PyTorchKR Papers

최신 논문

총 6,088편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2010.01694공식 코드 · Papers with Code

On Losses for Modern Language Models

BERT set many state-of-the-art results over varied NLU benchmarks by pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP), the latter of which has been highly criticized. In this paper, we 1) clarify NSP's effect on BERT pre-training, 2) explore fourteen possible auxiliary pre-training tasks, of which seven are novel to modern language models, and 3) investigate different ways to include multiple tasks into pre-training. We show that NSP is detrimental to training due to its context splitting and shallow semantic signal. We also identify six auxiliary pre-training tasks -- sentence ordering, adjacent sentence prediction, TF prediction, TF-IDF prediction, a FastSent variant, and a Quick Thoughts variant -- that outperform a pure MLM baseline. Finally, we demonstrate that using multiple tasks in a multi-task pre-training framework provides better results than using any single auxiliary task. Using these methods, we outperform BERT Base on the GLUE benchmark using fewer than a quarter of the training tokens.

arXiv:2010.01611공식 코드 · Papers with Code

When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised

Question Answering (QA) is key for making possible a robust communication between human and machine. Modern language models used for QA have surpassed the human-performance in several essential tasks; however, these models require large amounts of human-generated training data which are costly and time-consuming to create. This paper studies augmenting human-made datasets with synthetic data as a way of surmounting this problem. A state-of-the-art model based on deep transformers is used to inspect the impact of using synthetic answerable and unanswerable questions to complement a well-known human-made dataset. The results indicate a tangible improvement in the performance of the language model (measured in terms of F1 and EM scores) trained on the mixed dataset. Specifically, unanswerable question-answers prove more effective in boosting the model: the F1 score gain from adding to the original dataset the answerable, unanswerable, and combined question-answers were 1.3%, 5.0%, and 6.7%, respectively. [Link to the Github repository: https://github.com/lnikolenko/EQA]

arXiv:2010.02123공식 코드 · Papers with Code

Lifelong Language Knowledge Distillation

It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To address this issue, we present Lifelong Language Knowledge Distillation (L2KD), a simple but efficient method that can be easily applied to existing LLL architectures in order to mitigate the degradation. Specifically, when the LLL model is trained on a new task, we assign a teacher model to first learn the new task, and pass the knowledge to the LLL model via knowledge distillation. Therefore, the LLL model can better adapt to the new task while keeping the previously learned knowledge. Experiments show that the proposed L2KD consistently improves previous state-of-the-art models, and the degradation comparing to multi-task models in LLL tasks is well mitigated for both sequence generation and text classification tasks.

arXiv:2010.01891공식 코드 · Papers with Code

A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese

Semantic parsing is an important NLP task. However, Vietnamese is a low-resource language in this research area. In this paper, we present the first public large-scale Text-to-SQL semantic parsing dataset for Vietnamese. We extend and evaluate two strong semantic parsing baselines EditSQL (Zhang et al., 2019) and IRNet (Guo et al., 2019) on our dataset. We compare the two baselines with key configurations and find that: automatic Vietnamese word segmentation improves the parsing results of both baselines; the normalized pointwise mutual information (NPMI) score (Bouma, 2009) is useful for schema linking; latent syntactic features extracted from a neural dependency parser for Vietnamese also improve the results; and the monolingual language model PhoBERT for Vietnamese (Nguyen and Nguyen, 2020) helps produce higher performances than the recent best multilingual language model XLM-R (Conneau et al., 2020).

arXiv:2010.00784공식 코드 · Papers with Code

An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training

Pre-training large language models has become a standard in the natural language processing community. Such models are pre-trained on generic data (e.g. BookCorpus and English Wikipedia) and often fine-tuned on tasks in the same domain. However, in order to achieve state-of-the-art performance on out of domain tasks such as clinical named entity recognition and relation extraction, additional in domain pre-training is required. In practice, staged multi-domain pre-training presents performance deterioration in the form of catastrophic forgetting (CF) when evaluated on a generic benchmark such as GLUE. In this paper we conduct an empirical investigation into known methods to mitigate CF. We find that elastic weight consolidation provides best overall scores yielding only a 0.33% drop in performance across seven generic tasks while remaining competitive in bio-medical tasks. Furthermore, we explore gradient and latent clustering based data selection techniques to improve coverage when using elastic weight consolidation and experience replay methods.

