In this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval. By leveraging bidirectional attention through diffusion-based pretraining, our models capture comprehensive bidirectional context within passages, enabling the use of mean pooling and a late chunking strategy to better preserve global context across long documents. We release two model types: pplx-embed-v1 for standard retrieval, and pplx-embed-context-v1 for contextualized embeddings that incorporate global document context into passage representations. pplx-embed-v1 achieves competitive performance on the MTEB(Multilingual, v2), MTEB(Code), MIRACL, BERGEN, and ToolRet retrieval benchmarks, while pplx-embed-context-v1 sets new records on the ConTEB benchmark. Beyond public benchmarks, pplx-embed-v1 demonstrates strong performance on our internal evaluation suite, focusing on real-world, large-scale search scenarios constructed from 1B production web pages. These results validate the models' effectiveness in production environments where retrieval quality and efficiency are critical at scale.
Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of contextualization, i.e., how well words are interpreted in context, by studying the extent to which semantic classes of a word can be inferred from its contextualized embeddings. Quantifying contextualization helps in understanding and utilizing pretrained language models. We show that top layer representations achieve high accuracy inferring semantic class…
University of California, San Diego（加州大学圣地亚哥分校）；Microsoft Research Asia（微软亚洲研究院）；Sun Yat-sen University（中山大学）
In this paper, we propose LaPraDoR, a pretrained dual-tower dense retriever that does not require any supervised data for training. Specifically, we first present Iterative Contrastive Learning (ICoL) that iteratively trains the query and document encoders with a cache mechanism. ICoL not only enlarges the number of negative instances but also keeps representations of cached examples in the same hidden space. We then propose Lexicon-Enhanced Dense Retrieval (LEDR) as a simple yet effective way to enhance dense retrieval with lexical matching. We evaluate LaPraDoR on the recently proposed BEIR …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Allen School of Computer Science & Engineering, University of Washington（华盛顿大学艾伦计算机科学与工程学院）
As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful models for this task have used hierarchical models to contextualize sentence representations, and Conditional Random Fields (CRFs) to incorporate dependencies between subsequent labels. In this work, we show that pretrained language models, BERT (Devlin et al., 2018) in particular, can be used for this task to capture contextual dependencies without the need for …
Pretrained contextualized text encoders are now a staple of the NLP community. We present a survey on language representation learning with the aim of consolidating a series of shared lessons learned across a variety of recent efforts. While significant advancements continue at a rapid pace, we find that enough has now been discovered, in different directions, that we can begin to organize advances according to common themes. Through this organization, we highlight important considerations when interpreting recent contributions and choosing which model to use.
This paper describes an approach to detect idiomaticity only from the contextualized representation of a MWE over multilingual pretrained language models. Our experiments find that larger models are usually more effective in idiomaticity detection. However, using a higher layer of the model may not guarantee a better performance. In multilingual scenarios, the convergence of different languages are not consistent and rich-resource languages have big advantages over other languages.
Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained. To address this gap, we assess whether contextual word representations extracted from deep pretrained language models create distinguishable representations for different senses of a given word. We analyze the representation geometry and find that most layers of deep pretrained language models create highly anisotropic representations, pointing towards the existence of representation degeneration problem in contextual word …
Contextual information integration for stance detection via cross-attention
Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Lucerne University of Applied Sciences and Arts（卢塞恩应用科学与艺术大学）
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and extralinguistic context. Based on a pretrained language model (PLM), dynamic contextualized word embeddings model time and social space jointly, which makes them attractive for a range of NLP tasks involving semantic variability. We highlight potential app…
Pompeu Fabra University（庞培法布拉大学）；Amazon AI（亚马逊人工智能）；Catalan Institute for Research and Advanced Studies (ICREA)（加泰罗尼亚研究与高级研究院（ICREA））
The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among other information, it has been shown that entire syntax trees are implicitly embedded in the geometry of such models. As these models are often fine-tuned, it becomes increasingly important to understand how the encoded knowledge evolves along the fine-tuning. In this paper, we analyze the evolution of the embedded syntax trees along the fine-tuning process of B…
Institut Mines-Télécom Atlantique（法国大西洋矿业电信学院）；Centre Hospitalier Universitaire de Brest（布雷斯特大学医院中心）
In recent literature, contextual pretrained Language Models (LMs) demonstrated their potential in generalizing the knowledge to several Natural Language Processing (NLP) tasks including supervised Word Sense Disambiguation (WSD), a challenging problem in the field of Natural Language Understanding (NLU). However, word representations from these models are still very dense, costly in terms of memory footprint, as well as minimally interpretable. In order to address such issues, we propose a new supervised biologically inspired technique for transferring large pre-trained language model represen…
Charles University（查理大学）；Faculty Of Mathematics and Physics（数学与物理学院）
Eye-Tracking data is a very useful source of information to study cognition and especially language comprehension in humans. In this paper, we describe our systems for the CMCL 2022 shared task on predicting eye-tracking information. We describe our experiments with pretrained models like BERT and XLM and the different ways in which we used those representations to predict four eye-tracking features. Along with analysing the effect of using two different kinds of pretrained multilingual language models and different ways of pooling the tokenlevel representations, we also explore how contextual…
