Artificial Neural networks are mathematical models at their core. This truismpresents some fundamental difficulty when networks are tasked with Natural Language Processing. A key problem lies in measuring the similarity or distance among vectors in NLP embedding space, since the mathematical concept of distance does not always agree with the linguistic concept. We suggest that the best way to measure linguistic distance among vectors is by employing the Language Model (LM) that created them. We introduce Language Model Distance (LMD) for measuring accuracy of vector transformations based on the Distributional Hypothesis ( LMD Accuracy ). We show the efficacy of this metric by applying it to a simple neural network learning the Procrustes algorithm for bilingual word mapping.
Qatar Computing Research Institute（卡塔尔计算研究所）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；Dalhousie University（达尔豪斯大学）
We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the representational space using hierarchical clustering. We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its fine-tuned version. We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information. We perform a thorough analy…
Meaning is context-dependent, but many properties of language (should) remain the same even if we transform the context. For example, sentiment, entailment, or speaker properties should be the same in a translation and original of a text. We introduce language invariant properties: i.e., properties that should not change when we transform text, and how they can be used to quantitatively evaluate the robustness of transformation algorithms. We use translation and paraphrasing as transformation examples, but our findings apply more broadly to any transformation. Our results indicate that many NL…
Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language Processing (NLP), the augmentation methods used in creating similar pairs with regard to contrastive learning (CL) assumptions are challenging. This is because, even simply modifying a word in the input might change the semantic meaning of the sentence, and hence, would violate the distributional hypothesis. In this review paper, we formalize the contrastiv…
University of California, Los Angeles（加州大学洛杉矶分校）；Virginia Tech（弗吉尼亚理工大学）
The vast majority of text transformation techniques in NLP are inherently limited in their ability to expand input space coverage due to an implicit constraint to preserve the original class label. In this work, we propose the notion of sibylvariance (SIB) to describe the broader set of transforms that relax the label-preserving constraint, knowably vary the expected class, and lead to significantly more diverse input distributions. We offer a unified framework to organize all data transformations, including two types of SIB: (1) Transmutations convert one discrete kind into another, (2) Mixtu…
English Natural Language Understanding (NLU) systems have achieved great performances and even outperformed humans on benchmarks like GLUE and SuperGLUE. However, these benchmarks contain only textbook Standard American English (SAE). Other dialects have been largely overlooked in the NLP community. This leads to biased and inequitable NLU systems that serve only a sub-population of speakers. To understand disparities in current models and to facilitate more dialect-competent NLU systems, we introduce the VernAcular Language Understanding Evaluation (VALUE) benchmark, a challenging variant of …
Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
Embeddings are generic representations that are useful for many NLP tasks. In this paper, we introduce DENSIFIER, a method that learns an orthogonal transformation of the embedding space that focuses the information relevant for a task in an ultradense subspace of a dimensionality that is smaller by a factor of 100 than the original space. We show that ultradense embeddings generated by DENSIFIER reach state of the art on a lexicon creation task in which words are annotated with three types of lexical information - sentiment, concreteness and frequency. On the SemEval2015 10B sentiment analysi…
Stemming is an integral part of Natural Language Processing (NLP). It's a preprocessing step in almost every NLP application. Arguably, the most important usage of stemming is in Information Retrieval (IR). While there are lots of work done on stemming in languages like English, Nepali stemming has only a few works. This study focuses on creating a Rule Based stemmer for Nepali text. Specifically, it is an affix stripping system that identifies two different class of suffixes in Nepali grammar and strips them separately. Only a single negativity prefix (Na) is identified and stripped. This stu…
Ubiquitous Knowledge Processing Lab (UKP-TUDA)（普适知识处理实验室（UKP-TUDA））；Hessian Center for AI (hessian.AI)（黑森人工智能中心（hessian.AI））；Technical University of Darmstadt（达姆施塔特工业大学）
Nnamdi Azikiwe University（纳姆迪·阿齐基韦大学）；Federal College of Education (Technical), Umunze（乌蒙泽联邦教育学院（技术类））；University of Sheffield（谢菲尔德大学）
