Journal Article•
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
TL;DR: This article introduced a unified framework that converts all text-based language problems into a text-to-text format and compared pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks.
Abstract: Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.
Citations
More filters
TL;DR: In this article, an audio-aware spoken multiple-choice question answering (SMCQA) framework is proposed, where two different mechanisms are introduced to distill the useful cues from speech, and then a BERT-based SMCQA framework is presented.
Abstract: Spoken multiple-choice question answering (SMCQA) requires machines to select the correct choice to answer the question by referring to the passage, where the passage, the question, and multiple choices are all in the form of speech. While the audio could contain useful cues for SMCQA, usually only the auto-transcribed text is utilized in model development. Thanks to the large-scaled pre-trained language representation models, such as the bidirectional encoder representations from Transformers (BERT), systems with only auto-transcribed text can still achieve a certain level of performance. However, previous studies have evidenced that acoustic-level statistics can offset text inaccuracies caused by the automatic speech recognition systems or representation inadequacy lurking in word embedding generators, thereby making the SMCQA system robust. Along the line of research, in this study, an audio-aware SMCQA framework is proposed. Two different mechanisms are introduced to distill the useful cues from speech, and then a BERT-based SMCQA framework is presented. In other words, the proposed SMCQA framework not only inherits the advantages of contextualized language representations learned by BERT but integrates the complementary acoustic-level information distilled from audio with the text-level information. A series of experiments demonstrates remarkable improvements in accuracy over selected baselines and SOTA systems on a published Chinese SMCQA dataset.
Posted Content•
TL;DR: In this paper, a text-based and vector-based pseudo relevance feedback (Pseudo Relevance Feedback) is used to improve the performance of bag-of-words re-rankers.
Abstract: Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform traditional bag-of-words rerankers. However, it is unclear how to integrate PRF directly with emergent deep language models. In this article, we address this gap by investigating methods for integrating PRF signals into rerankers and dense retrievers based on deep language models. We consider text-based and vector-based PRF approaches, and investigate different ways of combining and scoring relevance signals. An extensive empirical evaluation was conducted across four different datasets and two task settings (retrieval and ranking).
Text-based PRF results show that the use of PRF had a mixed effect on deep rerankers across different datasets. We found that the best effectiveness was achieved when (i) directly concatenating each PRF passage with the query, searching with the new set of queries, and then aggregating the scores; (ii) using Borda to aggregate scores from PRF runs.
Vector-based PRF results show that the use of PRF enhanced the effectiveness of deep rerankers and dense retrievers over several evaluation metrics. We found that higher effectiveness was achieved when (i) the query retains either the majority or the same weight within the PRF mechanism, and (ii) a shallower PRF signal (i.e., a smaller number of top-ranked passages) was employed, rather than a deeper signal. Our vector-based PRF method is computationally efficient; thus this represents a general PRF method others can use with deep rerankers and dense retrievers.
Posted Content•
TL;DR: The authors used the Fusion-in-Decoder approach to cope with multiple long inputs and incorporated the predicted citation intents into training for intent control to generate multiple citation sentences for scientific literature review and assist article writing.
Abstract: Machine-generated citation sentences can aid automated scientific literature review and assist article writing. Current methods in generating citation text were limited to single citation generation using the citing document and a cited document as input. However, in real-world situations, writers often summarize several studies in one sentence or discuss relevant information across the entire paragraph. In addition, multiple citation intents have been previously identified, implying that writers may need control over the intents of generated sentences to cover different scenarios. Therefore, this work focuses on generating multiple citations and releasing a newly collected dataset named CiteMI to drive the future research. We first build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs. Second, we incorporate the predicted citation intents into training for intent control. The experiments demonstrate that the proposed approaches provide much more comprehensive features for generating citation sentences.
Posted Content•
TL;DR: This paper proposed LOT, a benchmark for Chinese long text modeling evaluation, which requires many distinct capabilities such as modeling long-range commonsense and discourse relations, as well as the coherence and controllability of generation.
Abstract: Standard multi-task benchmarks are essential for driving the progress of general pretraining models to generalize to various downstream tasks. However, existing benchmarks such as GLUE and GLGE tend to focus on short text understanding and generation tasks, without considering long text modeling, which requires many distinct capabilities such as modeling long-range commonsense and discourse relations, as well as the coherence and controllability of generation. The lack of standardized benchmarks makes it difficult to fully evaluate these capabilities of a model and fairly compare different models, especially Chinese pretraining models. Therefore, we propose LOT, a benchmark including two understanding and two generation tasks for Chinese long text modeling evaluation. We construct the datasets for the tasks based on various kinds of human-written Chinese stories. Besides, we release an encoder-decoder Chinese long text pretraining model named LongLM with up to 1 billion parameters. We pretrain LongLM on 120G Chinese novels with two generative tasks including text infilling and conditional continuation. Extensive experiments on LOT demonstrate that LongLM matches the performance of similar-sized pretraining models on the understanding tasks and outperforms strong baselines substantially on the generation tasks.
Posted Content•
TL;DR: This paper introduced a dataset of 4,631 CQA threads for answer summarization, curated by professional linguists, and proposed reinforcement learning rewards to improve factual consistency and answer coverage.
Abstract: Community Question Answering (CQA) fora such as Stack Overflow and Yahoo! Answers contain a rich resource of answers to a wide range of community-based questions. Each question thread can receive a large number of answers with different perspectives. One goal of answer summarization is to produce a summary that reflects the range of answer perspectives. A major obstacle for abstractive answer summarization is the absence of a dataset to provide supervision for producing such summaries. Recent works propose heuristics to create such data, but these are often noisy and do not cover all perspectives present in the answers. This work introduces a novel dataset of 4,631 CQA threads for answer summarization, curated by professional linguists. Our pipeline gathers annotations for all subtasks involved in answer summarization, including the selection of answer sentences relevant to the question, grouping these sentences based on perspectives, summarizing each perspective, and producing an overall summary. We analyze and benchmark state-of-the-art models on these subtasks and introduce a novel unsupervised approach for multi-perspective data augmentation, that further boosts overall summarization performance according to automatic evaluation. Finally, we propose reinforcement learning rewards to improve factual consistency and answer coverage and analyze areas for improvement.