Hong Kong University of Science and Technology（香港科技大学）
Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources.Financial sector also accumulates large amount of financial communication text.However, there is no pretrained finance specific language models available. In this work,we address the need by pretraining a financial domain specific BERT models, FinBERT, using a large scale of financial communication corpora. Experiments on three financial sentiment classification tasks confirm the advantage of FinBERT over gene…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland（马里兰大学）
A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This multilingual model is fined-tuned to the retrieval task with monolingual data such as English MS MARCO using the same training recipe as the monolingual retrieval model used. However, such transferred models suffer from mismatches in the languages of the input text during training and inference. In this work, we propose transferring monolingual retrieval models usin…
Aalto University（阿尔托大学）；The University of Manchester（曼彻斯特大学）；Mila, Québec AI Institute（米拉魁北克人工智能研究所）；Nanyang Technological University（南洋理工大学）
Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without adequate treatment. Early detection of mental disorders and suicidal ideation from social content provides a potential way for effective social intervention. Recent advances in pretrained contextualized language representations have promoted the development of several domain-specific pretrained models and facilitated several downstream applications. However, there are no existing pretrained language models for mental healthcare. This paper trains and release two pretraine…
When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment. Massively pretrained language models like BERT can encode not only just the words in a document but also the context around the words along with them. This begs the questions, "Does a pretrain language model also automatically encode sentiment information about each word?" and "Can it be used to infer polarity towards different aspects?". In this work we try to answer this question by showing that training a comparison of a contextual embedding from BERT and a …
University of California, Santa Barbara（加州大学圣巴巴拉分校）
To reduce the toxic degeneration in a pretrained Language Model (LM), previous work on Language Model detoxification has focused on reducing the toxicity of the generation itself (self-toxicity) without consideration of the context. As a result, a type of implicit offensive language where the generations support the offensive language in the context is ignored. Different from the LM controlling tasks in previous work, where the desired attributes are fixed for generation, the desired stance of the generation depends on the offensiveness of the context. Therefore, we propose a novel control met…
Hebrew University of Jerusalem（耶路撒冷希伯来大学）；University of Washington（华盛顿大学）；Apple, Inc.（苹果公司）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as important as typically thought for pretrained language models. We introduce PAPA, a new probing method that replaces the input-dependent attention matrices with constant ones -- the average attention weights over multiple inputs. We use PAPA to analyze several established pretrained Transformers on six downstream tasks. We find that without any input-dependen…
Pretrained Language Models (PLM) have established a new paradigm through learning informative contextualized representations on large-scale text corpus. This new paradigm has revolutionized the entire field of natural language processing, and set the new state-of-the-art performance for a wide variety of NLP tasks. However, though PLMs could store certain knowledge/facts from training corpus, their knowledge awareness is still far from satisfactory. To address this issue, integrating knowledge into PLMs have recently become a very active research area and a variety of approaches have been deve…
Center for Information and Language Processing (CIS)（信息与语言处理中心（CIS））；LMU Munich（慕尼黑大学）
Multilingual pretrained language models (MPLMs) exhibit multilinguality and are well suited for transfer across languages. Most MPLMs are trained in an unsupervised fashion and the relationship between their objective and multilinguality is unclear. More specifically, the question whether MPLM representations are language-agnostic or they simply interleave well with learned task prediction heads arises. In this work, we locate language-specific information in MPLMs and identify its dimensionality and the layers where this information occurs. We show that language-specific information is scatte…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；TU Berlin（柏林工业大学）
An increasing awareness of biased patterns in natural language processing resources, like BERT, has motivated many metrics to quantify `bias' and `fairness'. But comparing the results of different metrics and the works that evaluate with such metrics remains difficult, if not outright impossible. We survey the existing literature on fairness metrics for pretrained language models and experimentally evaluate compatibility, including both biases in language models as in their downstream tasks. We do this by a mixture of traditional literature survey and correlation analysis, as well as by runnin…
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
Zhejiang University（浙江大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Fudan University（复旦大学）；Chinese University of Hong Kong（中国香港大学）
In this paper, we address the problem of learning low dimension representation of entities on relational databases consisting of multiple tables. Embeddings help to capture semantics encoded in the database and can be used in a variety of settings like auto-completion of tables, fully-neural query processing of relational joins queries, seamlessly handling missing values, and more. Current work is restricted to working with just single table, or using pretrained embeddings over an external corpus making them unsuitable for use in real-world databases. In this work, we look into ways of using t…
Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Schütze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has been addressed by separately learning representations for rare words. In this work, we transfer this idea to pretrained language models: We introduce BERTRAM, a powerful architecture based on BERT that is capable of inferring high-quality embeddings for rare words that are suitable as input representations for deep language models. This is achieved by enabling…
