PyTorchKR Papers

최신 논문

총 661편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.00071공식 코드 · Papers with Code

Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark

Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires evaluation metrics that can quantify its prevalence. To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (BEGIN), comprised of 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora. We collect human annotations assessing the extent to which the models' responses can be attributed to the given background information. We then use BEGIN to analyze eight evaluation metrics. We find that these metrics rely on spurious correlations, do not reliably distinguish attributable abstractive responses from unattributable ones, and perform substantially worse when the knowledge source is longer. Our findings underscore the need for more sophisticated and robust evaluation metrics for knowledge-grounded dialogue. We make BEGIN publicly available at https://github.com/google/BEGIN-dataset.

arXiv:2105.00823공식 코드 · Papers with Code

Switching Contexts: Transportability Measures for NLP

This paper explores the topic of transportability, as a sub-area of generalisability. By proposing the utilisation of metrics based on well-established statistics, we are able to estimate the change in performance of NLP models in new contexts. Defining a new measure for transportability may allow for better estimation of NLP system performance in new domains, and is crucial when assessing the performance of NLP systems in new tasks and domains. Through several instances of increasing complexity, we demonstrate how lightweight domain similarity measures can be used as estimators for the transportability in NLP applications. The proposed transportability measures are evaluated in the context of Named Entity Recognition and Natural Language Inference tasks.

arXiv:2104.10813공식 코드 · Papers with Code

Finding Fuzziness in Neural Network Models of Language Processing

Humans often communicate by using imprecise language, suggesting that fuzzy concepts with unclear boundaries are prevalent in language use. In this paper, we test the extent to which models trained to capture the distributional statistics of language show correspondence to fuzzy-membership patterns. Using the task of natural language inference, we test a recent state of the art model on the classical case of temperature, by examining its mapping of temperature data to fuzzy-perceptions such as "cool", "hot", etc. We find the model to show patterns that are similar to classical fuzzy-set theoretic formulations of linguistic hedges, albeit with a substantial amount of noise, suggesting that models trained solely on language show promise in encoding fuzziness.

arXiv:2104.08821공식 코드 · Papers with Code

SimCSE: Simple Contrastive Learning of Sentence Embeddings

This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective, with only standard dropout used as noise. This simple method works surprisingly well, performing on par with previous supervised counterparts. We find that dropout acts as minimal data augmentation, and removing it leads to a representation collapse. Then, we propose a supervised approach, which incorporates annotated pairs from natural language inference datasets into our contrastive learning framework by using "entailment" pairs as positives and "contradiction" pairs as hard negatives. We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman's correlation respectively, a 4.2% and 2.2% improvement compared to the previous best results. We also show -- both theoretically and empirically -- that the contrastive learning objective regularizes pre-trained embeddings' anisotropic space to be more uniform, and it better aligns positive pairs when supervised signals are available.

arXiv:2104.08731공식 코드 · Papers with Code

Can NLI Models Verify QA Systems' Predictions?

To build robust question answering systems, we need the ability to verify whether answers to questions are truly correct, not just "good enough" in the context of imperfect QA datasets. We explore the use of natural language inference (NLI) as a way to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question). We leverage large pre-trained models and recent prior datasets to construct powerful question converter and decontextualization modules, which can reformulate QA instances as premise-hypothesis pairs with very high reliability. Then, by combining standard NLI datasets with NLI examples automatically derived from QA training data, we can train NLI models to judge the correctness of QA models' proposed answers. We show that our NLI approach can generally improve the confidence estimation of a QA model across different domains, evaluated in a selective QA setting. Careful manual analysis over the predictions of our NLI model shows that it can further identify cases where the QA model produces the right answer for the wrong reason, or where the answer cannot be verified as addressing all aspects of the question.

