PyTorchKR Papers

최신 논문

총 4,696편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2009.07253공식 코드 · Papers with Code

Autoregressive Knowledge Distillation through Imitation Learning

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed, making state-of-the-art models cumbersome to deploy in real-world, time-sensitive settings. We develop a compression technique for autoregressive models that is driven by an imitation learning perspective on knowledge distillation. The algorithm is designed to address the exposure bias problem. On prototypical language generation tasks such as translation and summarization, our method consistently outperforms other distillation algorithms, such as sequence-level knowledge distillation. Student models trained with our method attain 1.4 to 4.8 BLEU/ROUGE points higher than those trained from scratch, while increasing inference speed by up to 14 times in comparison to the teacher model.

arXiv:2009.07243공식 코드 · Papers with Code

A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation

This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling algorithms (top-k, nucleus and tempered sampling). We focus on the task of open-ended language generation. We first show that the existing sampling algorithms have similar performance. After carefully inspecting the transformations defined by different sampling algorithms, we identify three key properties that are shared among them: entropy reduction, order preservation, and slope preservation. To validate the importance of the identified properties, we design two sets of new sampling algorithms: one set in which each algorithm satisfies all three properties, and one set in which each algorithm violates at least one of the properties. We compare their performance with existing sampling algorithms, and find that violating the identified properties could lead to drastic performance degradation, as measured by the Q-D trade-off. On the other hand, we find that the set of sampling algorithms that satisfies these properties performs on par with the existing sampling algorithms. Our data and code are available at https://github.com/moinnadeem/characterizing-sampling-algorithms

arXiv:2009.06358

Improving Language Generation with Sentence Coherence Objective

Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community. Existing models are often prone to output paragraphs of texts that gradually diverge from the given prompt. Although the generated text may have a reasonable perplexity and diversity, it could easily be identified by human as gibberish. The goal of our project is to improve the coherence and consistency across sentences in a language-generation model. We aim to solve this issue by first training a sentence pair coherence classifier with GPT-2 pretrained model, and then co-train the GPT-2 language model with this new coherence objective using a method analogous to the REINFORCE algorithm. This fine-tuned language model is able to generate lengthy paragraph conditioned on a given topic without diverging too much. The simplicity of this model allows it to be applicable to a variety of underlying language model architecture since it only modifies the final layer of the pre-trained model.

arXiv:2009.05451

A Comparison of LSTM and BERT for Small Corpus

Recent advancements in the NLP field showed that transfer learning helps with achieving state-of-the-art results for new tasks by tuning pre-trained models instead of starting from scratch. Transformers have made a significant improvement in creating new state-of-the-art results for many NLP tasks including but not limited to text classification, text generation, and sequence labeling. Most of these success stories were based on large datasets. In this paper we focus on a real-life scenario that scientists in academia and industry face frequently: given a small dataset, can we use a large pre-trained model like BERT and get better results than simple models? To answer this question, we use a small dataset for intent classification collected for building chatbots and compare the performance of a simple bidirectional LSTM model with a pre-trained BERT model. Our experimental results show that bidirectional LSTM models can achieve significantly higher results than a BERT model for a small dataset and these simple models get trained in much less time than tuning the pre-trained counterparts. We conclude that the performance of a model is dependent on the task and the data, and therefore before making a model choice, these factors should be taken into consideration instead of directly choosing the most popular model.

arXiv:2009.04530공식 코드 · Papers with Code

Discovering Textual Structures: Generative Grammar Induction using Template Trees

Natural language generation provides designers with methods for automatically generating text, e.g. for creating summaries, chatbots and game content. In practise, text generators are often either learned and hard to interpret, or created by hand using techniques such as grammars and templates. In this paper, we introduce a novel grammar induction algorithm for learning interpretable grammars for generative purposes, called Gitta. We also introduce the novel notion of template trees to discover latent templates in corpora to derive these generative grammars. By using existing human-created grammars, we found that the algorithm can reasonably approximate these grammars using only a few examples. These results indicate that Gitta could be used to automatically learn interpretable and easily modifiable grammars, and thus provide a stepping stone for human-machine co-creation of generative models.

