We present a method for labeling spans of text with large language models (LLMs) and apply it to the task of identifying shell language, language which plays a structural or connective role without constituting the main content of a text. We compare several recent LLMs by evaluating their “annotations” against a small human-curated test set, and train a smaller supervised model on thousands of LLM-annotated examples. The described method enables workflows that can learn complex or nuanced linguistic phenomena without tedious, large-scale hand-annotations of training data or specialized feature engineering.

We present a case study describing our efforts to integrate the open source GECToR code and models into our production NLP pipeline that powers many of Educational Testing Service’s products and prototypes. The paper’s contributions includes a discussion of the issues we encountered during integration and our solutions, the overarching lessons we learned about integrating open source projects, and, last but not least, the open source contributions we made as part of the journey.

In this theme paper, we focus on Automated Writing Evaluation (AWE), using Ellis Page’s seminal 1966 paper to frame the presentation. We discuss some of the current frontiers in the field and offer some thoughts on the emergent uses of this technology.

The effect of noisy labels on the performance of NLP systems has been studied extensively for system training. In this paper, we focus on the effect that noisy labels have on system evaluation. Using automated scoring as an example, we demonstrate that the quality of human ratings used for system evaluation have a substantial impact on traditional performance metrics, making it impossible to compare system evaluations on labels with different quality. We propose that a new metric, PRMSE, developed within the educational measurement community, can help address this issue, and provide practical guidelines on using PRMSE.

For the last 5 years, we have developed and maintained RSMTool – an open-source tool for evaluating NLP systems that automatically score written and spoken responses. RSMTool is designed to be cross-disciplinary, borrowing heavily from NLP, machine learning, and educational measurement. Its cross-disciplinary nature has required us to learn a user-centered development approach in terms of both design and implementation. We share some of these lessons in this paper.

Literacy is crucial for functioning in modern society. It underpins everything from educational attainment and employment opportunities to health outcomes. We describe My Turn To Read, an app that uses interleaved reading to help developing and struggling readers improve reading skills while reading for meaning and pleasure. We hypothesize that the longer-term impact of the app will be to help users become better, more confident readers with an increased stamina for extended reading. We describe the technology and present preliminary evidence in support of this hypothesis.

The issues of algorithmic fairness and bias have recently featured prominently in many publications highlighting the fact that training the algorithms for maximum performance may often result in predictions that are biased against various groups. Educational applications based on NLP and speech processing technologies often combine multiple complex machine learning algorithms and are thus vulnerable to the same sources of bias as other machine learning systems. Yet such systems can have high impact on people’s lives especially when deployed as part of high-stakes tests. In this paper we discuss different definitions of fairness and possible ways to apply them to educational applications. We then use simulated and real data to consider how test-takers’ native language backgrounds can affect their automated scores on an English language proficiency assessment. We illustrate that total fairness may not be achievable and that different definitions of fairness may require different solutions.

In this study, we developed an automated algorithm to provide feedback about the specific content of non-native English speakers’ spoken responses. The responses were spontaneous speech, elicited using integrated tasks where the language learners listened to and/or read passages and integrated the core content in their spoken responses. Our models detected the absence of key points considered to be important in a spoken response to a particular test question, based on two different models: (a) a model using word-embedding based content features and (b) a state-of-the art short response scoring engine using traditional n-gram based features. Both models achieved a substantially improved performance over the majority baseline, and the combination of the two models achieved a significant further improvement. In particular, the models were robust to automated speech recognition (ASR) errors, and performance based on the ASR word hypotheses was comparable to that based on manual transcriptions. The accuracy and F-score of the best model for the questions included in the train set were 0.80 and 0.68, respectively. Finally, we discussed possible approaches to generating targeted feedback about the content of a language learner’s response, based on automatically detected missing key points.

In this position paper, we argue that building operational automated scoring systems is a task that has disciplinary complexity above and beyond standard competitive shared tasks which usually involve applying the latest machine learning techniques to publicly available data in order to obtain the best accuracy. Automated scoring systems warrant significant cross-discipline collaboration of which natural language processing and machine learning are just two of many important components. Such systems have multiple stakeholders with different but valid perspectives that can often times be at odds with each other. Our position is that it is essential for us as NLP researchers to understand and incorporate these perspectives in our research and work towards a mutually satisfactory solution in order to build automated scoring systems that are accurate, fair, unbiased, and useful.

