Slot-filling, Translation, Intent classification, and Language identification, or STIL, is a newly-proposed task for multilingual Natural Language Understanding (NLU). By performing simultaneous slot filling and translation into a single output language (English in this case), some portion of downstream system components can be monolingual, reducing development and maintenance cost. Results are given using the multilingual BART model (Liu et al., 2020) fine-tuned on 7 languages using the MultiATIS++ dataset. When no translation is performed, mBART's performance is comparable to the current state of the art system (Cross-Lingual BERT by Xu et al. (2020)) for the languages tested, with better average intent classification accuracy (96.07% versus 95.50%) but worse average slot F1 (89.87% versus 90.81%). When simultaneous translation is performed, average intent classification accuracy degrades by only 1.7% relative and average slot F1 degrades by only 1.2% relative.
We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared natural language output space. Unlike prior discriminative methods, our model naturally incorporates label semantics and shares knowledge across tasks. Our framework is general purpose, performing well on few-shot, low-resource, and high-resource tasks. We demonstrate these advantages on popular named entity recognition, slot labeling, and intent classification benchmarks. We set a new state-of-the-art for few-shot slot labeling, improving substantially upon the previous 5-shot ($75.0\% \rightarrow 90.9\%$) and 1-shot ($70.4\% \rightarrow 81.0\%$) state-of-the-art results. Furthermore, our model generates large improvements ($46.27\% \rightarrow 63.83\%$) in low-resource slot labeling over a BERT baseline by incorporating label semantics. We also maintain competitive results on high-resource tasks, performing within two points of the state-of-the-art on all tasks and setting a new state-of-the-art on the SNIPS dataset.
Recent advancements in the NLP field showed that transfer learning helps with achieving state-of-the-art results for new tasks by tuning pre-trained models instead of starting from scratch. Transformers have made a significant improvement in creating new state-of-the-art results for many NLP tasks including but not limited to text classification, text generation, and sequence labeling. Most of these success stories were based on large datasets. In this paper we focus on a real-life scenario that scientists in academia and industry face frequently: given a small dataset, can we use a large pre-trained model like BERT and get better results than simple models? To answer this question, we use a small dataset for intent classification collected for building chatbots and compare the performance of a simple bidirectional LSTM model with a pre-trained BERT model. Our experimental results show that bidirectional LSTM models can achieve significantly higher results than a BERT model for a small dataset and these simple models get trained in much less time than tuning the pre-trained counterparts. We conclude that the performance of a model is dependent on the task and the data, and therefore before making a model choice, these factors should be taken into consideration instead of directly choosing the most popular model.
Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI. The traditional approach of information-sharing topic handlers is balanced with a focus on opinion-oriented exchanges that Emora delivers, and new conversational abilities are developed that support dialogues that consist of a collaborative understanding and learning process of the partner's life experiences. We present a curated dialogue system that leverages highly expressive natural language templates, powerful intent classification, and ontology resources to provide an engaging and interesting conversational experience to every user.
Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive. We show that lightweight augmentation, a set of augmentation methods involving word span and sentence level operations, alleviates data scarcity problems. Our experiments on limited data settings show that lightweight augmentation yields significant performance improvement on slot filling on the ATIS and SNIPS datasets, and achieves competitive performance with respect to more complex, state-of-the-art, augmentation approaches. Furthermore, lightweight augmentation is also beneficial when combined with pre-trained LM-based models, as it improves BERT-based joint intent and slot filling models.
This paper investigates the Cyber-Physical behavior of users in a large indoor shopping mall by leveraging anonymized (opt in) Wi-Fi association and browsing logs recorded by the mall operators. Our analysis shows that many users exhibit a high correlation between their cyber activities and their physical context. To find this correlation, we propose a mechanism to semantically label a physical space with rich categorical information from DBPedia concepts and compute a contextual similarity that represents a user's activities with the mall context. We demonstrate the application of cyber-physical contextual similarity in two situations: user visit intent classification and future location prediction. The experimental results demonstrate that exploitation of contextual similarity significantly improves the accuracy of such applications.
Despite the fact that data imbalance is becoming more and more common in real-world Spoken Language Understanding (SLU) applications, it has not been studied extensively in the literature. To the best of our knowledge, this paper presents the first systematic study on handling data imbalance for SLU. In particular, we discuss the application of existing data balancing techniques for SLU and propose a multi-task SLU model for intent classification and slot filling. Aiming to avoid over-fitting, in our model methods for data balancing are leveraged indirectly via an auxiliary task which makes use of a class-balanced batch generator and (possibly) synthetic data. Our results on a real-world dataset indicate that i) our proposed model can boost performance on low frequency intents significantly while avoiding a potential performance decrease on the head intents, ii) synthetic data are beneficial for bootstrapping new intents when realistic data are not available, but iii) once a certain amount of realistic data becomes available, using synthetic data in the auxiliary task only yields better performance than adding them to the primary task training data, and iv) in a joint training scenario, balancing the intent distribution individually improves not only intent classification but also slot filling performance.