arXiv:2104.08676공식 코드 · Papers with Code

Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning

We introduce distributed NLI, a new NLU task with a goal to predict the distribution of human judgements for natural language inference. We show that by applying additional distribution estimation methods, namely, Monte Carlo (MC) Dropout, Deep Ensemble, Re-Calibration, and Distribution Distillation, models can capture human judgement distribution more effectively than the softmax baseline. We show that MC Dropout is able to achieve decent performance without any distribution annotations while Re-Calibration can give further improvements with extra distribution annotations, suggesting the value of multiple annotations for one example in modeling the distribution of human judgements. Despite these improvements, the best results are still far below the estimated human upper-bound, indicating that predicting the distribution of human judgements is still an open, challenging problem with a large room for improvements. We showcase the common errors for MC Dropout and Re-Calibration. Finally, we give guidelines on the usage of these methods with different levels of data availability and encourage future work on modeling the human opinion distribution for language reasoning. Our code and data are publicly available at https://github.com/easonnie/ChaosNLI

arXiv:2104.08142공식 코드 · Papers with Code

Supervising Model Attention with Human Explanations for Robust Natural Language Inference

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from learning these biases, which can result in restrictive models and lower performance. We instead investigate teaching the model how a human would approach the NLI task, in order to learn features that will generalise better to previously unseen examples. Using natural language explanations, we supervise the model's attention weights to encourage more attention to be paid to the words present in the explanations, significantly improving model performance. Our experiments show that the in-distribution improvements of this method are also accompanied by out-of-distribution improvements, with the supervised models learning from features that generalise better to other NLI datasets. Analysis of the model indicates that human explanations encourage increased attention on the important words, with more attention paid to words in the premise and less attention paid to punctuation and stop-words.

arXiv:2104.07705공식 코드 · Papers with Code

How to Train BERT with an Academic Budget

While large language models a la BERT are used ubiquitously in NLP, pretraining them is considered a luxury that only a few well-funded industry labs can afford. How can one train such models with a more modest budget? We present a recipe for pretraining a masked language model in 24 hours using a single low-end deep learning server. We demonstrate that through a combination of software optimizations, design choices, and hyperparameter tuning, it is possible to produce models that are competitive with BERT-base on GLUE tasks at a fraction of the original pretraining cost.

arXiv:2104.04751공식 코드 · Papers with Code

NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance

Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences remains unclear. We propose a new diagnostics test suite which allows to assess whether a dataset constitutes a good testbed for evaluating the models' meaning understanding capabilities. We specifically apply controlled corruption transformations to widely used benchmarks (MNLI and ANLI), which involve removing entire word classes and often lead to non-sensical sentence pairs. If model accuracy on the corrupted data remains high, then the dataset is likely to contain statistical biases and artefacts that guide prediction. Inversely, a large decrease in model accuracy indicates that the original dataset provides a proper challenge to the models' reasoning capabilities. Hence, our proposed controls can serve as a crash test for developing high quality data for NLI tasks.

arXiv:2104.04998공식 코드 · Papers with Code

Unsupervised Learning of Explainable Parse Trees for Improved Generalisation

Recursive neural networks (RvNN) have been shown useful for learning sentence representations and helped achieve competitive performance on several natural language inference tasks. However, recent RvNN-based models fail to learn simple grammar and meaningful semantics in their intermediate tree representation. In this work, we propose an attention mechanism over Tree-LSTMs to learn more meaningful and explainable parse tree structures. We also demonstrate the superior performance of our proposed model on natural language inference, semantic relatedness, and sentiment analysis tasks and compare them with other state-of-the-art RvNN based methods. Further, we present a detailed qualitative and quantitative analysis of the learned parse trees and show that the discovered linguistic structures are more explainable, semantically meaningful, and grammatically correct than recent approaches. The source code of the paper is available at https://github.com/atul04/Explainable-Latent-Structures-Using-Attention.

arXiv:2104.04916공식 코드 · Papers with Code

Cross-Lingual Word Embedding Refinement by $\ell_{1}$ Norm Optimisation

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the $\ell_{2}$ norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. $\ell_{1}$ norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the $\ell_{1}$ refinement substantially outperforms four state-of-the-art baselines in both supervised and unsupervised settings. It is therefore recommended that this strategy be adopted as a standard for CLWE methods.