Writing Mentor is a free Google Docs add-on designed to provide feedback to struggling writers and help them improve their writing in a self-paced and self-regulated fashion. Writing Mentor uses natural language processing (NLP) methods and resources to generate feedback in terms of features that research into post-secondary struggling writers has classified as developmental (Burstein et al., 2016b). These features span many writing sub-constructs (use of sources, claims, and evidence; topic development; coherence; and knowledge of English conventions). Prelimi- nary analysis indicates that users have a largely positive impression of Writing Mentor in terms of usability and potential impact on their writing.

In large-scale educational assessments, the use of automated scoring has recently become quite common. While the majority of student responses can be processed and scored without difficulty, there are a small number of responses that have atypical characteristics that make it difficult for an automated scoring system to assign a correct score. We describe a pipeline that detects and processes these kinds of responses at run-time. We present the most frequent kinds of what are called non-scorable responses along with effective filtering models based on various NLP and speech processing technologies. We give an overview of two operational automated scoring systems —one for essay scoring and one for speech scoring— and describe the filtering models they use. Finally, we present an evaluation and analysis of filtering models used for spoken responses in an assessment of language proficiency.

We present the task of second language acquisition (SLA) modeling. Given a history of errors made by learners of a second language, the task is to predict errors that they are likely to make at arbitrary points in the future. We describe a large corpus of more than 7M words produced by more than 6k learners of English, Spanish, and French using Duolingo, a popular online language-learning app. Then we report on the results of a shared task challenge aimed studying the SLA task via this corpus, which attracted 15 teams and synthesized work from various fields including cognitive science, linguistics, and machine learning.

The Association of Computational Linguistic’s Anthology is the open source archive, and the main source for computational linguistics and natural language processing’s scientific literature. The ACL Anthology is currently maintained exclusively by community volunteers and has to be available and up-to-date at all times. We first discuss the current, open source approach used to achieve this, and then discuss how the planned use of Docker images will improve the Anthology’s long-term stability. This change will make it easier for researchers to utilize Anthology data for experimentation. We believe the ACL community can directly benefit from the extension-friendly architecture of the Anthology. We end by issuing an open challenge of reviewer matching we encourage the community to rally towards.

Automated scoring of written and spoken responses is an NLP application that can significantly impact lives especially when deployed as part of high-stakes tests such as the GRE® and the TOEFL®. Ethical considerations require that automated scoring algorithms treat all test-takers fairly. The educational measurement community has done significant research on fairness in assessments and automated scoring systems must incorporate their recommendations. The best way to do that is by making available automated, non-proprietary tools to NLP researchers that directly incorporate these recommendations and generate the analyses needed to help identify and resolve biases in their scoring systems. In this paper, we attempt to provide such a solution.

We consider the automatic scoring of a task for which both the content of the response as well its spoken fluency are important. We combine features from a text-only content scoring system originally designed for written responses with several categories of acoustic features. Although adding any single category of acoustic features to the text-only system on its own does not significantly improve performance, adding all acoustic features together does yield a small but significant improvement. These results are consistent for responses to open-ended questions and to questions focused on some given source material.

We explore various supervised learning strategies for automated scoring of content knowledge for a large corpus of 130 different content-based questions spanning four subject areas (Science, Math, English Language Arts, and Social Studies) and containing over 230,000 responses scored by human raters. Based on our analyses, we provide specific recommendations for content scoring. These are based on patterns observed across multiple questions and assessments and are, therefore, likely to generalize to other scenarios and prove useful to the community as automated content scoring becomes more popular in schools and classrooms.

We demonstrate a method of improving a seed sentiment lexicon developed on essay data by using a pivot-based paraphrasing system for lexical expansion coupled with sentiment profile enrichment using crowdsourcing. Profile enrichment alone yields up to 15% improvement in the accuracy of the seed lexicon on 3-way sentence-level sentiment polarity classification of essay data. Using lexical expansion in addition to sentiment profiles provides a further 7% improvement in performance. Additional experiments show that the proposed method is also effective with other subjectivity lexicons and in a different domain of application (product reviews).

Most state-of-the-art statistical machine translation systems use log-linear models, which are defined in terms of hypothesis features and weights for those features. It is standard to tune the feature weights in order to maximize a translation quality metric, using held-out test sentences and their corresponding reference translations. However, obtaining reference translations is expensive. In our earlier work (Madnani et al., 2007), we introduced a new full-sentence paraphrase technique, based on English-to-English decoding with an MT system, and demonstrated that the resulting paraphrases can be used to cut the number of human reference translations needed in half. In this paper, we take the idea a step further, asking how far it is possible to get with just a single good reference translation for each item in the development set. Our analysis suggests that it is necessary to invest in four or more human translations in order to significantly improve on a single translation augmented by monolingual paraphrases.