Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be
en proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches i
mproved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.
Detection of toxic spans - detecting toxicity of contents in the granularity of tokens - is crucial for effective moderation of online discussions. The baseline approach for this problem using the transformer model is to add a token classification he
ad to the language model and fine-tune the layers with the token labeled dataset. One of the limitations of such a baseline approach is the scarcity of labeled data. To improve the results, We studied leveraging existing public datasets for a related but different task of entire comment/sentence classification. We propose two approaches: the first approach fine-tunes transformer models that are pre-trained on sentence classification samples. In the second approach, we perform weak supervision with soft attention to learn token level labels from sentence labels. Our experiments show improvements in the F1 score over the baseline approach. The implementation has been released publicly.
Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce Knodle, a sof
tware framework that treats weak data annotations, deep learning models, and methods for improving weakly supervised training as separate, modular components. This modularization gives the training process access to fine-grained information such as data set characteristics, matches of heuristic rules, or elements of the deep learning model ultimately used for prediction. Hence, our framework can encompass a wide range of training methods for improving weak supervision, ranging from methods that only look at correlations of rules and output classes (independently of the machine learning model trained with the resulting labels), to those that harness the interplay of neural networks and weakly labeled data. We illustrate the benchmarking potential of the framework with a performance comparison of several reference implementations on a selection of datasets that are already available in Knodle.
Automatic summarization aims to extract important information from large amounts of textual data in order to create a shorter version of the original texts while preserving its information. Training traditional extractive summarization models relies
heavily on human-engineered labels such as sentence-level annotations of summary-worthiness. However, in many use cases, such human-engineered labels do not exist and manually annotating thousands of documents for the purpose of training models may not be feasible. On the other hand, indirect signals for summarization are often available, such as agent actions for customer service dialogues, headlines for news articles, diagnosis for Electronic Health Records, etc. In this paper, we develop a general framework that generates extractive summarization as a byproduct of supervised learning tasks for indirect signals via the help of attention mechanism. We test our models on customer service dialogues and experimental results demonstrated that our models can reliably select informative sentences and words for automatic summarization.
Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-t
rivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process a walk in the dark''. In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category names. We then train interim models with individual candidate seed words. Lastly, we estimate the interim models' error rate in an unsupervised manner. The seed words that yield the lowest estimated error rates are added to the final seed word set. A comprehensive evaluation of six binary classification tasks on four popular datasets demonstrates that the proposed method outperforms a baseline using only category name seed words and obtained comparable performance as a counterpart using expert-annotated seed words.