arXiv:2009.05019

Multi-modal embeddings using multi-task learning for emotion recognition

General embeddings like word2vec, GloVe and ELMo have shown a lot of success in natural language tasks. The embeddings are typically extracted from models that are built on general tasks such as skip-gram models and natural language generation. In this paper, we extend the work from natural language understanding to multi-modal architectures that use audio, visual and textual information for machine learning tasks. The embeddings in our network are extracted using the encoder of a transformer model trained using multi-task training. We use person identification and automatic speech recognition as the tasks in our embedding generation framework. We tune and evaluate the embeddings on the downstream task of emotion recognition and demonstrate that on the CMU-MOSEI dataset, the embeddings can be used to improve over previous state of the art results.

arXiv:2009.04968

Modern Methods for Text Generation

Synthetic text generation is challenging and has limited success. Recently, a new architecture, called Transformers, allow machine learning models to understand better sequential data, such as translation or summarization. BERT and GPT-2, using Transformers in their cores, have shown a great performance in tasks such as text classification, translation and NLI tasks. In this article, we analyse both algorithms and compare their output quality in text generation tasks.

arXiv:2009.04765공식 코드 · Papers with Code

Brain2Word: Decoding Brain Activity for Language Generation

Brain decoding, understood as the process of mapping brain activities to the stimuli that generated them, has been an active research area in the last years. In the case of language stimuli, recent studies have shown that it is possible to decode fMRI scans into an embedding of the word a subject is reading. However, such word embeddings are designed for natural language processing tasks rather than for brain decoding. Therefore, they limit our ability to recover the precise stimulus. In this work, we propose to directly classify an fMRI scan, mapping it to the corresponding word within a fixed vocabulary. Unlike existing work, we evaluate on scans from previously unseen subjects. We argue that this is a more realistic setup and we present a model that can decode fMRI data from unseen subjects. Our model achieves 5.22% Top-1 and 13.59% Top-5 accuracy in this challenging task, significantly outperforming all the considered competitive baselines. Furthermore, we use the decoded words to guide language generation with the GPT-2 model. This way, we advance the quest for a system that translates brain activities into coherent text.

arXiv:2009.03457

Robust Conversational AI with Grounded Text Generation

This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transformer neural network as its backbone, combined with symbol-manipulation modules for knowledge base inference and prior knowledge encoding, to generate responses grounded in dialog belief state and real-world knowledge for task completion. GTG is pre-trained on large amounts of raw text and human conversational data, and can be fine-tuned to complete a wide range of tasks. The hybrid approach and its variants are being developed simultaneously by multiple research teams. The primary results reported on task-oriented dialog benchmarks are very promising, demonstrating the big potential of this approach. This article provides an overview of this progress and discusses related methods and technologies that can be incorporated for building robust conversational AI systems.

arXiv:2009.03136

Black Box to White Box: Discover Model Characteristics Based on Strategic Probing

In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model information: the underlying architecture and primary training dataset. With the process in this paper, a structured set of input probes and the output of the model become the training data for a deep classifier. Two subdomains in Machine Learning are explored: image based classifiers and text transformers with GPT-2. With image classification, the focus is on exploring commonly deployed architectures and datasets available in popular public libraries. Using a single transformer architecture with multiple levels of parameters, text generation is explored by fine tuning off different datasets. Each dataset explored in image and text are distinguishable from one another. Diversity in text transformer outputs implies further research is needed to successfully classify architecture attribution in text domain.

arXiv:2009.03015

Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of such models for malicious purposes. In this paper, we study natural language watermarking as a defense to help better mark and trace the provenance of text. We introduce the Adversarial Watermarking Transformer (AWT) with a jointly trained encoder-decoder and adversarial training that, given an input text and a binary message, generates an output text that is unobtrusively encoded with the given message. We further study different training and inference strategies to achieve minimal changes to the semantics and correctness of the input text. AWT is the first end-to-end model to hide data in text by automatically learning -- without ground truth -- word substitutions along with their locations in order to encode the message. We empirically show that our model is effective in largely preserving text utility and decoding the watermark while hiding its presence against adversaries. Additionally, we demonstrate that our method is robust against a range of attacks.

