We explore using the 6B parameter GPT-J language model to create a plan for a simulated robot to achieve 30 classes of goals in ScienceWorld, a text game simulator for elementary science experiments and for which previously published empirical work has shown large language models (LLM)s to be a poor fit (Wang et al., 2022). Using the Markov assumption, the LLM outperforms the state-of-the-art based on reinforcement learning by a factor of 1.4. When we fill the LLM’s input buffer with as many prior steps as will fit, improvement rises to 3.3x. Even when training on only 6.5% of the training data, we observe a 2.3x improvement over the state-of-the-art. Our experiments show that performance varies widely across the 30 classes of actions, indicating that averaging over tasks can hide significant performance issues.

Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.

Language Identification is the task of identifying a document’s language. For applications like automatic spell checker selection, language identification must use very short strings such as text message fragments. In this work, we reproduce a language identification architecture that Apple briefly sketched in a blog post. We confirm the bi-LSTM model’s performance and find that it outperforms current open-source language identifiers. We further find that its language identification mistakes are due to confusion between related languages.

Danish language technology has been hindered by a lack of broad-coverage corpora at the scale modern NLP prefers. This paper describes the Danish Gigaword Corpus, the result of a focused effort to provide a diverse and freely-available one billion word corpus of Danish text. The Danish Gigaword corpus covers a wide array of time periods, domains, speakers’ socio-economic status, and Danish dialects.

Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e.g., an introductory college textbook or a manual. PTLMs have shown great success in many question-answering tasks, given significant supervised training, but much less so in zero-shot settings. We propose a new task that includes two college-level introductory texts in the social sciences (American Government 2e) and humanities (U.S. History), hundreds of true/false statements based on review questions written by the textbook authors, validation/development tests based on the first eight chapters of the textbooks, blind tests based on the remaining textbook chapters, and baseline results given state-of-the-art PTLMs. Since the questions are balanced, random performance should be ~50%. T5, fine-tuned with BoolQ achieves the same performance, suggesting that the textbook’s content is not pre-represented in the PTLM. Taking the exam closed book, but having read the textbook (i.e., adding the textbook to T5’s pre-training), yields at best minor improvement (56%), suggesting that the PTLM may not have “understood” the textbook (or perhaps misunderstood the questions). Performance is better (~60%) when the exam is taken open-book (i.e., allowing the machine to automatically retrieve a paragraph and use it to answer the question).

We describe Machine-Aided Script Curator (MASC), a system for human-machine collaborative script authoring. Scripts produced with MASC include (1) English descriptions of sub-events that comprise a larger, complex event; (2) event types for each of those events; (3) a record of entities expected to participate in multiple sub-events; and (4) temporal sequencing between the sub-events. MASC automates portions of the script creation process with suggestions for event types, links to Wikidata, and sub-events that may have been forgotten. We illustrate how these automations are useful to the script writer with a few case-study scripts.

Word embeddings are an active topic in the NLP research community. State-of-the-art neural models achieve high performance on downstream tasks, albeit at the cost of computationally expensive training. Cost aware solutions require cheaper models that still achieve good performance. We present several reproduction studies of intrinsic evaluation tasks that evaluate non-contextual word representations in multiple languages. Furthermore, we present 50-8-8, a new data set for the outlier identification task, which avoids limitations of the original data set, such as ambiguous words, infrequent words, and multi-word tokens, while increasing the number of test cases. The data set is expanded to contain semantic and syntactic tests and is multilingual (English, German, and Italian). We provide an in-depth analysis of word embedding models with a range of hyper-parameters. Our analysis shows the suitability of different models and hyper-parameters for different tasks and the greater difficulty of representing German and Italian languages.

Word clustering groups words that exhibit similar properties. One popular method for this is Brown clustering, which uses short-range distributional information to construct clusters. Specifically, this is a hard hierarchical clustering with a fixed-width beam that employs bi-grams and greedily minimizes global mutual information loss. The result is word clusters that tend to outperform or complement other word representations, especially when constrained by small datasets. However, Brown clustering has high computational complexity and does not lend itself to parallel computation. This, together with the lack of efficient implementations, limits their applicability in NLP. We present efficient implementations of Brown clustering and the alternative Exchange clustering as well as a number of methods to accelerate the computation of both hierarchical and flat clusters. We show empirically that clusters obtained with the accelerated method match the performance of clusters computed using the original methods.

Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable at distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms’ optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.

We present Abbreviation Explorer, a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation (UAD). Abbreviation Explorer helps to identify long-forms that are easily confused, and to pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. It can also support determining which long-forms would benefit from additional input text for unsupervised abbreviation disambiguation. The system provides options for creating corrective rules that merge redundant long-forms with identical meaning. The identified rules can be easily applied to the already existing vector spaces used by UAD to improve disambiguation performance, while also avoiding the cost of retraining.

As part of the BioNLP Open Shared Tasks 2019, the CRAFT Shared Tasks 2019 provides a platform to gauge the state of the art for three fundamental language processing tasks — dependency parse construction, coreference resolution, and ontology concept identification — over full-text biomedical articles. The structural annotation task requires the automatic generation of dependency parses for each sentence of an article given only the article text. The coreference resolution task focuses on linking coreferring base noun phrase mentions into chains using the symmetrical and transitive identity relation. The ontology concept annotation task involves the identification of concept mentions within text using the classes of ten distinct ontologies in the biomedical domain, both unmodified and augmented with extension classes. This paper provides an overview of each task, including descriptions of the data provided to participants and the evaluation metrics used, and discusses participant results relative to baseline performances for each of the three tasks.

Abbreviations and acronyms are a part of textual communication in most domains. However, abbreviations are not necessarily defined in documents that employ them. Understanding all abbreviations used in a given document often requires extensive knowledge of the target domain and the ability to disambiguate based on context. This creates considerable entry barriers to newcomers and difficulties in automated document processing. Existing abbreviation expansion systems or tools require substantial technical knowledge for set up or make strong assumptions which limit their use in practice. Here, we present Abbreviation Expander, a system that builds on state of the art methods for identification of abbreviations, acronyms and their definitions and a novel disambiguator for abbreviation expansion in an easily accessible web-based solution.