Language Technologies Institute, School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院语言技术研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random seeds can lead to substantially different results. To better understand this phenomenon, we experiment with four datasets from the GLUE benchmark, fine-tuning BERT hundreds of times on each while varying only the random seeds. We find substantial performance increases compared to previously reported results, and we quantify how the performance of the best-f…
We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so effective for cross-lingual transfer. We show, contrary to what was previously hypothesized, that transfer is possible even when there is no shared vocabulary across the monolingual corpora and also when the text comes from very different domains. The only requirement is that there are some shared parameters in the top layers of the multi-lingual encoder. To better …
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state tracker (DST) and response generator (RG). The dialogue state consists of the domain-slot-value triples, which are regarded as the user's constraints to search the domain-related databases. The large-scale task-oriented dialogue data with the annotated structured dialogue state usually are inaccessible. It prevents the development of the pretrained language m…
One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a state-of-the-art data augmentation method, called the contextual data augmentation (CDA), that generates labeled training instances using a pretrained language model. The CDA has been reported to work well for several other natural language processing tasks, including text classification and machine translation. This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Harvard John A. Paulson School of Engineering and Applied Sciences（哈佛大学约翰·A·保尔森工程与应用科学学院）；MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；University of Washington（华盛顿大学）
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic knowledge they capture, we study the representations produced by several recent pretrained contextualizers (variants of ELMo, the OpenAI transformer language model, and BERT) with a suite of seventeen diverse probing tasks. We find that linear models trained on top of frozen contextual representations are competitive with state-of-the-art task-specific models in…
An Empirical Bayes Framework for Open-Domain Dialogue Generation
School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究所）
IT University of Copenhagen（哥本哈根信息技术大学）；Uppsala University（乌普萨拉大学）；KU Leuven（鲁汶大学）；University of Copenhagen（哥本哈根大学）
With an increase of dataset availability, the potential for learning from a variety of data sources has increased. One particular method to improve learning from multiple data sources is to embed the data source during training. This allows the model to learn generalizable features as well as distinguishing features between datasets. However, these dataset embeddings have mostly been used before contextualized transformer-based embeddings were introduced in the field of Natural Language Processing. In this work, we compare two methods to embed datasets in a transformer-based multilingual depen…
Shanghai Jiao Tong University（上海交通大学）；College of Zhiyuan, Shanghai Jiao Tong University（上海交通大学致远学院）；AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院）
Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task. Despite of sharing a lot of processing characteristics and even task purpose, it is surprisingly that jointly considering these two related tasks was never formally reported in previous work. Thus this paper makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal predicates and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by explicit contextual semantic role labels…
Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can capture complex syntactic word relations. In this paper, we use the deep contextualized language model BERT for the task of ad hoc table retrieval. We investigate how to encode table content considering the table structure and input length limit of BERT. We also propose an approach that incorporates features from prior literature on table retrieval and jointly…
Stanford University（斯坦福大学）；Google Research（谷歌研究院）；Bar Ilan University（巴伊兰大学）；AI2；University of Pennsylvania（宾夕法尼亚大学）
Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance and show that a simple method of canonicalizing numbers can have a significant …
FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs
Center for Computational & Data Sciences, Independent University, Bangladesh（计算与数据科学中心，独立大学，孟加拉国）；Amazon GenAI（亚马逊生成人工智能）；Qatar Computing Research Institute（卡塔尔计算研究所）；University of Virginia（弗吉尼亚大学）
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due to their dependence on external language models and the deterministic approach to weight boosting, their performance is limited. In this paper, we propose training neural contextual adapters for personalization in neural transducer based ASR models. Our approach can not only bias towards user-defined words, but also has the flexibility to work with pretraine…
We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the impact of the training set size and the linguistic properties of the task. Surprisingly, we find that both of these simpler baselines can match contextual embeddings on industry-scale data, and often perform within 5 to 10% accuracy (absolute) on benchmark tasks. Furthermore, we identify properties of data for which contextual embeddings give particularly la…
We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their static counterparts, aligning them poses a challenge due to their dynamic nature. To this end, we construct context-independent variants of the original monolingual spaces and utilize their mapping to derive an alignment for the context-dependent spaces. This mapping readily supports processing of a target language, improving transfer by context-aware embedd…
CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Kuaishou Technology（快手科技）
Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall system suffers from error propagation. In this paper, we propose a novel training method that enables pretrained contextual embeddings to process acoustic features. In particular, we extend it with an encoder of pretrained speech recognition systems in order to construct end-to-end spoken language understanding systems. Our proposed method is based on the t…