End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One question arises from this: how to train an end-to-end SLU with limited amounts of data? Many researchers have explored approaches that make use of other related data resources, typically by pre-training parts of the model on high-resource speech recognition. In this paper, we suggest improving the generalization performance of SLU models with a non-standard learning algorithm, Reptile. Though Reptile was originally proposed for model-agnostic meta learning, we argue that it can also be used to directly learn a target task and result in better generalization than conventional gradient descent. In this work, we employ Reptile to the task of end-to-end spoken intent classification. Experiments on four datasets of different languages and domains show improvement of intent prediction accuracy, both when Reptile is used alone and used in addition to pre-training.
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made it much easier to achieve this. Still, there may still be subtle differences between languages that are neglected when doing so. To address this, we present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language. Compared with a number of strong baselines, we observe significant gains in effectiveness on document and intent classification for a diverse set of languages.
Chatbot is a technology that is used to mimic human behavior using natural language. There are different types of Chatbot that can be used as conversational agent in various business domains in order to increase the customer service and satisfaction. For any business domain, it requires a knowledge base to be built for that domain and design an information retrieval based system that can respond the user with a piece of documentation or generated sentences. The core component of a Chatbot is Natural Language Understanding (NLU) which has been impressively improved by deep learning methods. But we often lack such properly built NLU modules and requires more time to build it from scratch for high quality conversations. This may encourage fresh learners to build a Chatbot from scratch with simple architecture and using small dataset, although it may have reduced functionality, rather than building high quality data driven methods. This research focuses on Named Entity Recognition (NER) and Intent Classification models which can be integrated into NLU service of a Chatbot. Named entities will be inserted manually in the knowledge base and automatically detected in a given sentence. The NER model in the proposed architecture is based on artificial neural network which is trained on manually created entities and evaluated using CoNLL-2003 dataset.
Code-mixing is the phenomenon of using multiple languages in the same utterance of a text or speech. It is a frequently used pattern of communication on various platforms such as social media sites, online gaming, product reviews, etc. Sentiment analysis of the monolingual text is a well-studied task. Code-mixing adds to the challenge of analyzing the sentiment of the text due to the non-standard writing style. We present a candidate sentence generation and selection based approach on top of the Bi-LSTM based neural classifier to classify the Hinglish code-mixed text into one of the three sentiment classes positive, negative, or neutral. The proposed approach shows an improvement in the system performance as compared to the Bi-LSTM based neural classifier. The results present an opportunity to understand various other nuances of code-mixing in the textual data, such as humor-detection, intent classification, etc.
User intent understanding is a crucial step in designing both conversational agents and search engines. Detecting or inferring user intent is challenging, since the user utterances or queries can be short, ambiguous, and contextually dependent. To address these research challenges, my thesis work focuses on: 1) Utterance topic and intent classification for conversational agents 2) Query intent mining and classification for Web search engines, focusing on the e-commerce domain. To address the first topic, I proposed novel models to incorporate entity information and conversation-context clues to predict both topic and intent of the user's utterances. For the second research topic, I plan to extend the existing state of the art methods in Web search intent prediction to the e-commerce domain, via: 1) Developing a joint learning model to predict search queries' intents and the product categories associated with them, 2) Discovering new hidden users' intents. All the models will be evaluated on the real queries available from a major e-commerce site search engine. The results from these studies can be leveraged to improve performance of various tasks such as natural language understanding, query scoping, query suggestion, and ranking, resulting in an enriched user experience.
Email remains one of the most frequently used means of online communication. People spend a significant amount of time every day on emails to exchange information, manage tasks and schedule events. Previous work has studied different ways for improving email productivity by prioritizing emails, suggesting automatic replies or identifying intents to recommend appropriate actions. The problem has been mostly posed as a supervised learning problem where models of different complexities were proposed to classify an email message into a predefined taxonomy of intents or classes. The need for labeled data has always been one of the largest bottlenecks in training supervised models. This is especially the case for many real-world tasks, such as email intent classification, where large scale annotated examples are either hard to acquire or unavailable due to privacy or data access constraints. Email users often take actions in response to intents expressed in an email (e.g., setting up a meeting in response to an email with a scheduling request). Such actions can be inferred from user interaction logs. In this paper, we propose to leverage user actions as a source of weak supervision, in addition to a limited set of annotated examples, to detect intents in emails. We develop an end-to-end robust deep neural network model for email intent identification that leverages both clean annotated data and noisy weak supervision along with a self-paced learning mechanism. Extensive experiments on three different intent detection tasks show that our approach can effectively leverage the weakly supervised data to improve intent detection in emails.