Most languages, especially in Africa, have fewer or no established part-of-speech (POS) tagged corpus. However, POS tagged corpus is essential for natural language processing (NLP) to support advanced researches such as machine translation, speech recognition, etc. Even in cases where there is no POS tagged corpus, there are some languages for which parallel texts are available online. The task of POS tagging a new language corpus with a new tagset usually face a bootstrapping problem at the initial stages of the annotation process. The unavailability of automatic taggers to help the human ann…
Ionian University（伊奥尼亚大学）；University of the Aegean（爱琴海大学）
The domain of natural language processing (NLP), which has greatly evolved over the last years, has highly benefited from the recent developments in word and sentence embeddings. Such embeddings enable the transformation of complex NLP tasks, like semantic similarity or Question and Answering (Q&A), into much simpler to perform vector comparisons. However, such a problem transformation raises new challenges like the efficient comparison of embeddings and their manipulation. In this work, we will discuss about various word and sentence embeddings algorithms, we will select a sentence embedding …
Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and does not overtrain easily. However, it does have a serious drawback: the training time is often intorelably long, especially on the large corpora which are often used in NLP. In this paper, we present a novel and realistic method for speeding up the training time of a transformation-based learner without sacrificing performance. The paper compares and contrasts the training time needed and perform…
The Rise of AfricaNLP: A Survey of Contributions, Contributors, Community Impact, and Bibliometric Analysis
Instituto Politécnico Nacional（国立理工学院）；University of Gondar（贡德尔大学）；Northwest University Kano（卡诺西北大学）；Bayero University Kano（巴耶罗大学卡诺分校）；University of Huddersfield（哈德斯菲尔德大学）；iCog Labs（iCog实验室）；Pennsylvania State University（宾夕法尼亚州立大学）；University of Pretoria（比勒陀利亚大学）；Masakhane；University of Hamburg（汉堡大学）；Imperial College London（伦敦帝国理工学院）
Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from…
Universidade de Vigo（维戈大学）；Cardiff University（卡迪夫大学）
Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear transformations, using no more than a small bilingual dictionary as supervision. In this work, we propose to apply an additional transformation after the initial alignment step, which moves cross-lingual synonyms towards a middle point between them. By applying this transformation our aim is to obtain a better cross-lingual integration of the vector spaces. In additio…
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipelin…
Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small contributions for the top tokens, compared to the overall model performance. Second, owing to their textual nature, the input variables, after appropriate transformations, are effectively binary (presence or absence of a token in an observation), making the input-output relationship difficult to understand. Common NLP interpretation techniques do not have flexibil…
In practice, it is common to find oneself with far too little text data to train a deep neural network. This "Big Data Wall" represents a challenge for minority language communities on the Internet, organizations, laboratories and companies that compete the GAFAM (Google, Amazon, Facebook, Apple, Microsoft). While most of the research effort in text data augmentation aims on the long-term goal of finding end-to-end learning solutions, which is equivalent to "using neural networks to feed neural networks", this engineering work focuses on the use of practical, robust, scalable and easy-to-imple…
COPPE/Universidade Federal do Rio de Janeiro (UFRJ)（里约热内卢联邦大学科佩研究所）
Over the last few decades, institutions around the world have been challenged to deal with the sheer volume of information captured in unstructured formats, especially in textual documents. The so called Digital Transformation age, characterized by important technological advances and the advent of disruptive methods in Artificial Intelligence, offers opportunities to make better use of this information. Recent techniques in Natural Language Processing (NLP) with Deep Learning approaches allow to efficiently process a large volume of data in order to obtain relevant information, to identify pa…
The University of Melbourne（墨尔本大学）；RMIT University（皇家墨尔本理工大学）
This paper describes the submissions of the Natural Language Processing (NLP) team from the Australian Research Council Industrial Transformation Training Centre (ITTC) for Cognitive Computing in Medical Technologies to the TREC 2021 Clinical Trials Track. The task focuses on the problem of matching eligible clinical trials to topics constituting a summary of a patient's admission notes. We explore different ways of representing trials and topics using NLP techniques, and then use a common retrieval model to generate the ranked list of relevant trials for each topic. The results from all our s…
Johns Hopkins University（约翰斯·霍普金斯大学）；Yale University（耶鲁大学）；New York University（纽约大学）