arXiv:2010.00770공식 코드 · Papers with Code

XDA: Accurate, Robust Disassembly with Transfer Learning

Accurate and robust disassembly of stripped binaries is challenging. The root of the difficulty is that high-level structures, such as instruction and function boundaries, are absent in stripped binaries and must be recovered based on incomplete information. Current disassembly approaches rely on heuristics or simple pattern matching to approximate the recovery, but these methods are often inaccurate and brittle, especially across different compiler optimizations. We present XDA, a transfer-learning-based disassembly framework that learns different contextual dependencies present in machine code and transfers this knowledge for accurate and robust disassembly. We design a self-supervised learning task motivated by masked Language Modeling to learn interactions among byte sequences in binaries. The outputs from this task are byte embeddings that encode sophisticated contextual dependencies between input binaries' byte tokens, which can then be finetuned for downstream disassembly tasks. We evaluate XDA's performance on two disassembly tasks, recovering function boundaries and assembly instructions, on a collection of 3,121 binaries taken from SPEC CPU2017, SPEC CPU2006, and the BAP corpus. The binaries are compiled by GCC, ICC, and MSVC on x86/x64 Windows and Linux platforms over 4 optimization levels. XDA achieves 99.0% and 99.7% F1 score at recovering function boundaries and instructions, respectively, surpassing the previous state-of-the-art on both tasks. It also maintains speed on par with the fastest ML-based approach and is up to 38x faster than hand-written disassemblers like IDA Pro. We release the code of XDA at https://github.com/CUMLSec/XDA.

arXiv:2010.00677공식 코드 · Papers with Code

Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding

Linguistic steganography studies how to hide secret messages in natural language cover texts. Traditional methods aim to transform a secret message into an innocent text via lexical substitution or syntactical modification. Recently, advances in neural language models (LMs) enable us to directly generate cover text conditioned on the secret message. In this study, we present a new linguistic steganography method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model. We formally analyze the statistical imperceptibility of this method and empirically show it outperforms the previous state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics, respectively. Finally, human evaluations show that 51% of generated cover texts can indeed fool eavesdroppers.

arXiv:2010.01057공식 코드 · Papers with Code

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention

Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores. The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. In particular, it obtains state-of-the-art results on five well-known datasets: Open Entity (entity typing), TACRED (relation classification), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), and SQuAD 1.1 (extractive question answering). Our source code and pretrained representations are available at https://github.com/studio-ousia/luke.

arXiv:2010.00198공식 코드 · Papers with Code

Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models

Studies on the Named Entity Recognition (NER) task have shown outstanding results that reach human parity on input texts with correct text formattings, such as with proper punctuation and capitalization. However, such conditions are not available in applications where the input is speech, because the text is generated from a speech recognition system (ASR), and that the system does not consider the text formatting. In this paper, we (1) presented the first Vietnamese speech dataset for NER task, and (2) the first pre-trained public large-scale monolingual language model for Vietnamese that achieved the new state-of-the-art for the Vietnamese NER task by 1.3% absolute F1 score comparing to the latest study. And finally, (3) we proposed a new pipeline for NER task from speech that overcomes the text formatting problem by introducing a text capitalization and punctuation recovery model (CaPu) into the pipeline. The model takes input text from an ASR system and performs two tasks at the same time, producing proper text formatting that helps to improve NER performance. Experimental results indicated that the CaPu model helps to improve by nearly 4% of F1-score.

arXiv:2009.14654공식 코드 · Papers with Code

OWL2Vec*: Embedding of OWL Ontologies

Semantic embedding of knowledge graphs has been widely studied and used for prediction and statistical analysis tasks across various domains such as Natural Language Processing and the Semantic Web. However, less attention has been paid to developing robust methods for embedding OWL (Web Ontology Language) ontologies which can express a much wider range of semantics than knowledge graphs and have been widely adopted in domains such as bioinformatics. In this paper, we propose a random walk and word embedding based ontology embedding method named OWL2Vec*, which encodes the semantics of an OWL ontology by taking into account its graph structure, lexical information and logical constructors. Our empirical evaluation with three real world datasets suggests that OWL2Vec* benefits from these three different aspects of an ontology in class membership prediction and class subsumption prediction tasks. Furthermore, OWL2Vec* often significantly outperforms the state-of-the-art methods in our experiments.

