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

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a...

/pdf/natural-questions-a-benchmark-for-question-answering-10mm1ytgmc.pdf

Natural Questions: A Benchmark for Question Answering Research

Unsupervised word representations are very useful in NLP tasks both as inputs to learning algorithms and as extra word features in NLP systems. However, most of these models are built with only local context and one representation per word. This is problematic because words are often polysemous and global context can also provide useful information for learning word meanings. We present a new neural network architecture which 1) learns word embeddings that better capture the semantics of words by incorporating both local and global document context, and 2) accounts for homonymy and polysemy by learning multiple embeddings per word. We introduce a new dataset with human judgments on pairs of words in sentential context, and evaluate our model on it, showing that our model outperforms competitive baselines and other neural language models.

/pdf/improving-word-representations-via-global-context-and-4x4fd6wohu.pdf

Improving Word Representations via Global Context and Multiple Word Prototypes

The strongly typed syntax of grammar formalisms such as CCG, TAG, LFG and HPSG offers a synchronous framework for deriving syntactic structures and semantic logical forms.  In contrast---partly due to the lack of a strong type system---dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages.  However, the lack of a type system makes a formal mechanism for deriving logical forms from dependency structures challenging.  We address this by introducing a robust system based on the lambda calculus for deriving neo-Davidsonian logical forms from dependency trees. These logical forms are then used for semantic parsing of natural language to Freebase. Experiments on the Free917 and WebQuestions datasets show that our representation is superior to the original dependency trees and that it outperforms a CCG-based representation on this task. Compared to prior work, we obtain the strongest result to date on Free917 and competitive results on WebQuestions.

/pdf/transforming-dependency-structures-to-logical-forms-for-sfy1c8ers7.pdf

Transforming Dependency Structures to Logical Forms for Semantic Parsing

Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.

Question Answering on Freebase via Relation Extraction and Textual Evidence

A multiword is compositional if its meaning can be expressed in terms of the meaning of its constituents. In this paper, we collect and analyse the compositionality judgments for a range of compound nouns using Mechanical Turk. Unlike existing compositionality datasets, our dataset has judgments on the contribution of constituent words as well as judgments for the phrase as a whole. We use this dataset to study the relation between the judgments at constituent level to that for the whole phrase. We then evaluate two different types of distributional models for compositionality detection – constituent based models and composition function based models. Both the models show competitive performance though the composition function based models perform slightly better. In both types, additive models perform better than their multiplicative counterparts.

/pdf/an-empirical-study-on-compositionality-in-compound-nouns-463xodph44.pdf

An Empirical Study on Compositionality in Compound Nouns

Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need. In this paper we turn to paraphrases as a means of capturing this knowledge and present a general framework which learns felicitous paraphrases for various QA tasks. Our method is trained end-to-end using question-answer pairs as a supervision signal. A question and its paraphrases serve as input to a neural scoring model which assigns higher weights to linguistic expressions most likely to yield correct answers. We evaluate our approach on QA over Freebase and answer sentence selection. Experimental results on three datasets show that our framework consistently improves performance, achieving competitive results despite the use of simple QA models.

/pdf/learning-to-paraphrase-for-question-answering-4fl4qw38wf.pdf

Learning to Paraphrase for Question Answering

Existing question answering methods infer answers either from a knowledge base or from raw text. While knowledge base (KB) methods are good at answering compositional questions, their performance is often affected by the incompleteness of the KB. Au contraire, web text contains millions of facts that are absent in the KB, however in an unstructured form. Universal schema can support reasoning on the union of both structured KBs and unstructured text by aligning them in a common embedded space. In this paper we extend universal schema to natural language question answering, employing Memory networks to attend to the large body of facts in the combination of text and KB. Our models can be trained in an end-to-end fashion on question-answer pairs. Evaluation results on Spades fill-in-the-blank question answering dataset show that exploiting universal schema for question answering is better than using either a KB or text alone. This model also outperforms the current state-of-the-art by 8.5 F1 points.

/pdf/question-answering-on-knowledge-bases-and-text-using-4oo8p18klo.pdf

Siva Reddy

Papers

Transforming Dependency Structures to Logical Forms for Semantic Parsing

Question Answering on Freebase via Relation Extraction and Textual Evidence

An Empirical Study on Compositionality in Compound Nouns

Learning to Paraphrase for Question Answering

Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks