Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.

/pdf/language-models-are-few-shot-learners-2fg8gvia7m.pdf

Language Models are Few-Shot Learners

A Long Short-Term Memory (LSTM) network is a type of recurrent neural network architecture which has recently obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. TreeLSTMs outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences (SemEval 2014, Task 1) and sentiment classification (Stanford Sentiment Treebank).

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice.

Skip-thought vectors

We present a siamese adaptation of the Long Short-Term Memory (LSTM) network for labeled data comprised of pairs of variable-length sequences. Our model is applied to assess semantic similarity between sentences, where we exceed state of the art, outperforming carefully handcrafted features and recently proposed neural network systems of greater complexity. For these applications, we provide word-embedding vectors supplemented with synonymic information to the LSTMs, which use a fixed size vector to encode the underlying meaning expressed in a sentence (irrespective of the particular wording/syntax). By restricting subsequent operations to rely on a simple Manhattan metric, we compel the sentence representations learned by our model to form a highly structured space whose geometry reflects complex semantic relationships. Our results are the latest in a line of findings that showcase LSTMs as powerful language models capable of tasks requiring intricate understanding.

/pdf/siamese-recurrent-architectures-for-learning-sentence-28biyctynq.pdf

Siamese recurrent architectures for learning sentence similarity

Shared Task 1 of SemEval-2014 comprised two subtasks on the same dataset of sentence pairs: recognizing textual entailment and determining textual similarity. We used an existing system based on formal semantics and logical inference to participate in the first subtask, reaching an accuracy of 82%, ranking in the top 5 of more than twenty participating systems. For determining semantic similarity we took a supervised approach using a variety of features, the majority of which was produced by our system for recognizing textual entailment. In this subtask our system achieved a mean squared error of 0.322, the best of all participating systems.

/pdf/the-meaning-factory-formal-semantics-for-recognizing-textual-4d7i7u7rsw.pdf

The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity

Analogies such as man is to king as woman is to X are often used to illustrate the amazing power of word embeddings. Concurrently, they have also been used to expose how strongly human biases are encoded in vector spaces trained on natural language, with examples like man is to computer programmer as woman is to homemaker. Recent work has shown that analogies are in fact not an accurate diagnostic for bias, but this does not mean that they are not used anymore, or that their legacy is fading. Instead of focusing on the intrinsic problems of the analogy task as a bias detection tool, we discuss a series of issues involving implementation as well as subjective choices that might have yielded a distorted picture of bias in word embeddings. We stand by the truth that human biases are present in word embeddings, and, of course, the need to address them. But analogies are not an accurate tool to do so, and the way they have been most often used has exacerbated some possibly non-existing biases and perhaps hidden others. Because they are still widely popular, and some of them have become classics within and outside the NLP community, we deem it important to provide a series of clarifications that should put well-known, and potentially new analogies, into the right perspective.

Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor

Transfer learning, particularly approaches that combine multi-task learning with pre-trained contextualized embeddings and fine-tuning, have advanced the field of Natural Language Processing tremendously in recent years. In this paper we present MaChAmp, a toolkit for easy use of fine-tuning BERT-like models in multi-task settings. The benefits of MaChAmp are its flexible configuration options, and the support of a variety of NLP tasks in a uniform toolkit, from text classification to sequence labeling and dependency parsing.

Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human predictive power proves similar to that of our bleached models, and both perform better than lexical models.

/pdf/bleaching-text-abstract-features-for-cross-lingual-gender-ovhxf02fsl.pdf

Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

We introduce Biomedical Event Extraction as Sequence Labeling (BeeSL), a joint end-to-end neural information extraction model. BeeSL recasts the task as sequence labeling, taking advantage of a multi-label aware encoding strategy and jointly modeling the intermediate tasks via multi-task learning. BeeSL is fast, accurate, end-to-end, and unlike current methods does not require any external knowledge base or preprocessing tools. BeeSL outperforms the current best system (Li et al., 2019) on the Genia 2011 benchmark by 1.57% absolute F1 score reaching 60.22% F1, establishing a new state of the art for the task. Importantly, we also provide first results on biomedical event extraction without gold entity information. Empirical results show that BeeSL’s speed and accuracy makes it a viable approach for large-scale real-world scenarios.

/pdf/biomedical-event-extraction-as-sequence-labeling-1yoyusyo0f.pdf

Rob van der Goot

Papers

The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity

Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor

Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP

Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

Biomedical Event Extraction as Sequence Labeling