Stuart M. Shieber

Mirac Suzgun, Stuart M. Shieber, Dan Jurafsky · stanford

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-Fisher algorithm for edit distance, BARTScore and BERTScore for similarity analysis, the Knuth-Morris-Pratt algorithm for lexical search, and Faiss for semantic search. Besides, it wraps existing efficient and widely-used implementations of certain frameworks and metrics, such as sacreBLEU and ROUGE, whenever it is appropriate and suitable. 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.

Yuntian Deng, Kiran Prasad, Roland Fernandez et al.

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason effectively, it may be that LMs could reason more effectively with some intermediate computation that is not in natural language. In this work, we explore an alternative reasoning approach: instead of explicitly producing the chain of thought reasoning steps, we use the language model's internal hidden states to perform implicit reasoning. The implicit reasoning steps are distilled from a teacher model trained on explicit chain-of-thought reasoning, and instead of doing reasoning "horizontally" by producing intermediate words one-by-one, we distill it such that the reasoning happens "vertically" among the hidden states in different layers. We conduct experiments on a multi-digit multiplication task and a grade school math problem dataset and find that this approach enables solving tasks previously not solvable without explicit chain-of-thought, at a speed comparable to no chain-of-thought.

Mirac Suzgun, Luke Melas-Kyriazi, Suproteem K. Sarkar et al.

Innovation is a major driver of economic and social development, and information about many kinds of innovation is embedded in semi-structured data from patents and patent applications. Although the impact and novelty of innovations expressed in patent data are difficult to measure through traditional means, ML offers a promising set of techniques for evaluating novelty, summarizing contributions, and embedding semantics. In this paper, we introduce the Harvard USPTO Patent Dataset (HUPD), a large-scale, well-structured, and multi-purpose corpus of English-language patent applications filed to the United States Patent and Trademark Office (USPTO) between 2004 and 2018. With more than 4.5 million patent documents, HUPD is two to three times larger than comparable corpora. Unlike previously proposed patent datasets in NLP, HUPD contains the inventor-submitted versions of patent applications--not the final versions of granted patents--thereby allowing us to study patentability at the time of filing using NLP methods for the first time. It is also novel in its inclusion of rich structured metadata alongside the text of patent filings: By providing each application's metadata along with all of its text fields, the dataset enables researchers to perform new sets of NLP tasks that leverage variation in structured covariates. As a case study on the types of research HUPD makes possible, we introduce a new task to the NLP community--namely, binary classification of patent decisions. We additionally show the structured metadata provided in the dataset enables us to conduct explicit studies of concept shifts for this task. Finally, we demonstrate how HUPD can be used for three additional tasks: multi-class classification of patent subject areas, language modeling, and summarization.

Yuntian Deng, Yejin Choi, Stuart Shieber

When leveraging language models for reasoning tasks, generating explicit chain-of-thought (CoT) steps often proves essential for achieving high accuracy in final outputs. In this paper, we investigate if models can be taught to internalize these CoT steps. To this end, we propose a simple yet effective method for internalizing CoT steps: starting with a model trained for explicit CoT reasoning, we gradually remove the intermediate steps and finetune the model. This process allows the model to internalize the intermediate reasoning steps, thus simplifying the reasoning process while maintaining high performance. Our approach enables a GPT-2 Small model to solve 9-by-9 multiplication with up to 99% accuracy, whereas standard training cannot solve beyond 4-by-4 multiplication. Furthermore, our method proves effective on larger language models, such as Mistral 7B, achieving over 50% accuracy on GSM8K without producing any intermediate steps.

Xiaoyan Bai, Itamar Pres, Yuntian Deng et al.

