Usage of large language models and chat bots will almost surely continue to grow, since they are so easy to use, and so (incredibly) credible. I would be more comfortable with this reality if we encouraged more evaluations with humans-in-the-loop to come up with a better characterization of when the machine can be trusted and when humans should intervene. This article will describe a homework assignment, where I asked my students to use tools such as chat bots and web search to write a number of essays. Even after considerable discussion in class on hallucinations, many of the essays were full of misinformation that should have been fact-checked. Apparently, it is easier to believe ChatGPT than to be skeptical. Fact-checking and web search are too much trouble.

A lot has happened since OpenAI released ChatGPT to the public in November 2022. We review how things unfolded over the course of the year, tracking significant events and announcements from the tech giants leading the generative AI race and from other players of note; along the way we note the wider impacts of the technology’s progress.

Large language models (LLMs) have achieved amazing successes. They have done well on standardized tests in medicine and the law. That said, the bar has been raised so high that it could take decades to make good on expectations. To buy time for this long-term research program, the field needs to identify some good short-term applications for smooth-talking machines that are more fluent than trustworthy.

GPT-3 is a large-scale natural language model developed by OpenAI that can perform many different tasks, including topic classification. Although researchers claim that it requires only a small number of in-context examples to learn a task, in practice GPT-3 requires these training examples to be either of exceptional quality or a higher quantity than easily created by hand. To address this issue, this study teaches GPT-3 to classify whether a question is related to data science by augmenting a small training set with additional examples generated by GPT-3 itself. This study compares two augmented classifiers: the Classification Endpoint with an increased training set size and the Completion Endpoint with an augmented prompt optimized using a genetic algorithm. We find that data augmentation significantly increases the accuracy of both classifiers, and that the embedding-based Classification Endpoint achieves the best accuracy of about 76%, compared to human accuracy of 85%. In this way, giving large language models like GPT-3 the ability to propose their own training examples can improve short text classification performance.

House price prediction is an important problem that could benefit home buyers and sellers. Traditional models for house price prediction use numerical attributes such as the number of rooms but disregard the house description text. The recent developments in text processing suggest these can be valuable attributes, which motivated us to use house descriptions. This paper focuses on the house asking/advertising price and studies the impact of using house description texts to predict the final house price. To achieve this, we collected a large and diverse set of attributes on house postings, including the house advertising price. Then, we compare the performance of three scenarios: using only the house description, only numeric attributes, or both. We processed the description text through three word embedding techniques: TF-IDF, Word2Vec, and BERT. Four regression algorithms are trained using only textual data, non-textual data, or both. Our results show that by using exclusively the description data with Word2Vec and a Deep Learning model, we can achieve good performance. However, the best overall performance is obtained when using both textual and non-textual features. An $R^2$ of 0.7904 is achieved by the deep learning model using only description data on the testing data. This clearly indicates that using the house description text alone is a strong predictor for the house price. However, when observing the RMSE on the test data, the best model was gradient boosting using both numeric and description data. Overall, we observe that combining the textual and non-textual features improves the learned model and provides performance benefits when compared against using only one of the feature types. We also provide a freely available application for house price prediction, which is solely based on a house text description and uses our final developed model with Word2Vec and Deep Learning to predict the house price.

Many research topics in natural language processing (NLP), such as explanation generation, dialog modeling, or machine translation, require evaluation that goes beyond standard metrics like accuracy or F1 score toward a more human-centered approach. Therefore, understanding how to design user studies becomes increasingly important. However, few comprehensive resources exist on planning, conducting, and evaluating user studies for NLP, making it hard to get started for researchers without prior experience in the field of human evaluation. In this paper, we summarize the most important aspects of user studies and their design and evaluation, providing direct links to NLP tasks and NLP-specific challenges where appropriate. We (i) outline general study design, ethical considerations, and factors to consider for crowdsourcing, (ii) discuss the particularities of user studies in NLP, and provide starting points to select questionnaires, experimental designs, and evaluation methods that are tailored to the specific NLP tasks. Additionally, we offer examples with accompanying statistical evaluation code, to bridge the gap between theoretical guidelines and practical applications.

There has been considerable work recently in the natural language community and elsewhere on Responsible AI. Much of this work focuses on fairness and biases (henceforth Risks 1.0), following the 2016 best seller: Weapons of Math Destruction. Two books published in 2022, The Chaos Machine and Like, Comment, Subscribe, raise additional risks to public health/safety/security such as genocide, insurrection, polarized politics, vaccinations (henceforth, Risks 2.0). These books suggest that the use of machine learning to maximize engagement in social media has created a Frankenstein Monster that is exploiting human weaknesses with persuasive technology, the illusory truth effect, Pavlovian conditioning, and Skinner’s intermittent variable reinforcement. Just as we cannot expect tobacco companies to sell fewer cigarettes and prioritize public health ahead of profits, so too, it may be asking too much of companies (and countries) to stop trafficking in misinformation given that it is so effective and so insanely profitable (at least in the short term). Eventually, we believe the current chaos will end, like the lawlessness in Wild West, because chaos is bad for business. As computer scientists, this paper will summarize criticisms from other fields and focus on implications for computer science; we will not attempt to contribute to those other fields. There is quite a bit of work in computer science on these risks, especially on Risks 1.0 (bias and fairness), but more work is needed, especially on Risks 2.0 (addictive, dangerous, and deadly).