arXiv:2008.12009

A Survey of Evaluation Metrics Used for NLG Systems

The success of Deep Learning has created a surge in interest in a wide a range of Natural Language Generation (NLG) tasks. Deep Learning has not only pushed the state of the art in several existing NLG tasks but has also facilitated researchers to explore various newer NLG tasks such as image captioning. Such rapid progress in NLG has necessitated the development of accurate automatic evaluation metrics that would allow us to track the progress in the field of NLG. However, unlike classification tasks, automatically evaluating NLG systems in itself is a huge challenge. Several works have shown that early heuristic-based metrics such as BLEU, ROUGE are inadequate for capturing the nuances in the different NLG tasks. The expanding number of NLG models and the shortcomings of the current metrics has led to a rapid surge in the number of evaluation metrics proposed since 2014. Moreover, various evaluation metrics have shifted from using pre-determined heuristic-based formulae to trained transformer models. This rapid change in a relatively short time has led to the need for a survey of the existing NLG metrics to help existing and new researchers to quickly come up to speed with the developments that have happened in NLG evaluation in the last few years. Through this survey, we first wish to highlight the challenges and difficulties in automatically evaluating NLG systems. Then, we provide a coherent taxonomy of the evaluation metrics to organize the existing metrics and to better understand the developments in the field. We also describe the different metrics in detail and highlight their key contributions. Later, we discuss the main shortcomings identified in the existing metrics and describe the methodology used to evaluate evaluation metrics. Finally, we discuss our suggestions and recommendations on the next steps forward to improve the automatic evaluation metrics.

arXiv:2008.10875공식 코드 · Papers with Code

ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation

Plug-and-play language models (PPLMs) enable topic-conditioned natural language generation by pairing large pre-trained generators with attribute models used to steer the predicted token distribution towards the selected topic. Despite their computational efficiency, PPLMs require large amounts of labeled texts to effectively balance generation fluency and proper conditioning, making them unsuitable for low-resource settings. We present ETC-NLG, an approach leveraging topic modeling annotations to enable fully-unsupervised End-to-end Topic-Conditioned Natural Language Generation over emergent topics in unlabeled document collections. We first test the effectiveness of our approach in a low-resource setting for Italian, evaluating the conditioning for both topic models and gold annotations. We then perform a comparative evaluation of ETC-NLG for Italian and English using a parallel corpus. Finally, we propose an automatic approach to estimate the effectiveness of conditioning on the generated utterances.

arXiv:2008.09333

Tweet to News Conversion: An Investigation into Unsupervised Controllable Text Generation

Text generator systems have become extremely popular with the advent of recent deep learning models such as encoder-decoder. Controlling the information and style of the generated output without supervision is an important and challenging Natural Language Processing (NLP) task. In this paper, we define the task of constructing a coherent paragraph from a set of disaster domain tweets, without any parallel data. We tackle the problem by building two systems in pipeline. The first system focuses on unsupervised style transfer and converts the individual tweets into news sentences. The second system stitches together the outputs from the first system to form a coherent news paragraph. We also propose a novel training mechanism, by splitting the sentences into propositions and training the second system to merge the sentences. We create a validation and test set consisting of tweet-sets and their equivalent news paragraphs to perform empirical evaluation. In a completely unsupervised setting, our model was able to achieve a BLEU score of 19.32, while successfully transferring styles and joining tweets to form a meaningful news paragraph.

arXiv:2008.08896공식 코드 · Papers with Code

Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR

Systems that generate natural language text from abstract meaning representations such as AMR are typically evaluated using automatic surface matching metrics that compare the generated texts to reference texts from which the input meaning representations were constructed. We show that besides well-known issues from which such metrics suffer, an additional problem arises when applying these metrics for AMR-to-text evaluation, since an abstract meaning representation allows for numerous surface realizations. In this work we aim to alleviate these issues by proposing $\mathcal{M}\mathcal{F}_\beta$, a decomposable metric that builds on two pillars. The first is the principle of meaning preservation $\mathcal{M}$: it measures to what extent a given AMR can be reconstructed from the generated sentence using SOTA AMR parsers and applying (fine-grained) AMR evaluation metrics to measure the distance between the original and the reconstructed AMR. The second pillar builds on a principle of (grammatical) form $\mathcal{F}$ that measures the linguistic quality of the generated text, which we implement using SOTA language models. In two extensive pilot studies we show that fulfillment of both principles offers benefits for AMR-to-text evaluation, including explainability of scores. Since $\mathcal{M}\mathcal{F}_\beta$ does not necessarily rely on gold AMRs, it may extend to other text generation tasks.