Relations between words are governed by hierarchical structure rather than linear ordering. Sequence-to-sequence (seq2seq) models, despite their success in downstream NLP applications, often fail to generalize in a hierarchy-sensitive manner when performing syntactic transformations - for example, transforming declarative sentences into questions. However, syntactic evaluations of seq2seq models have only observed models that were not pre-trained on natural language data before being trained to perform syntactic transformations, in spite of the fact that pre-training has been found to induce h…
Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）
The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an under-studied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. …
The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
Technology Innovation Institute（技术创新研究所）；Islamic University of Technology（伊斯兰理工大学）；Stanford University（斯坦福大学）；Amazon GenAI（亚马逊生成式人工智能部门）；AI Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）
Advancing Machine and Human Reasoning (AMHR) Lab（推进机器与人类推理（AMHR）实验室）；University of South Florida（南佛罗里达大学）
The Natural Language Inference (NLI) task is an important task in modern NLP, as it asks a broad question to which many other tasks may be reducible: Given a pair of sentences, does the first entail the second? Although the state-of-the-art on current benchmark datasets for NLI are deep learning-based, it is worthwhile to use other techniques to examine the logical structure of the NLI task. We do so by testing how well a machine-oriented controlled natural language (Attempto Controlled English) can be used to parse NLI sentences, and how well automated theorem provers can reason over the resu…
University of Utah（犹他大学）；University of California, Los Angeles（加州大学洛杉矶分校）；VISA research（VISA研究院）
Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper, we utilize interactive visualization to increase the interpretability and accessibility of a collection of state-of-the-art debiasing techniques. To aid this, we present Visualization of Embedding Representations for deBiasing system ("VERB"), an open-source web-based visualization tool that helps the users gain a technical understanding and visual intuitio…
Tsinghua University（清华大学）；Tencent Inc（腾讯公司）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
Hyperbolic neural networks have shown great potential for modeling complex data. However, existing hyperbolic networks are not completely hyperbolic, as they encode features in a hyperbolic space yet formalize most of their operations in the tangent space (a Euclidean subspace) at the origin of the hyperbolic space. This hybrid method greatly limits the modeling ability of networks. In this paper, we propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model by adapting the Lorentz transformations (including boost and rotation) to formalize essential operation…
The Ohio State University（俄亥俄州立大学）；University of Warwick（华威大学）
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding features in downstream models, and are largely unexplored. We consider four properties of word embedding geometry, namely: position relative to the origin, distribution of features in the vector space, global pairwise distances, and local pairwise distances. We define a sequence of transformations to generate new embeddings that expose subsets of these …
University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）
Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or standard recurrent networks to achieve the best performance. In this work, we propose a new model that encodes the full structural information contained in the graph. Our architecture couples the recently proposed Gated Graph Neural Networks with an input transformation that allows nodes and edges to have their own hidden representations, while t…
A Comprehensive Analysis of Arabic Natural Language Processing Research: Trends, Topic Evolution, and Research Gaps -- A Bibliometric and Topic-Based Study
University of Basrah（巴士拉大学）；University of Manchester（曼彻斯特大学）
Many natural language processing (NLP) applications require the computation of similarities between pairs of syntactic or semantic trees. Many researchers have used tree edit distance for this task, but this technique suffers from the drawback that it deals with single node operations only. We have extended the standard tree edit distance algorithm to deal with subtree transformation operations as well as single nodes. The extended algorithm with subtree operations, TED+ST, is more effective and flexible than the standard algorithm, especially for applications that pay attention to relations a…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Princeton University（普林斯顿大学）；Institute for Advanced Study（高等研究院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of Washington（华盛顿大学）
Suppose we are given a large matrix $A=(a_{i,j})$ that cannot be stored in memory but is in a disk or is presented in a data stream. However, we need to compute a matrix decomposition of the entry-wisely transformed matrix, $f(A):=(f(a_{i,j}))$ for some function $f$. Is it possible to do it in a space efficient way? Many machine learning applications indeed need to deal with such large transformed matrices, for example word embedding method in NLP needs to work with the pointwise mutual information (PMI) matrix, while the entrywise transformation makes it difficult to apply known linear algebr…
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augment…
