Many measures of societal bias in language models have been proposed in recent years. A popular approach is to use a set of word filling prompts to evaluate the behavior of the language models. In this work, we analyze the validity of two such measures -- StereoSet and CrowS-Pairs. We show that these measures produce unexpected and illogical results when appropriate control group samples are constructed. Based on this, we believe that they are problematic and using them in the future should be reconsidered. We propose a way forward with an improved testing protocol. Finally, we also introduce a new gender bias dataset for Slovak.
Johannes Kepler University（约翰内斯·开普勒大学）；EPFL（洛桑联邦理工学院）；Idiap Research Institute（IDIAP研究所）；TU Wien（维也纳工业大学）；Complexity Science Hub Vienna（维也纳复杂性科学中心）
Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts of interest (such as genders). In this study, we show that, depending on what one aims to quantify as bias, this commonly-used approach can introduce non-relevant concepts into bias measurement. We propose an alternative approach to bias measurement utilizing the smoothed first-order co-occurrence relation…
Slot filling is an important problem in Spoken Language Understanding (SLU) and Natural Language Processing (NLP), which involves identifying a user's intent and assigning a semantic concept to each word in a sentence. This paper presents a word feature vector method and combines it into the convolutional neural network (CNN). We consider 18 word features and each word feature is constructed by merging similar word labels. By introducing the concept of external library, we propose a feature set approach that is beneficial for building the relationship between a word from the training dataset a…
Recognizing lexical semantic relations between word pairs is an important task for many applications of natural language processing. One of the mainstream approaches to this task is to exploit the lexico-syntactic paths connecting two target words, which reflect the semantic relations of word pairs. However, this method requires that the considered words co-occur in a sentence. This requirement is hardly satisfied because of Zipf's law, which states that most content words occur very rarely. In this paper, we propose novel methods with a neural model of $P(path|w_1, w_2)$ to solve this problem…
University of Milano-Bicocca（米兰比可卡大学）；FIZ Karlsruhe - Leibniz Institute for Information Infrastructure（FIZ卡尔斯鲁厄——莱布尼茨信息基础设施研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over time due to various reasons, such as cultural and societal impact. Metaphorical expressions are known to co-evolve with language and literal word meanings, and even drive, to some extent, this evolution. This poses the question of whether different, possibly time-specific, representations of literal meanings may impact the metaphor detection task. To the best of our knowledge,…
We investigate the usage of convolutional neural networks (CNNs) for the slot filling task in spoken language understanding. We propose a novel CNN architecture for sequence labeling which takes into account the previous context words with preserved order information and pays special attention to the current word with its surrounding context. Moreover, it combines the information from the past and the future words for classification. Our proposed CNN architecture outperforms even the previously best ensembling recurrent neural network model and achieves state-of-the-art results with an F1-scor…
Beijing University of Posts and Telecommunications（北京邮电大学）；Meituan Group（美团集团）
In real dialogue scenarios, the existing slot filling model, which tends to memorize entity patterns, has a significantly reduced generalization facing Out-of-Vocabulary (OOV) problems. To address this issue, we propose an OOV robust slot filling model based on multi-level data augmentations to solve the OOV problem from both word and slot perspectives. We present a unified contrastive learning framework, which pull representations of the origin sample and augmentation samples together, to make the model resistant to OOV problems. We evaluate the performance of the model from some specific slo…
Word Embeddings have been shown to contain the societal biases present in the original corpora. Existing methods to deal with this problem have been shown to only remove superficial biases. The method of Adversarial Debiasing was presumed to be similarly superficial, but this is was not verified in previous works. Using the experiments that demonstrated the shallow removal in other methods, I show results that suggest Adversarial Debiasing is more effective at removing bias and thus motivate further investigation on the utility of Adversarial Debiasing.
Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems. Supervised learning approaches have proven effective at tackling this challenge, but they need a significant amount of labeled training data in a given domain. However, new domains (i.e., unseen in training) may emerge after deployment. Thus, it is imperative that these models seamlessly adapt and fill slots from both seen and unseen domains -- unseen domain…
Emoji have become a significant part of our informal textual communication. Previous work addressing the societal and linguistic functions of emoji overlook the evolving meaning of the symbol. This evolution could be addressed through the framework of semantic drifts. In this paper we model and analyze the semantic drift of emoji and discuss the features that may be contributing to the drift, some are unique to emoji and some are more general.
IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to out-of-domain datasets. However, SPLADE still struggles with exact matching of low-frequency words in training data. In addition, domain shifts in vocabulary and word frequencies deteriorate the IR performance of SPLADE. Because supervision data are scarce in the target domain, addressing the domain shifts without supervision data is necessary. This paper proposes a…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Alibaba Group（阿里巴巴集团）；Tencent Medical AI Lab（腾讯医疗人工智能实验室）；Institute for Data Science, Tsinghua University（清华大学数据科学研究院）
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or adopt joint models which sequentially label slots while summarizing the utterance-level intent without explicitly preserving the hierarchical relationship among words, slots, and intents. To exploit the semantic hierarchy for effective modeling, we propose a capsule-based neural network model which accomplishes slot filling and intent detection via a dynamic rou…
Sofia University “St. Kliment Ohridski”（圣克莱门特·奥里季斯基索菲亚大学）；Qatar Computing Research Institute, HBKU（卡塔尔计算研究所（哈马德·本·哈利法大学））
Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such models. Moreover, data scarceness and specialized vocabularies pose additional challenges. Recently, the advances in pre-trained language models, namely contextualized models such as ELMo and BERT have revolutionized the field by tapping the potential of training very large models with just a few steps of fine-tuning on a task-specific dataset. Here, we leverage …
American University of Beirut（贝鲁特美国大学）；Beirut, Lebanon（黎巴嫩贝鲁特）
Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of thi…
Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant dimensions like embedding models, types of texts, and different languages. In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models. Furthermore, we analyze the cross-lingual biases encoded in bilingual embedding spaces, i…
In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information. Previous studies on Chinese SLU do not consider the word information, failing to detect word boundaries that are beneficial for intent detection and slot filling. To address this issue, we propose a multi-level word adapter to inject word information for Chinese SLU, which consists of (1) sentence-level word adapter, which directly fuses the sentence representations of the word information and character information to perform intent detection and (2) character-level word adapter, which is appli…
Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort…
Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks have been deemed to proceed independently. However, more recently, joint models for intent classification and slot filling have achieved state-of-the-art performance, and have proved that there exists a strong relationship between the two tasks. This article is a compilation of past work in natural language understanding, especially joint intent classification and slot filling. We observe three milestones in this research so far: Intent detection to identify the speaker…
University of Oregon（俄勒冈大学）；Adobe Research（奥多比研究院）
Slot Filling (SF) is one of the sub-tasks of Spoken Language Understanding (SLU) which aims to extract semantic constituents from a given natural language utterance. It is formulated as a sequence labeling task. Recently, it has been shown that contextual information is vital for this task. However, existing models employ contextual information in a restricted manner, e.g., using self-attention. Such methods fail to distinguish the effects of the context on the word representation and the word label. To address this issue, in this paper, we propose a novel method to incorporate the contextual …
Using natural language to give instructions to robots is challenging, since natural language understanding is still largely an open problem. In this paper we address this problem by restricting our attention to commands modeled as one action, plus arguments (also known as slots). For action detection (also called intent detection) and slot filling various architectures of Recurrent Neural Networks and Long Short Term Memory (LSTM) networks were evaluated, having LSTMs achieved a superior accuracy. As the action requested may not fall within the robots capabilities, a Support Vector Machine(SVM…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Language representations are efficient tools used across NLP applications, but they are strife with encoded societal biases. These biases are studied extensively, but with a primary focus on English language representations and biases common in the context of Western society. In this work, we investigate biases present in Hindi language representations with focuses on caste and religion-associated biases. We demonstrate how biases are unique to specific language representations based on the history and culture of the region they are widely spoken in, and how the same societal bias (such as bin…
In recent years, Recurrent Neural Networks (RNNs) based models have been applied to the Slot Filling problem of Spoken Language Understanding and achieved the state-of-the-art performances. In this paper, we investigate the effect of incorporating pre-trained language models into RNN based Slot Filling models. Our evaluation on the Airline Travel Information System (ATIS) data corpus shows that we can significantly reduce the size of labeled training data and achieve the same level of Slot Filling performance by incorporating extra word embedding and language model embedding layers pre-trained…
Word embeddings are extensively used in various NLP problems as a state-of-the-art semantic feature vector representation. Despite their success on various tasks and domains, they might exhibit an undesired bias for stereotypical categories due to statistical and societal biases that exist in the dataset they are trained on. In this study, we analyze the gender bias in four different pre-trained word embeddings specifically for the depression category in the mental disorder domain. We use contextual and non-contextual embeddings that are trained on domain-independent as well as clinical domain…
Clinical word embeddings are extensively used in various Bio-NLP problems as a state-of-the-art feature vector representation. Although they are quite successful at the semantic representation of words, due to the dataset - which potentially carries statistical and societal bias - on which they are trained, they might exhibit gender stereotypes. This study analyses gender bias of clinical embeddings on three medical categories: mental disorders, sexually transmitted diseases, and personality traits. To this extent, we analyze two different pre-trained embeddings namely (contextualized) clinica…
ICC (UBA-CONICET)（ICC（布宜诺斯艾利斯大学-国家科学技术研究委员会））；Maestría en Data Mining (UBA)（数据挖掘硕士项目（布宜诺斯艾利斯大学））；Escuela IDAES (UNSAM)（IDAES学院（圣马丁将军大学））
