Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into similar feature distributions. However, these approaches ignore the direct alignment of input word distributions between domains, which is a vital factor in word-level classification tasks such as cross-domain NER. In this work, we shed new light on cross-domain NER by introducing a subword-level solution, X-Piece, for input word-level distribution shift in NER. Specifically, we re-tokenize the input words of the source domain to approach the target subword distribution, which is formulated and solved as an optimal transport problem. As this approach focuses on the input level, it can also be combined with previous DIRL methods for further improvement. Experimental results show the effectiveness of the proposed method based on BERT-tagger on four benchmark NER datasets. Also, the proposed method is proved to benefit DIRL methods such as DANN.
Multilingual search can be achieved with subword tokenization. The accuracy of traditional TF-IDF approaches depend on manually curated tokenization, stop words and stemming rules, whereas subword TF-IDF (STF-IDF) can offer higher accuracy without such heuristics. Moreover, multilingual support can be incorporated inherently as part of the subword tokenization model training. XQuAD evaluation demonstrates the advantages of STF-IDF: superior information retrieval accuracy of 85.4% for English and over 80% for 10 other languages without any heuristics-based preprocessing. The software to reprodu…
Tel Aviv University（特拉维夫大学）；Bar Ilan University（巴伊兰大学）
Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference. However, previous studies have claimed that this form of subword tokenization is inadequate for processing morphologically-rich languages (MRLs). We revisit this hypothesis by pretraining a BERT-style masked language model over character sequences instead of word-pieces. We compare the resulting model, dubbed TavBERT, against contemporary PLMs based on subwords for three highly complex and ambiguous MRLs (Hebrew, Turkish, and Arabic), testing them on both mo…
Borealis AI；Institute for Computer Science and Control（计算机科学与控制研究所）
Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown words. Word-level usage of such systems requires a way of pooling multiple subwords that correspond to a single word. In this paper we investigate how the choice of subword pooling affects the downstream performance on three tasks: morphological probing, POS tagging and NER, in 9 typologically diverse languages. We compare these in two massively multilingual models, mBERT and XLM-RoBERTa. For morphological tasks, the wid…
Blavatnik School of Computer Science（布拉瓦特尼克计算机科学学院）；Tel-Aviv University（特拉维夫大学）；Department of Computer Science（计算机科学系）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）
Most current popular subword tokenizers are trained based on word frequency statistics over a corpus, without considering information about co-occurrence or context. Nevertheless, the resulting vocabularies are used in language models' highly contextualized settings. We present SaGe, a tokenizer that tailors subwords for their downstream use by baking in the contextualized signal at the vocabulary creation phase. We show that SaGe does a better job than current widespread tokenizers in keeping token contexts cohesive, while not incurring a large price in terms of encoding efficiency or domain …
Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge
University of Melbourne（墨尔本大学）；National University of Mongolia（蒙古国立大学）；University of Edinburgh（爱丁堡大学）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；IMT Atlantique（IMT大西洋电信学院）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Amazon Alexa（亚马逊Alexa）
Named entity recognition (NER) is a vital task in spoken language understanding, which aims to identify mentions of named entities in text e.g., from transcribed speech. Existing neural models for NER rely mostly on dedicated word-level representations, which suffer from two main shortcomings. First, the vocabulary size is large, yielding large memory requirements and training time. Second, these models are not able to learn morphological or phonological representations. To remedy the above shortcomings, we adopt a neural solution based on bidirectional LSTMs and conditional random fields, whe…
BNLP is an open source language processing toolkit for Bengali language consisting with tokenization, word embedding, POS tagging, NER tagging facilities. BNLP provides pre-trained model with high accuracy to do model based tokenization, embedding, POS tagging, NER tagging task for Bengali language. BNLP pre-trained model achieves significant results in Bengali text tokenization, word embedding, POS tagging and NER tagging task. BNLP is using widely in the Bengali research communities with 16K downloads, 119 stars and 31 forks. BNLP is available at https://github.com/sagorbrur/bnlp.
University of Tokyo（东京大学）；Bogazici University（海峡大学）
Morphological information is important for many sequence labeling tasks in Natural Language Processing (NLP). Yet, existing approaches rely heavily on manual annotations or external software to capture this information. In this study, we propose using subword contextual embeddings to capture the morphological information for languages with rich morphology. In addition, we incorporate these embeddings in a hierarchical multi-task setting which is not employed before, to the best of our knowledge. Evaluated on Dependency Parsing (DEP) and Named Entity Recognition (NER) tasks, which are shown to …
AIPHES, Heidelberg Institute for Theoretical Studies（海德堡理论研究所 AIPHES）
We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages bet- ter than alternative subword approaches, while requiring vastly fewer resources and no tokenization. BPEmb is available at https://github.com/bheinzerling/bpemb
State-of-the-art models in natural language processing rely on separate rigid subword tokenization algorithms, which limit their generalization ability and adaptation to new settings. In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. To this end, we introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters in a data-driven fashion. Concretely, GBST enumerates candidate subword blocks and learns to score them in a position-wise fashion using a …
Synapse Développement（Synapse发展公司）；IRIT, Université Paul Sabatier（保罗·萨巴捷大学IRIT研究所）
We present our system for the CAp 2017 NER challenge which is about named entity recognition on French tweets. Our system leverages unsupervised learning on a larger dataset of French tweets to learn features feeding a CRF model. It was ranked first without using any gazetteer or structured external data, with an F-measure of 58.89\%. To the best of our knowledge, it is the first system to use fasttext embeddings (which include subword representations) and an embedding-based sentence representation for NER.