Language models are increasingly capable, yet still fail at a seemingly simple task of multi-digit multiplication. In this work, we study why, by reverse-engineering a model that successfully learns multiplication via \emph{implicit chain-of-thought}, and report three findings: (1) Evidence of long-range structure: Logit attributions and linear probes indicate that the model encodes the necessary long-range dependencies for multi-digit multiplication. (2) Mechanism: the model encodes long-range dependencies using attention to construct a directed acyclic graph to ``cache'' and ``retrieve'' pairwise partial products. (3) Geometry: the model implements partial products in attention heads by forming Minkowski sums between pairs of digits, and digits are represented using a Fourier basis, both of which are intuitive and efficient representations that the standard fine-tuning model lacks. With these insights, we revisit the learning dynamics of standard fine-tuning and find that the model converges to a local optimum that lacks the required long-range dependencies. We further validate this understanding by introducing an auxiliary loss that predicts the ``running sum'' via a linear regression probe, which provides an inductive bias that enables the model to successfully learn multi-digit multiplication. In summary, by reverse-engineering the mechanisms of an implicit chain-of-thought model we uncover a pitfall for learning long-range dependencies in Transformers and provide an example of how the correct inductive bias can address this issue.

Matthew Finlayson, Aaron Mueller, Sebastian Gehrmann et al.

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.

Abdelrhman Saleh, Tovly Deutsch, Stephen Casper et al.

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.

Tovly Deutsch, Masoud Jasbi, Stuart Shieber

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.

Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov et al.

We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-based mechanisms. We provide the first demonstration of neural networks recognizing the generalized Dyck languages, which express the core of what it means to be a language with hierarchical structure. Our memory-augmented architectures are easy to train in an end-to-end fashion and can learn the Dyck languages over as many as six parenthesis-pairs, in addition to two deterministic palindrome languages and the string-reversal transduction task, by emulating pushdown automata. Our experiments highlight the increased modeling capacity of memory-augmented models over simple RNNs, while inflecting our understanding of the limitations of these models.

Yonatan Belinkov, Adam Poliak, Stuart M. Shieber et al.

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.

Yonatan Belinkov, Adam Poliak, Stuart M. Shieber et al.

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.

Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov et al.

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.

Mirac Suzgun, Yonatan Belinkov, Stuart M. Shieber

Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established themselves as a dominant model for language processing. Yet, there still remains an uncertainty regarding their language learning capabilities. In this paper, we empirically evaluate the inductive learning capabilities of Long Short-Term Memory networks, a popular extension of simple RNNs, to learn simple formal languages, in particular $a^nb^n$, $a^nb^nc^n$, and $a^nb^nc^nd^n$. We investigate the influence of various aspects of learning, such as training data regimes and model capacity, on the generalization to unobserved samples. We find striking differences in model performances under different training settings and highlight the need for careful analysis and assessment when making claims about the learning capabilities of neural network models.

Sam Wiseman, Stuart M. Shieber, Alexander M. Rush

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.

Allen Schmaltz, Yoon Kim, Alexander M. Rush et al.

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.

Sam Wiseman, Stuart M. Shieber, Alexander M. Rush

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.

Allen Schmaltz, Alexander M. Rush, Stuart M. Shieber

Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence. We find that, in fact, an n-gram language model with a simple heuristic gives strong results on this task. Furthermore, we show that a long short-term memory (LSTM) language model is even more effective at recovering order, with our basic model outperforming a state-of-the-art syntactic model by 11.5 BLEU points. Additional data and larger beams yield further gains, at the expense of training and search time.

Allen Schmaltz, Yoon Kim, Alexander M. Rush et al.

We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016. The attention-based encoder-decoder models can be used for the generation of corrections, in addition to error identification, which is of interest for certain end-user applications. We show that a character-based encoder-decoder model is particularly effective, outperforming other results on the AESW Shared Task on its own, and showing gains over a word-based counterpart. Our final model--a combination of three character-based encoder-decoder models, one word-based encoder-decoder model, and a sentence-level CNN--is the highest performing system on the AESW 2016 binary prediction Shared Task.

Sam Wiseman, Alexander M. Rush, Stuart M. Shieber

There is compelling evidence that coreference prediction would benefit from modeling global information about entity-clusters. Yet, state-of-the-art performance can be achieved with systems treating each mention prediction independently, which we attribute to the inherent difficulty of crafting informative cluster-level features. We instead propose to use recurrent neural networks (RNNs) to learn latent, global representations of entity clusters directly from their mentions. We show that such representations are especially useful for the prediction of pronominal mentions, and can be incorporated into an end-to-end coreference system that outperforms the state of the art without requiring any additional search.