arXiv:2008.06239

Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems

Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each module with the least amount of samples (i.e., few-shots) given the high cost related to the data collection. The most common and effective technique to solve this problem is transfer learning, where large language models, either pre-trained on text or task-specific data, are fine-tuned on the few samples. These methods require fine-tuning steps and a set of parameters for each task. Differently, language models, such as GPT-2 (Radford et al., 2019) and GPT-3 (Brown et al., 2020), allow few-shot learning by priming the model with few examples. In this paper, we evaluate the priming few-shot ability of language models in the NLU, DST, DP and NLG tasks. Importantly, we highlight the current limitations of this approach, and we discuss the possible implication for future work.

arXiv:2008.07467

Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement

In the online advertising industry, the process of designing an ad creative (i.e., ad text and image) requires manual labor. Typically, each advertiser launches multiple creatives via online A/B tests to infer effective creatives for the target audience, that are then refined further in an iterative fashion. Due to the manual nature of this process, it is time-consuming to learn, refine, and deploy the modified creatives. Since major ad platforms typically run A/B tests for multiple advertisers in parallel, we explore the possibility of collaboratively learning ad creative refinement via A/B tests of multiple advertisers. In particular, given an input ad creative, we study approaches to refine the given ad text and image by: (i) generating new ad text, (ii) recommending keyphrases for new ad text, and (iii) recommending image tags (objects in image) to select new ad image. Based on A/B tests conducted by multiple advertisers, we form pairwise examples of inferior and superior ad creatives, and use such pairs to train models for the above tasks. For generating new ad text, we demonstrate the efficacy of an encoder-decoder architecture with copy mechanism, which allows some words from the (inferior) input text to be copied to the output while incorporating new words associated with higher click-through-rate. For the keyphrase and image tag recommendation task, we demonstrate the efficacy of a deep relevance matching model, as well as the relative robustness of ranking approaches compared to ad text generation in cold-start scenarios with unseen advertisers. We also share broadly applicable insights from our experiments using data from the Yahoo Gemini ad platform.

arXiv:2008.05122공식 코드 · Papers with Code

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it perform poorly? What happens under a controlled change in the input? LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis. We include case studies for a diverse set of workflows, including exploring counterfactuals for sentiment analysis, measuring gender bias in coreference systems, and exploring local behavior in text generation. LIT supports a wide range of models--including classification, seq2seq, and structured prediction--and is highly extensible through a declarative, framework-agnostic API. LIT is under active development, with code and full documentation available at https://github.com/pair-code/lit.

arXiv:2008.03082

Perception Score, A Learned Metric for Open-ended Text Generation Evaluation

Automatic evaluation for open-ended natural language generation tasks remains a challenge. Existing metrics such as BLEU show a low correlation with human judgment. We propose a novel and powerful learning-based evaluation metric: Perception Score. The method measures the overall quality of the generation and scores holistically instead of only focusing on one evaluation criteria, such as word overlapping. Moreover, it also shows the amount of uncertainty about its evaluation result. By connecting the uncertainty, Perception Score gives a more accurate evaluation for the generation system. Perception Score provides state-of-the-art results on two conditional generation tasks and two unconditional generation tasks.

arXiv:2008.01548

Defining and Evaluating Fair Natural Language Generation

Our work focuses on the biases that emerge in the natural language generation (NLG) task of sentence completion. In this paper, we introduce a framework of fairness for NLG followed by an evaluation of gender biases in two state-of-the-art language models. Our analysis provides a theoretical formulation for biases in NLG and empirical evidence that existing language generation models embed gender bias.