supervision provided by most agreement dependencies in a corpus. We trained a single RNN to perform both the agreement task and an additional task, either CCG supertagging or language modeling. Multi-task training led to significantly low…
Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS)（智能技术单一研究中心（CiTIUS））；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）
This paper explores the ability of Transformer models to capture subject-verb and noun-adjective agreement dependencies in Galician. We conduct a series of word prediction experiments in which we manipulate dependency length together with the presence of an attractor noun that acts as a lure. First, we evaluate the overall performance of the existing monolingual and multilingual models for Galician. Secondly, to observe the effects of the training process, we compare the different degrees of achievement of two monolingual BERT models at different training points. We also release their checkpoi…
John Hopkins University（约翰·霍普金斯大学）；Facebook AI Research（Facebook人工智能研究院）；Catalan Institute for Research and Advanced Studies（加泰罗尼亚研究与高等研究院）；Universitat Pompeu Fabra（庞培法布拉大学）
Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation. This success has sparked interest in probing whether these models are inducing human-like grammatical knowledge from the raw data they are exposed to, and, consequently, whether they can shed new light on long-standing debates concerning the innate structure necessary for language acquisition. In this article, we survey representative studies of the syntactic abilities of deep networks, and discuss the broader implications that this work …
Pompeu Fabra University（庞培法布拉大学）；Catalan Institute for Research and Advanced Studies (ICREA)（加泰罗尼亚研究与高级研究所）
Multilingual Transformer-based language models, usually pretrained on more than 100 languages, have been shown to achieve outstanding results in a wide range of cross-lingual transfer tasks. However, it remains unknown whether the optimization for different languages conditions the capacity of the models to generalize over syntactic structures, and how languages with syntactic phenomena of different complexity are affected. In this work, we explore the syntactic generalization capabilities of the monolingual and multilingual versions of BERT and RoBERTa. More specifically, we evaluate the synt…
Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Stockholm University（斯德哥尔摩大学）；MIT（麻省理工学院）
We present a method for classifying syntactic errors in learner language, namely errors whose correction alters the morphosyntactic structure of a sentence. The methodology builds on the established Universal Dependencies syntactic representation scheme, and provides complementary information to other error-classification systems. Unlike existing error classification methods, our method is applicable across languages, which we showcase by producing a detailed picture of syntactic errors in learner English and learner Russian. We further demonstrate the utility of the methodology for analyzing …
Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and they have been found to be useful for transfer learning and continual learning. We search for the reasons for the effectiveness of AT by contrasting vanilla and adversarially fine-tuned BERT models. We identify partial preservation of BERT's syntactic abilities during fine-tuning as the key to the success of AT. We observe that adversarially fine-tuned model…
CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions
Center for Language and Cognition (CLCG), University of Groningen（格罗宁根大学语言与认知中心）；Georgetown University（乔治城大学）；Computational Linguistics, Department of Linguistics, Bielefeld University（比勒菲尔德大学语言学系计算语言学）
Meta AI；MIT（麻省理工学院）；Johns Hopkins（约翰斯·霍普金斯大学）；Purdue University（普渡大学）
Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these judgements with just a single context-free sentence as input. This does not match language models' training regime, in which input sentences are always highly contextualized by the surrounding corpus. This mismatch raises an important question: how robust are models' syntactic judgements in different contexts? In this paper, we investigate the stability of lan…
Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during training. We address this issue by deploying a novel word-learning paradigm to test BERT's few-shot learning capabilities for two aspects of English verbs: alternations and classes of selectional preferences. For the former, we fine-tune BERT on a single frame in a verbal-alternation pair and ask whether the model expects the novel verb to occur in its sister frame…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Li Ka Shing Knowledge Institute, St Michael’s Hospital（李嘉诚知识研究所（圣迈克尔医院））；Surgical Safety Technologies（手术安全技术公司）
Recently, neural language models (LMs) have demonstrated impressive abilities in generating high-quality discourse. While many recent papers have analyzed the syntactic aspects encoded in LMs, there has been no analysis to date of the inter-sentential, rhetorical knowledge. In this paper, we propose a method that quantitatively evaluates the rhetorical capacities of neural LMs. We examine the capacities of neural LMs understanding the rhetoric of discourse by evaluating their abilities to encode a set of linguistic features derived from Rhetorical Structure Theory (RST). Our experiments show t…
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks. In this work, we tackle the task of unsupervised disentanglement between semantics and structure in neural language representations: we aim to learn a transformation of the contextualized vectors, that discards the lexical semantics, but keeps the structural information. To this end, we automatically generate groups of sentences which are structurally similar but semantically different, and use metric-learning approach to learn a transformation that emphasizes the str…