arXiv:2009.14794공식 코드 · Papers with Code

Rethinking Attention with Performers

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness. To approximate softmax attention-kernels, Performers use a novel Fast Attention Via positive Orthogonal Random features approach (FAVOR+), which may be of independent interest for scalable kernel methods. FAVOR+ can be also used to efficiently model kernelizable attention mechanisms beyond softmax. This representational power is crucial to accurately compare softmax with other kernels for the first time on large-scale tasks, beyond the reach of regular Transformers, and investigate optimal attention-kernels. Performers are linear architectures fully compatible with regular Transformers and with strong theoretical guarantees: unbiased or nearly-unbiased estimation of the attention matrix, uniform convergence and low estimation variance. We tested Performers on a rich set of tasks stretching from pixel-prediction through text models to protein sequence modeling. We demonstrate competitive results with other examined efficient sparse and dense attention methods, showcasing effectiveness of the novel attention-learning paradigm leveraged by Performers.

arXiv:2009.14167공식 코드 · Papers with Code

Contrastive Distillation on Intermediate Representations for Language Model Compression

Existing language model compression methods mostly use a simple L2 loss to distill knowledge in the intermediate representations of a large BERT model to a smaller one. Although widely used, this objective by design assumes that all the dimensions of hidden representations are independent, failing to capture important structural knowledge in the intermediate layers of the teacher network. To achieve better distillation efficacy, we propose Contrastive Distillation on Intermediate Representations (CoDIR), a principled knowledge distillation framework where the student is trained to distill knowledge through intermediate layers of the teacher via a contrastive objective. By learning to distinguish positive sample from a large set of negative samples, CoDIR facilitates the student's exploitation of rich information in teacher's hidden layers. CoDIR can be readily applied to compress large-scale language models in both pre-training and finetuning stages, and achieves superb performance on the GLUE benchmark, outperforming state-of-the-art compression methods.

arXiv:2009.14109공식 코드 · Papers with Code

Improving Low Compute Language Modeling with In-Domain Embedding Initialisation

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation of rare words, and this pattern holds across several different domains. In the process, we show that the standard convention of tying input and output embeddings does not improve perplexity when initializing with embeddings trained on in-domain data.

arXiv:2009.12404공식 코드 · Papers with Code

Visually Grounded Compound PCFGs

Exploiting visual groundings for language understanding has recently been drawing much attention. In this work, we study visually grounded grammar induction and learn a constituency parser from both unlabeled text and its visual groundings. Existing work on this task (Shi et al., 2019) optimizes a parser via Reinforce and derives the learning signal only from the alignment of images and sentences. While their model is relatively accurate overall, its error distribution is very uneven, with low performance on certain constituents types (e.g., 26.2% recall on verb phrases, VPs) and high on others (e.g., 79.6% recall on noun phrases, NPs). This is not surprising as the learning signal is likely insufficient for deriving all aspects of phrase-structure syntax and gradient estimates are noisy. We show that using an extension of probabilistic context-free grammar model we can do fully-differentiable end-to-end visually grounded learning. Additionally, this enables us to complement the image-text alignment loss with a language modeling objective. On the MSCOCO test captions, our model establishes a new state of the art, outperforming its non-grounded version and, thus, confirming the effectiveness of visual groundings in constituency grammar induction. It also substantially outperforms the previous grounded model, with largest improvements on more `abstract' categories (e.g., +55.1% recall on VPs).

arXiv:2009.13102공식 코드 · Papers with Code

Deep Transformers with Latent Depth

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection. As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair. The proposed method alleviates the vanishing gradient issue and enables stable training of deep Transformers (e.g. 100 layers). We evaluate on WMT English-German machine translation and masked language modeling tasks, where our method outperforms existing approaches for training deeper Transformers. Experiments on multilingual machine translation demonstrate that this approach can effectively leverage increased model capacity and bring universal improvement for both many-to-one and one-to-many translation with diverse language pairs.