Citations play a vital role in understanding the impact of scientific literature. Generally, citations are analyzed quantitatively whereas qualitative analysis of citations can reveal deeper insights into the impact of a scientific artifact in the community. Therefore, citation impact analysis (which includes sentiment and intent classification) enables us to quantify the quality of the citations which can eventually assist us in the estimation of ranking and impact. The contribution of this paper is two-fold. First, we benchmark the well-known language models like BERT and ALBERT along with several popular networks for both tasks of sentiment and intent classification. Second, we provide ImpactCite, which is XLNet-based method for citation impact analysis. All evaluations are performed on a set of publicly available citation analysis datasets. Evaluation results reveal that ImpactCite achieves a new state-of-the-art performance for both citation intent and sentiment classification by outperforming the existing approaches by 3.44% and 1.33% in F1-score. Therefore, we emphasize ImpactCite (XLNet-based solution) for both tasks to better understand the impact of a citation. Additional efforts have been performed to come up with CSC-Clean corpus, which is a clean and reliable dataset for citation sentiment classification.
Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an NLU system to new languages use machine translation with slot label projection from source to the translated utterances, and thus are sensitive to projection errors. In this work, we propose a novel end-to-end model that learns to align and predict target slot labels jointly for cross-lingual transfer. We introduce MultiATIS++, a new multilingual NLU corpus that extends the Multilingual ATIS corpus to nine languages across four language families, and evaluate our method using the corpus. Results show that our method outperforms a simple label projection method using fast-align on most languages, and achieves competitive performance to the more complex, state-of-the-art projection method with only half of the training time. We release our MultiATIS++ corpus to the community to continue future research on cross-lingual NLU.
Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.
We develop a chatbot using Deep Bidirectional Transformer models (BERT) to handle client questions in financial investment customer service. The bot can recognize 381 intents, and decides when to say "I don't know" and escalates irrelevant/uncertain questions to human operators. Our main novel contribution is the discussion about uncertainty measure for BERT, where three different approaches are systematically compared on real problems. We investigated two uncertainty metrics, information entropy and variance of dropout sampling in BERT, followed by mixed-integer programming to optimize decision thresholds. Another novel contribution is the usage of BERT as a language model in automatic spelling correction. Inputs with accidental spelling errors can significantly decrease intent classification performance. The proposed approach combines probabilities from masked language model and word edit distances to find the best corrections for misspelled words. The chatbot and the entire conversational AI system are developed using open-source tools, and deployed within our company's intranet. The proposed approach can be useful for industries seeking similar in-house solutions in their specific business domains. We share all our code and a sample chatbot built on a public dataset on Github.
Question-answering (QA) is certainly the best known and probably also one of the most complex problem within Natural Language Processing (NLP) and artificial intelligence (AI). Since the complete solution to the problem of finding a generic answer still seems far away, the wisest thing to do is to break down the problem by solving single simpler parts. Assuming a modular approach to the problem, we confine our research to intent classification for an answer, given a question. Through the use of an LSTM network, we show how this type of classification can be approached effectively and efficiently, and how it can be properly used within a basic prototype responder.
In a modern spoken language understanding (SLU) system, the natural language understanding (NLU) module takes interpretations of a speech from the automatic speech recognition (ASR) module as the input. The NLU module usually uses the first best interpretation of a given speech in downstream tasks such as domain and intent classification. However, the ASR module might misrecognize some speeches and the first best interpretation could be erroneous and noisy. Solely relying on the first best interpretation could make the performance of downstream tasks non-optimal. To address this issue, we introduce a series of simple yet efficient models for improving the understanding of semantics of the input speeches by collectively exploiting the n-best speech interpretations from the ASR module.
In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel encoding scheme in BERT, a powerful language representation model solely based on attention mechanisms. Incomplete data in natural language processing refer to text with missing or incorrect words, and its presence can hinder the performance of current models that were not implemented to withstand such noises, but must still perform well even under duress. This is due to the fact that current approaches are built for and trained with clean and complete data, and thus are not able to extract features that can adequately represent incomplete data. Our proposed approach consists of obtaining intermediate input representations by applying an embedding layer to the input tokens followed by vanilla transformers. These intermediate features are given as input to novel denoising transformers which are responsible for obtaining richer input representations. The proposed approach takes advantage of stacks of multilayer perceptrons for the reconstruction of missing words' embeddings by extracting more abstract and meaningful hidden feature vectors, and bidirectional transformers for improved embedding representation. We consider two datasets for training and evaluation: the Chatbot Natural Language Understanding Evaluation Corpus and Kaggle's Twitter Sentiment Corpus. Our model shows improved F1-scores and better robustness in informal/incorrect texts present in tweets and in texts with Speech-to-Text error in the sentiment and intent classification tasks.