We introduce **string2string**, an open-source library that offers a comprehensive suite of efficient algorithms for a broad range of string-to-string problems. It includes traditional algorithmic solutions as well as recent advanced neural approaches to tackle various problems in string alignment, distance measurement, lexical and semantic search, and similarity analysis�along with several helpful visualization tools and metrics to facilitate the interpretation and analysis of these methods. Notable algorithms featured in the library include the Smith-Waterman algorithm for pairwise local alignment, the Hirschberg algorithm for global alignment, the Wagner-Fischer algorithm for edit distance, BARTScore and BERTScore for similarity analysis, the Knuth-Morris-Pratt algorithm for lexical search, and Faiss for semantic search. In addition, it wraps existing efficient and widely-used implementations of certain frameworks and metrics, such as sacreBLEU and ROUGE. Overall, the library aims to provide extensive coverage and increased flexibility in comparison to existing libraries for strings. It can be used for many downstream applications, tasks, and problems in natural-language processing, bioinformatics, and computational social sciences. It is implemented in Python, easily installable via pip, and accessible through a simple API. Source code, documentation, and tutorials are all available on our GitHub page: https://github.com/stanfordnlp/string2string* Documentation: https://string2string.readthedocs.io/en/latest/* GitHub page: https://github.com/stanfordnlp/string2string* Short video: https://drive.google.com/file/d/1IT-pBACDVUoEHewk__5Pz5mU5oAMq5k_/view?usp=sharing

Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the models accomplish this behavior, this study applies causal mediation analysis to pre-trained neural language models. We investigate the magnitude of models’ preferences for grammatical inflections, as well as whether neurons process subject-verb agreement similarly across sentences with different syntactic structures. We uncover similarities and differences across architectures and model sizes—notably, that larger models do not necessarily learn stronger preferences. We also observe two distinct mechanisms for producing subject-verb agreement depending on the syntactic structure of the input sentence. Finally, we find that language models rely on similar sets of neurons when given sentences with similar syntactic structure.

Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models. More recent methods have improved performance by discarding these features and utilizing deep learning models. However, it is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. This paper combines these two approaches with the goal of improving overall model performance and addressing this question. Evaluating on two large readability corpora, we find that, given sufficient training data, augmenting deep learning models with linguistically motivated features does not improve state-of-the-art performance. Our results provide preliminary evidence for the hypothesis that the state-of-the-art deep learning models represent linguistic features of the text related to readability. Future research on the nature of representations formed in these models can shed light on the learned features and their relations to linguistically motivated ones hypothesized in traditional approaches.

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in dialog. In this study, we analyze the internal representations learned by neural open-domain dialog systems and evaluate the quality of these representations for learning basic conversational skills. Our results suggest that standard open-domain dialog systems struggle with answering questions, inferring contradiction, and determining the topic of conversation, among other tasks. We also find that the dyadic, turn-taking nature of dialog is not fully leveraged by these models. By exploring these limitations, we highlight the need for additional research into architectures and training methods that can better capture high-level information about dialog.

Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial learning can be used in NLI to encourage models to learn representations free of hypothesis-only biases. Our analyses indicate that the representations learned via adversarial learning may be less biased, with only small drops in NLI accuracy.

Natural Language Inference (NLI) datasets often contain hypothesis-only biases—artifacts that allow models to achieve non-trivial performance without learning whether a premise entails a hypothesis. We propose two probabilistic methods to build models that are more robust to such biases and better transfer across datasets. In contrast to standard approaches to NLI, our methods predict the probability of a premise given a hypothesis and NLI label, discouraging models from ignoring the premise. We evaluate our methods on synthetic and existing NLI datasets by training on datasets containing biases and testing on datasets containing no (or different) hypothesis-only biases. Our results indicate that these methods can make NLI models more robust to dataset-specific artifacts, transferring better than a baseline architecture in 9 out of 12 NLI datasets. Additionally, we provide an extensive analysis of the interplay of our methods with known biases in NLI datasets, as well as the effects of encouraging models to ignore biases and fine-tuning on target datasets.