arXiv:2104.04670공식 코드 · Papers with Code

Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label description "Does the user like this movie?", and ask whether the next word is "yes" or "no". However, the next word prediction training objective is still misaligned with the target zero-shot learning objective. To address this weakness, we propose meta-tuning, which directly optimizes the zero-shot learning objective by fine-tuning pre-trained language models on a collection of datasets. We focus on classification tasks, and construct the meta-dataset by aggregating 43 existing datasets and annotating 441 label descriptions in a question-answering (QA) format. When evaluated on unseen tasks, meta-tuned models outperform a same-sized QA model and the previous SOTA zero-shot learning system based on natural language inference. Additionally, increasing parameter count from 220M to 770M improves AUC-ROC scores by 6.3%, and we forecast that even larger models would perform better. Therefore, measuring zero-shot learning performance on language models out-of-the-box might underestimate their true potential, and community-wide efforts on aggregating datasets and unifying their formats can help build models that answer prompts better.

arXiv:2104.04488공식 코드 · Papers with Code

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features. However, for models with text pairs as inputs (e.g., paraphrase identification), existing methods are not sufficient to capture feature interactions between two texts and their simple extension of computing all word-pair interactions between two texts is computationally inefficient. In this work, we propose the Group Mask (GMASK) method to implicitly detect word correlations by grouping correlated words from the input text pair together and measure their contribution to the corresponding NLP tasks as a whole. The proposed method is evaluated with two different model architectures (decomposable attention model and BERT) across four datasets, including natural language inference and paraphrase identification tasks. Experiments show the effectiveness of GMASK in providing faithful explanations to these models.

arXiv:2104.04243공식 코드 · Papers with Code

Incorporating External Knowledge to Enhance Tabular Reasoning

Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural language inference. We propose easy and effective modifications to how information is presented to a model for this task. We show via systematic experiments that these strategies substantially improve tabular inference performance.

arXiv:2104.03071공식 코드 · Papers with Code

BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with Tables

Recently, there has been an interest in factual verification and prediction over structured data like tables and graphs. To circumvent any false news incident, it is necessary to not only model and predict over structured data efficiently but also to explain those predictions. In this paper, as part of the SemEval-2021 Task 9, we tackle the problem of fact verification and evidence finding over tabular data. There are two subtasks. Given a table and a statement/fact, subtask A determines whether the statement is inferred from the tabular data, and subtask B determines which cells in the table provide evidence for the former subtask. We make a comparison of the baselines and state-of-the-art approaches over the given SemTabFact dataset. We also propose a novel approach CellBERT to solve evidence finding as a form of the Natural Language Inference task. We obtain a 3-way F1 score of 0.69 on subtask A and an F1 score of 0.65 on subtask B.

arXiv:2104.01666공식 코드 · Papers with Code

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning

Exploiting label hierarchies has become a promising approach to tackling the zero-shot multi-label text classification (ZS-MTC) problem. Conventional methods aim to learn a matching model between text and labels, using a graph encoder to incorporate label hierarchies to obtain effective label representations \cite{rios2018few}. More recently, pretrained models like BERT \cite{devlin2018bert} have been used to convert classification tasks into a textual entailment task \cite{yin-etal-2019-benchmarking}. This approach is naturally suitable for the ZS-MTC task. However, pretrained models are underexplored in the existing work because they do not generate individual vector representations for text or labels, making it unintuitive to combine them with conventional graph encoding methods. In this paper, we explore to improve pretrained models with label hierarchies on the ZS-MTC task. We propose a Reinforced Label Hierarchy Reasoning (RLHR) approach to encourage interdependence among labels in the hierarchies during training. Meanwhile, to overcome the weakness of flat predictions, we design a rollback algorithm that can remove logical errors from predictions during inference. Experimental results on three real-life datasets show that our approach achieves better performance and outperforms previous non-pretrained methods on the ZS-MTC task.