Merge-based syntax is mediated by distinct neurocognitive mechanisms: A clustering analysis of comprehension abilities in 84,000 individuals with language deficits across nine languages
Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
Peking University（北京大学）；Zhejiang University（浙江大学）；Beijing Language and Culture University（北京语言大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on regular languages and have close connections with counter languages. In this work, we systematically study the ability of Transformers to model such languages as well as the role of its individual components in doing so. We first provide a construction of Transformers for a subclass of counter languages, including well-studied languages such as n-ary Boolean…
Carnegie Mellon University（卡内基梅隆大学）；University of Utah（犹他大学）
Word embeddings have become a staple of several natural language processing tasks, yet much remains to be understood about their properties. In this work, we analyze word embeddings in terms of their principal components and arrive at a number of novel and counterintuitive observations. In particular, we characterize the utility of variance explained by the principal components as a proxy for downstream performance. Furthermore, through syntactic probing of the principal embedding space, we show that the syntactic information captured by a principal component does not correlate with the amount…
The utility of linguistic annotation in neural machine translation seemed to had been established in past papers. The experiments were however limited to recurrent sequence-to-sequence architectures and relatively small data settings. We focus on the state-of-the-art Transformer model and use comparably larger corpora. Specifically, we try to promote the knowledge of source-side syntax using multi-task learning either through simple data manipulation techniques or through a dedicated model component. In particular, we train one of Transformer attention heads to produce source-side dependency t…
ElementAI, a ServiceNow company（ElementAI，ServiceNow旗下公司）；University of Pennsylvania（宾夕法尼亚大学）；Polytechnique Montreal（蒙特利尔理工学院）；Mila（米拉研究所）
This paper explores the capabilities of current transformer-based language models for program evaluation of simple functional programming languages. We introduce a new program generation mechanism that allows control over syntactic sugar for semantically equivalent programs. T5 experiments reveal that neural functional program evaluation performs surprisingly well, achieving high 90% exact program match scores for most in-distribution and out-of-distribution tests. Using pretrained T5 weights has significant advantages over random initialization. We present and evaluate on three datasets to st…
National Institute of Informatics（国立信息学研究所）；SOKENDAI (The Graduate University for Advanced Studies)（综合研究大学院大学）；Centre for Speech Technology Research, University of Edinburgh（爱丁堡大学语音技术研究中心）
Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality speech directly from text or simple linguistic features such as phonemes. Unlike traditional pipeline TTS, the neural sequence-to-sequence TTS does not require manually annotated and complicated linguistic features such as part-of-speech tags and syntactic structures for system training. However, it must be carefully designed and well optimized so that it can implicitly extract useful linguistic features from the input features. In this paper we investigate under what conditions the neural sequence-to-sequence …
Counter machines have achieved a newfound relevance to the field of natural language processing (NLP): recent work suggests some strong-performing recurrent neural networks utilize their memory as counters. Thus, one potential way to understand the success of these networks is to revisit the theory of counter computation. Therefore, we study the abilities of real-time counter machines as formal grammars, focusing on formal properties that are relevant for NLP models. We first show that several variants of the counter machine converge to express the same class of formal languages. We also prove…
When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models
Blavatnik School of Computer Science, Tel Aviv University（特拉维夫大学布拉瓦尼克计算机科学学院）；Department of Linguistics, Tel Aviv University（特拉维夫大学语言学系）；Sagol School of Neuroscience, Tel Aviv University（特拉维夫大学萨戈尔神经科学学院）
Natural Language Processing (NLP) has become one of the leading application areas in the current Artificial Intelligence boom. Transfer learning has enabled large deep learning neural networks trained on the language modeling task to vastly improve performance in almost all downstream language tasks. Interestingly, when the language models are trained with data that includes software code, they demonstrate remarkable abilities in generating functioning computer code from natural language specifications. We argue that this creates a conundrum for the claim that eliminative neural models are a r…
University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）；The Ohio State University（俄亥俄州立大学）
Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality…
Large natural language models (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP tasks, but also in the nontraditional task of training a symbolic reasoning engine. We observe that these engines learn quickly and generalize in a natural way that reflects human intuition. For example, training such a system to model block-stacking might naturally generalize to stacking other types of objects because of structure in the real world that ha…
ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models
AI Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）；Nirma University（尼玛大学）；BITS Pilani（博拉理工学院皮拉尼校区）；IIIT Delhi（德里印度信息技术学院）；Amazon AI（亚马逊人工智能）；Stanford（斯坦福大学）；Amazon（亚马逊）
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer
School of Data Science, University of Science and Technology of China（中国科学技术大学数据科学学院）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；Tencent AI Lab（腾讯AI实验室）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）