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Reco…
Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
Department of Radiology, Weill Cornell Medicine, New York, NY, USA.（韦尔·科恩医学中心放射科, 纽约, NY, 美国）；School of Electrical and Computer Engineering, Cornell University and Cornell Tech, New York, NY, USA.（康奈尔大学电气与计算机工程学院及康奈尔科技, 纽约, NY, 美国）
Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in low-resource languages, leading models to produce suboptimal representations. Additionally, the dependency on a fixed vocabulary limits the subword models' adaptability across languages and domains. In this work, we propose a vocabulary-free neural tokenizer by distilling segmentation information from heuristic-based subword tokenization. We pre-train our char…
FI Group（FI集团）；Université Sorbonne Paris Nord（索邦巴黎北大学）
The task of Named Entity Recognition (NER) is an important component of many natural language processing systems, such as relation extraction and knowledge graph construction. In this work, we present a simple and effective approach for Named Entity Recognition. The main idea of our approach is to encode the input subword sequence with a pre-trained transformer such as BERT, and then, instead of directly classifying the word labels, another layer of transformer is added to the subword representation to better encode the word-level interaction. We evaluate our approach on three benchmark datase…
Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to languages with high inflection. Our approach results in a new state-of-the-art for the Polish language, taking first place in Task 3 of PolEval'18. After further training, our final model outperformed the second best model by 35%. We have open-sourced our pretrained models and code.
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Institute for Computer Science and Control（计算机科学与控制研究所）；Alfréd Rényi Institute of Mathematics（阿尔弗雷德·莱尼数学研究所）
We present an extended comparison of contextualized language models for Hungarian. We compare huBERT, a Hungarian model against 4 multilingual models including the multilingual BERT model. We evaluate these models through three tasks, morphological probing, POS tagging and NER. We find that huBERT works better than the other models, often by a large margin, particularly near the global optimum (typically at the middle layers). We also find that huBERT tends to generate fewer subwords for one word and that using the last subword for token-level tasks is generally a better choice than using the …
In biomedical literature, it is common for entity boundaries to not align with word boundaries. Therefore, effective identification of entity spans requires approaches capable of considering tokens that are smaller than words. We introduce a novel, subword approach for named entity recognition (NER) that uses byte-pair encodings (BPE) in combination with convolutional and recurrent neural networks to produce byte-level tags of entities. We present experimental results on several standard biomedical datasets, namely the BioCreative VI Bio-ID, JNLPBA, and GENETAG datasets. We demonstrate competi…
Named entity recognition (NER) is the task to detect and classify the entity spans in the text. When entity spans overlap between each other, this problem is named as nested NER. Span-based methods have been widely used to tackle the nested NER. Most of these methods will get a score $n \times n$ matrix, where $n$ means the length of sentence, and each entry corresponds to a span. However, previous work ignores spatial relations in the score matrix. In this paper, we propose using Convolutional Neural Network (CNN) to model these spatial relations in the score matrix. Despite being simple, exp…
How Important Is Tokenization in French Medical Masked Language Models?
LIA, Avignon University（阿维尼翁大学计算机科学与人工智能实验室）；Zenidoc（Zenidoc公司）；Nantes Université（南特大学）；École Centrale Nantes（南特中央理工学院）；CNRS（法国国家科学研究中心）；LS2N, UMR 6004（南特数字科学实验室）
Representation Learning of Structured Data for Medical Foundation Models
ASUS Intelligent Cloud Services (AICS)（华硕智能云服务（AICS））；Imperial College London（伦敦帝国学院）；University of Manchester（曼彻斯特大学）；Cheng Hsin General Hospital（程新总医院）；Crayon Software（克雷扬软件公司）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Southern California（南加州大学）
Taking word sequences as the input, typical named entity recognition (NER) models neglect errors from pre-processing (e.g., tokenization). However, these errors can influence the model performance greatly, especially for noisy texts like tweets. Here, we introduce Neural-Char-CRF, a raw-to-end framework that is more robust to pre-processing errors. It takes raw character sequences as inputs and makes end-to-end predictions. Word embedding and contextualized representation models are further tailored to capture textual signals for each character instead of each word. Our model neither requires …
Static subword tokenization algorithms have been an essential component of recent works on language modeling. However, their static nature results in important flaws that degrade the models' downstream performance and robustness. In this work, we propose MANTa, a Module for Adaptive Neural TokenizAtion. MANTa is a differentiable tokenizer trained end-to-end with the language model. The resulting system offers a trade-off between the expressiveness of byte-level models and the speed of models trained using subword tokenization. In addition, our tokenizer is highly explainable since it produces …