Numerous works use word embedding-based metrics to quantify societal biases and stereotypes in texts. Recent studies have found that word embeddings can capture semantic similarity but may be affected by word frequency. In this work we study the effect of frequency when measuring female vs. male gender bias with word embedding-based bias quantification methods. We find that Skip-gram with negative sampling and GloVe tend to detect male bias in high frequency words, while GloVe tends to return female bias in low frequency words. We show these behaviors still exist when words are randomly shuffl…
University of Gothenburg（哥德堡大学）；Kyoto University（京都大学）
Our languages are in constant flux driven by external factors such as cultural, societal and technological changes, as well as by only partially understood internal motivations. Words acquire new meanings and lose old senses, new words are coined or borrowed from other languages and obsolete words slide into obscurity. Understanding the characteristics of shifts in the meaning and in the use of words is useful for those who work with the content of historical texts, the interested general public, but also in and of itself. The findings from automatic lexical semantic change detection, and the …
Department of Computer Science（计算机科学系）；University of Sheffield（谢菲尔德大学）
It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. However, the extent to which the methods are capturing social stereotypes inherited from the data has been debated. Bias is a complex concept and there exist multiple ways to define it. Previous work has leveraged gender word pairs to measure bias and extract biased analogies. We show that the reliance on these gendered pairs has strong limitations: bias measures based off of them are not robust and cannot identify common types of real-world bias, whilst analogies utilising …
A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely by taking the pairwise dialogue history and candidate response as a whole, the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose a novel model to fill such …
Word embedding spaces are powerful tools for capturing latent semantic relationships between terms in corpora, and have become widely popular for building state-of-the-art natural language processing algorithms. However, studies have shown that societal biases present in text corpora may be incorporated into the word embedding spaces learned from them. Thus, there is an ethical concern that human-like biases contained in the corpora and their derived embedding spaces might be propagated, or even amplified with the usage of the biased embedding spaces in downstream applications. In an attempt t…
Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, slot filling, and language modeling. The neural network model keeps updating the intent estimation as word in the transcribed utterance arrives and uses it as contextual features in the joint model. Evaluation of the language model and online SLU model is made on the ATIS benchmarking data set. On language modeling task, our joint model achieves 11.8% relat…
University of Edinburgh（爱丁堡大学）；Rasa Technologies GmbH（Rasa技术公司）；Heriot-Watt University（赫瑞-瓦特大学）
Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a variety of metrics that quantify bias in models. Some of these metrics are intrinsic, measuring bias in word embedding spaces, and some are extrinsic, measuring bias in downstream tasks that the word embeddings enable. Do these intrinsic and extrinsic metrics correlate with each other? We compare intrinsic and extrinsic metrics across hundreds of trained models c…
Traditional slot filling in natural language understanding (NLU) predicts a one-hot vector for each word. This form of label representation lacks semantic correlation modelling, which leads to severe data sparsity problem, especially when adapting an NLU model to a new domain. To address this issue, a novel label embedding based slot filling framework is proposed in this paper. Here, distributed label embedding is constructed for each slot using prior knowledge. Three encoding methods are investigated to incorporate different kinds of prior knowledge about slots: atomic concepts, slot descript…
Universitat d’Alacant（阿利坎特大学）；Univ. of Sheffield（谢菲尔德大学）；Univ. Edinburgh（爱丁堡大学）
A popular application of machine translation (MT) is gisting: MT is consumed as is to make sense of text in a foreign language. Evaluation of the usefulness of MT for gisting is surprisingly uncommon. The classical method uses reading comprehension questionnaires (RCQ), in which informants are asked to answer professionally-written questions in their language about a foreign text that has been machine-translated into their language. Recently, gap-filling (GF), a form of cloze testing, has been proposed as a cheaper alternative to RCQ. In GF, certain words are removed from reference translation…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Intapp Inc.（Intapp公司）
We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data. Compared to the state-of-the-art methods, our approach does not require label embeddings as part of the input and therefore lends itself nicely to a wide range of model architectures. In addition, our architecture computes contextual distances between words and labels to avoid adding contextual windows, thus reducing memory footprint.…
University of Pisa（比萨大学）；ISTI (CNR)（意大利国家研究委员会信息科学与技术研究所）；University of Kansas（堪萨斯大学）；University of Exeter（埃克塞特大学）
Knowledge in the human mind exhibits a dualistic vector/network nature. Modelling words as vectors is key to natural language processing, whereas networks of word associations can map the nature of semantic memory. We reconcile these paradigms - fragmented across linguistics, psychology and computer science - by introducing FEature-Rich MUltiplex LEXical (FERMULEX) networks. This novel framework merges structural similarities in networks and vector features of words, which can be combined or explored independently. Similarities model heterogenous word associations across semantic/syntactic/pho…
We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks. The blanks control which part of the sequence to expand, making BLM ideal for a variety of text editing and rewriting tasks. The model can start from a single blank or partially completed text with blanks at specified locations. It iteratively determines which word to place in a blank and whether to insert new blanks, and stops generating when no blanks are left to fill. BLM can be efficiently trained using a lower bound of the marginal data likelihood. On the task of filling …
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of high-quality data. In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented dialogue systems. It leverages very few task-related parallel word pairs to generate code-switching sentences for learning the inter-lingual semant…