arXiv:2009.11963공식 코드 · Papers with Code

Toward a Thermodynamics of Meaning

As language models such as GPT-3 become increasingly successful at generating realistic text, questions about what purely text-based modeling can learn about the world have become more urgent. Is text purely syntactic, as skeptics argue? Or does it in fact contain some semantic information that a sufficiently sophisticated language model could use to learn about the world without any additional inputs? This paper describes a new model that suggests some qualified answers to those questions. By theorizing the relationship between text and the world it describes as an equilibrium relationship between a thermodynamic system and a much larger reservoir, this paper argues that even very simple language models do learn structural facts about the world, while also proposing relatively precise limits on the nature and extent of those facts. This perspective promises not only to answer questions about what language models actually learn, but also to explain the consistent and surprising success of cooccurrence prediction as a meaning-making strategy in AI.

arXiv:2009.11523공식 코드 · Papers with Code

Grounded Compositional Outputs for Adaptive Language Modeling

Language models have emerged as a central component across NLP, and a great deal of progress depends on the ability to cheaply adapt them (e.g., through finetuning) to new domains and tasks. A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size and is part of what makes it resistant to such adaptation. Prior work has used compositional input embeddings based on surface forms to ameliorate this issue. In this work, we go one step beyond and propose a fully compositional output embedding layer for language models, which is further grounded in information from a structured lexicon (WordNet), namely semantically related words and free-text definitions. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary. We evaluate the model on conventional language modeling as well as challenging cross-domain settings with an open vocabulary, finding that it matches or outperforms previous state-of-the-art output embedding methods and adaptation approaches. Our analysis attributes the improvements to sample efficiency: our model is more accurate for low-frequency words.

arXiv:2009.10684공식 코드 · Papers with Code

Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!

Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance comparison to previous work. In this paper, we first identify several patterns of invalid comparisons in published papers and describe them to avoid their propagation. We then propose a small empirical study to quantify the impact of the most common mistake and evaluate it leads to overestimating the final RE performance by around 5% on ACE05. We also seize this opportunity to study the unexplored ablations of two recent developments: the use of language model pretraining (specifically BERT) and span-level NER. This meta-analysis emphasizes the need for rigor in the report of both the evaluation setting and the datasets statistics and we call for unifying the evaluation setting in end-to-end RE.

arXiv:2009.09025공식 코드 · Papers with Code

COMET: A Neural Framework for MT Evaluation

We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in cross-lingual pretrained language modeling resulting in highly multilingual and adaptable MT evaluation models that exploit information from both the source input and a target-language reference translation in order to more accurately predict MT quality. To showcase our framework, we train three models with different types of human judgements: Direct Assessments, Human-mediated Translation Edit Rate and Multidimensional Quality Metrics. Our models achieve new state-of-the-art performance on the WMT 2019 Metrics shared task and demonstrate robustness to high-performing systems.

arXiv:2009.09343공식 코드 · Papers with Code

Dual-path CNN with Max Gated block for Text-Based Person Re-identification

Text-based person re-identification(Re-id) is an important task in video surveillance, which consists of retrieving the corresponding person's image given a textual description from a large gallery of images. It is difficult to directly match visual contents with the textual descriptions due to the modality heterogeneity. On the one hand, the textual embeddings are not discriminative enough, which originates from the high abstraction of the textual descriptions. One the other hand,Global average pooling (GAP) is commonly utilized to extract more general or smoothed features implicitly but ignores salient local features, which are more important for the cross-modal matching problem. With that in mind, a novel Dual-path CNN with Max Gated block (DCMG) is proposed to extract discriminative word embeddings and make visual-textual association concern more on remarkable features of both modalities. The proposed framework is based on two deep residual CNNs jointly optimized with cross-modal projection matching (CMPM) loss and cross-modal projection classification (CMPC) loss to embed the two modalities into a joint feature space. First, the pre-trained language model, BERT, is combined with the convolutional neural network (CNN) to learn better word embeddings in the text-to-image matching domain. Second, the global Max pooling (GMP) layer is applied to make the visual-textual features focus more on the salient part. To further alleviate the noise of the maxed-pooled features, the gated block (GB) is proposed to produce an attention map that focuses on meaningful features of both modalities. Finally, extensive experiments are conducted on the benchmark dataset, CUHK-PEDES, in which our approach achieves the rank-1 score of 55.81% and outperforms the state-of-the-art method by 1.3%.