In this paper, we systematically assess the ability of standard recurrent networks to perform dynamic counting and to encode hierarchical representations. All the neural models in our experiments are designed to be small-sized networks both to prevent them from memorizing the training sets and to visualize and interpret their behaviour at test time. Our results demonstrate that the Long Short-Term Memory (LSTM) networks can learn to recognize the well-balanced parenthesis language (Dyck-1) and the shuffles of multiple Dyck-1 languages, each defined over different parenthesis-pairs, by emulating simple real-time k-counter machines. To the best of our knowledge, this work is the first study to introduce the shuffle languages to analyze the computational power of neural networks. We also show that a single-layer LSTM with only one hidden unit is practically sufficient for recognizing the Dyck-1 language. However, none of our recurrent networks was able to yield a good performance on the Dyck-2 language learning task, which requires a model to have a stack-like mechanism for recognition.

While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furthermore, we show that this approach scales to real data sets and achieves strong performance nearing that of encoder-decoder text generation models.

Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records. In this work, we suggest a slightly more difficult data-to-text generation task, and investigate how effective current approaches are on this task. In particular, we introduce a new, large-scale corpus of data records paired with descriptive documents, propose a series of extractive evaluation methods for analyzing performance, and obtain baseline results using current neural generation methods. Experiments show that these models produce fluent text, but fail to convincingly approximate human-generated documents. Moreover, even templated baselines exceed the performance of these neural models on some metrics, though copy- and reconstruction-based extensions lead to noticeable improvements.

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches. Our strongest sequence-to-sequence model improves over our strongest phrase-based statistical machine translation model, with access to the same data, by 6 M2 (0.5 GLEU) points. Additionally, in the data environment of the standard CoNLL-2014 setup, we demonstrate that modeling (and tuning against) diffs yields similar or better M2 scores with simpler models and/or significantly less data than previous sequence-to-sequence approaches.

A major challenge in the field of automatic recognition of emotion and affect in speech is the subjective nature of affect labels. The most common approach to acquiring affect labels is to ask a panel of listeners to rate a corpus of spoken utterances along one or more dimensions of interest. For applications ranging from educational technology to voice search to dictation, a speaker’s level of certainty is a primary dimension of interest. In such applications, we would like to know the speaker’s actual level of certainty, but past research has only revealed listeners’ perception of the speaker’s level of certainty. In this paper, we present a method for eliciting spoken utterances using stimuli that we design such that they have a quantitative, crowdsourced legibility score. While we cannot control a speaker’s actual internal level of certainty, the use of these stimuli provides a better estimate of internal certainty compared to existing speech corpora. The Harvard Uncertainty Speech Corpus, containing speech data, certainty annotations, and prosodic features, is made available to the research community.

The more expressive and flexible a base formalism for machine translation is, the less efficient parsing of it will be. However, even among formalisms with the same parse complexity, some formalisms better realize the desired characteristics for machine translation formalisms than others. We introduce a particular formalism, probabilistic synchronous tree-insertion grammar (PSTIG) that we argue satisfies the desiderata optimally within the class of formalisms that can be parsed no less efficiently than context-free grammars and demonstrate that it outperforms state-of-the-art word-based and phrase-based finite-state translation models on training and test data taken from the EuroParl corpus (Koehn, 2005). We then argue that a higher level of translation quality can be achieved by hybridizing our in- duced model with elementary structures produced using supervised techniques such as those of Groves et al. (2004).

We present a new formalism, partially ordered multiset context-free grammars (poms-CFG), along with an Earley-style parsing algorithm. The formalism, which can be thought of as a generalization of context-free grammars with partially ordered right-hand sides, is of interest in its own right, and also as infrastructure for obtaining tighter complexity bounds for more expressive context-free formalisms intended to express free or multiple word-order, such as ID/LP grammars. We reduce ID/LP grammars to poms-grammars, thereby getting finer-grained bounds on the parsing complexity of ID/LP grammars. We argue that in practice, the width of attested ID/LP grammars is small, yielding effectively polynomial time complexity for ID/LP grammar parsing.