The tremendous amount of increase in the number of documents available on the Web has turned finding the relevant piece of information into a challenging, tedious, and time-consuming activity. Accordingly, automatic text summarization has become an important field of study by gaining significant attention from the researchers. Lately, with the advances in deep learning, neural abstractive text summarization with sequence-to-sequence (Seq2Seq) models has gained popularity. There have been many improvements in these models such as the use of pretrained language models (e.g., GPT, BERT, and XLM) and pretrained Seq2Seq models (e.g., BART and T5). These improvements have addressed certain shortcomings in neural summarization and have improved upon challenges such as saliency, fluency, and semantics which enable generating higher quality summaries. Unfortunately, these research attempts were mostly limited to the English language. Monolingual BERT models and multilingual pretrained Seq2Seq models have been released recently providing the opportunity to utilize such state-of-the-art models in low-resource languages such as Turkish. In this study, we make use of pretrained Seq2Seq models and obtain state-of-the-art results on the two large-scale Turkish datasets, TR-News and MLSum, for the text summarization task. Then, we utilize the title information in the datasets and establish hard baselines for the title generation task on both datasets. We show that the input to the models has a substantial amount of importance for the success of such tasks. Additionally, we provide extensive analysis of the models including cross-dataset evaluations, various text generation options, and the effect of preprocessing in ROUGE evaluations for Turkish. It is shown that the monolingual BERT models outperform the multilingual BERT models on all tasks across all the datasets. Lastly, qualitative evaluations of the generated summaries and titles of the models are provided.

The previous Emerging Trends article (Church et al., 2021. Natural Language Engineering27(5), 631–645.) introduced deep nets to poets. Poets is an imperfect metaphor, intended as a gesture toward inclusion. The future for deep nets will benefit by reaching out to a broad audience of potential users, including people with little or no programming skills, and little interest in training models. That paper focused on inference, the use of pre-trained models, as is, without fine-tuning. The goal of this paper is to make fine-tuning more accessible to a broader audience. Since fine-tuning is more challenging than inference, the examples in this paper will require modest programming skills, as well as access to a GPU. Fine-tuning starts with a general purpose base (foundation) model and uses a small training set of labeled data to produce a model for a specific downstream application. There are many examples of fine-tuning in natural language processing (question answering (SQuAD) and GLUE benchmark), as well as vision and speech.

Automated writing assistance – a category that encompasses a variety of computer-based tools that help with writing – has been around in one form or another for 60 years, although it’s always been a relatively minor part of the NLP landscape. But the category has been given a substantial boost from recent advances in deep learning. We review some history, look at where things stand today, and consider where things might be going.

GPT-3 made the mainstream media headlines this year, generating far more interest than we’d normally expect of a technical advance in NLP. People are fascinated by its ability to produce apparently novel text that reads as if it was written by a human. But what kind of practical applications can we expect to see, and can they be trusted?

It took a while, but natural language generation is now an established commercial software category. It’s commented upon frequently in both industry media and the mainstream press, and businesses are willing to pay hard cash to take advantage of the technology. We look at who’s active in the space, the nature of the technology that’s available today and where things might go in the future.

The law has language at its heart, so it’s not surprising that software that operates on natural language has played a role in some areas of the legal profession for a long time. But the last few years have seen an increased interest in applying modern techniques to a wider range of problems, so I look here at how natural language processing is being used in the legal sector today.

Natural language processing (NLP) techniques can be used to make inferences about peoples’ mental states from what they write on Facebook, Twitter and other social media. These inferences can then be used to create online pathways to direct people to health information and assistance and also to generate personalized interventions. Regrettably, the computational methods used to collect, process and utilize online writing data, as well as the evaluations of these techniques, are still dispersed in the literature. This paper provides a taxonomy of data sources and techniques that have been used for mental health support and intervention. Specifically, we review how social media and other data sources have been used to detect emotions and identify people who may be in need of psychological assistance; the computational techniques used in labeling and diagnosis; and finally, we discuss ways to generate and personalize mental health interventions. The overarching aim of this scoping review is to highlight areas of research where NLP has been applied in the mental health literature and to help develop a common language that draws together the fields of mental health, human-computer interaction and NLP.

My last column ended with some comments about Kuhn and word2vec. Word2vec has racked up plenty of citations because it satisifies both of Kuhn’s conditions for emerging trends: (1) a few initial (promising, if not convincing) successes that motivate early adopters (students) to do more, as well as (2) leaving plenty of room for early adopters to contribute and benefit by doing so. The fact that Google has so much to say on ‘How does word2vec work’ makes it clear that the definitive answer to that question has yet to be written. It also helps citation counts to distribute code and data to make it that much easier for the next generation to take advantage of the opportunities (and cite your work in the process).

By all accounts, 2016 is the year of the chatbot. Some commentators take the view that chatbot technology will be so disruptive that it will eliminate the need for websites and apps. But chatbots have a long history. So what's new, and what's different this time? And is there an opportunity here to improve how our industry does technology transfer?