arXiv:2103.08541공식 코드 · Papers with Code

Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence

Typical fact verification models use retrieved written evidence to verify claims. Evidence sources, however, often change over time as more information is gathered and revised. In order to adapt, models must be sensitive to subtle differences in supporting evidence. We present VitaminC, a benchmark infused with challenging cases that require fact verification models to discern and adjust to slight factual changes. We collect over 100,000 Wikipedia revisions that modify an underlying fact, and leverage these revisions, together with additional synthetically constructed ones, to create a total of over 400,000 claim-evidence pairs. Unlike previous resources, the examples in VitaminC are contrastive, i.e., they contain evidence pairs that are nearly identical in language and content, with the exception that one supports a given claim while the other does not. We show that training using this design increases robustness -- improving accuracy by 10% on adversarial fact verification and 6% on adversarial natural language inference (NLI). Moreover, the structure of VitaminC leads us to define additional tasks for fact-checking resources: tagging relevant words in the evidence for verifying the claim, identifying factual revisions, and providing automatic edits via factually consistent text generation.

arXiv:2102.12206공식 코드 · Papers with Code

PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains

Natural Language Processing algorithms have made incredible progress, but they still struggle when applied to out-of-distribution examples. We address a challenging and underexplored version of this domain adaptation problem, where an algorithm is trained on several source domains, and then applied to examples from unseen domains that are unknown at training time. Particularly, no examples, labeled or unlabeled, or any other knowledge about the target domain are available to the algorithm at training time. We present PADA: An example-based autoregressive Prompt learning algorithm for on-the-fly Any-Domain Adaptation, based on the T5 language model. Given a test example, PADA first generates a unique prompt for it and then, conditioned on this prompt, labels the example with respect to the NLP prediction task. PADA is trained to generate a prompt which is a token sequence of unrestricted length, consisting of Domain Related Features (DRFs) that characterize each of the source domains. Intuitively, the generated prompt is a unique signature that maps the test example to a semantic space spanned by the source domains. In experiments with 3 tasks (text classification and sequence tagging), for a total of 14 multi-source adaptation scenarios, PADA substantially outperforms strong baselines.

arXiv:2102.08597공식 코드 · Papers with Code

Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters

Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, "fully-connected layers with Quaternions" (4D hypercomplex numbers), which replace real-valued matrix multiplications in fully-connected layers with Hamilton products of Quaternions, both enjoy parameter savings with only 1/4 learnable parameters and achieve comparable performance in various applications. However, one key caveat is that hypercomplex space only exists at very few predefined dimensions (4D, 8D, and 16D). This restricts the flexibility of models that leverage hypercomplex multiplications. To this end, we propose parameterizing hypercomplex multiplications, allowing models to learn multiplication rules from data regardless of whether such rules are predefined. As a result, our method not only subsumes the Hamilton product, but also learns to operate on any arbitrary nD hypercomplex space, providing more architectural flexibility using arbitrarily $1/n$ learnable parameters compared with the fully-connected layer counterpart. Experiments of applications to the LSTM and Transformer models on natural language inference, machine translation, text style transfer, and subject verb agreement demonstrate architectural flexibility and effectiveness of the proposed approach.

arXiv:2102.05331공식 코드 · Papers with Code

Language Models for Lexical Inference in Context

Lexical inference in context (LIiC) is the task of recognizing textual entailment between two very similar sentences, i.e., sentences that only differ in one expression. It can therefore be seen as a variant of the natural language inference task that is focused on lexical semantics. We formulate and evaluate the first approaches based on pretrained language models (LMs) for this task: (i) a few-shot NLI classifier, (ii) a relation induction approach based on handcrafted patterns expressing the semantics of lexical inference, and (iii) a variant of (ii) with patterns that were automatically extracted from a corpus. All our approaches outperform the previous state of the art, showing the potential of pretrained LMs for LIiC. In an extensive analysis, we investigate factors of success and failure of our three approaches.