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 teacher-student framework across speech and text modalities that aligns the acoustic and the semantic latent spaces. Experimental results in three benchmarks show that our system reaches the performance comparable to the pipeline architecture without using any training data and outperforms it after fine-tuning with ten examples per class on two out of three benchmarks.
Training a spoken language understanding system, as the one in Alexa, typically requires a large human-annotated corpus of data. Manual annotations are expensive and time consuming. In Alexa Skill Kit (ASK) user experience with the skill greatly depends on the amount of data provided by skill developer. In this work, we present an automatic natural language generation system, capable of generating both human-like interactions and annotations by the means of paraphrasing. Our approach consists of machine translation (MT) inspired encoder-decoder deep recurrent neural network. We evaluate our model on the impact it has on ASK skill, intent, named entity classification accuracy and sentence level coverage, all of which demonstrate significant improvements for unseen skills on natural language understanding (NLU) models, trained on the data augmented with paraphrases.
Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SLU module. To address this issue, word confusion networks (WCNs) have been used to encode the input for SLU, which contain richer information than 1-best or n-best hypotheses list. To further eliminate ambiguity, the last system act of dialogue context is also utilized as additional input. In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly. It can integrate both structural information and ASR posterior probabilities of WCNs in the BERT architecture. Experiments on DSTC2, a benchmark of SLU, show that the proposed method is effective and can outperform previous state-of-the-art models significantly.
Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior probability has frequently been discarded in understanding the natural language. Thus, some recent spoken language understanding (SLU) modules have utilized end-to-end structures that preserve the uncertainty information. This further reduces the propagation of speech recognition error and guarantees computational efficiency. We claim that in this process, the speech comprehension can benefit from the inference of massive pre-trained language models (LMs). We transfer the knowledge from a concrete Transformer-based text LM to an SLU module which can face a data shortage, based on recent cross-modal distillation methodologies. We demonstrate the validity of our proposal upon the performance on Fluent Speech Command, an English SLU benchmark. Thereby, we experimentally verify our hypothesis that the knowledge could be shared from the top layer of the LM to a fully speech-based module, in which the abstracted speech is expected to meet the semantic representation.
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain. However, annotating data for each domain is both financially costly and non-scalable so we should fully utilize information across all domains. One existing approach solves the problem by conducting multi-domain learning, using shared parameters for joint training across domains. We propose to improve the parameterization of this method by using domain-specific and task-specific model parameters to improve knowledge learning and transfer. Experiments on 5 domains show that our model is more effective for multi-domain SLU and obtain the best results. In addition, we show its transferability by outperforming the prior best model by 12.4\% when adapting to a new domain with little data.
The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of generated utterances. Furthermore, we investigate and propose solutions to two previously overlooked semi-supervised learning scenarios of data scarcity in SLU: i) Rich-in-Ontology: ontology information with numerous valid dialogue acts is given; ii) Rich-in-Utterance: a large number of unlabelled utterances are available. Empirical results show that our method can produce synthetic training data that boosts the performance of language understanding models in various scenarios.
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to deal with errors by ASR. Moreover, there are acoustic features which are related with intents but not represented with the transcripts. In this paper, we present an end-to-end model which directly converts speech into dialog acts without the deterministic transcription process. In the proposed model, the dialog act recognition network is conjunct with an acoustic-to-word ASR model at its latent layer before the softmax layer, which provides a distributed representation of word-level ASR decoding information. Then, the entire network is fine-tuned in an end-to-end manner. This allows for stable training as well as robustness against ASR errors. The model is further extended to conduct DA segmentation jointly. Evaluations with the Switchboard corpus demonstrate that the proposed method significantly improves dialog act recognition accuracy from the conventional pipeline framework.
In real-world scenarios, users usually have multiple intents in the same utterance. Unfortunately, most spoken language understanding (SLU) models either mainly focused on the single intent scenario, or simply incorporated an overall intent context vector for all tokens, ignoring the fine-grained multiple intents information integration for token-level slot prediction. In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling, where we introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction. Experimental results on three multi-intent datasets show that our framework obtains substantial improvement and achieves the state-of-the-art performance. In addition, our framework achieves new state-of-the-art performance on two single-intent datasets.
Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of these using Recurrent-Neural-Networks (RNN), Convolution Neural Networks (CNN) and Attention based models. Most of the past work used two separate models for intent and slot prediction. Some of them also used sequence-to-sequence type models where slots are predicted after evaluating the utterance-level intent. In this work, we propose a parallel Intent and Slot Prediction technique where separate Bidirectional Gated Recurrent Units (GRU) are used for each task. We posit the usage of MLB (Multimodal Low-rank Bilinear Attention Network) fusion for improvement in performance of intent and slot learning. To the best of our knowledge, this is the first attempt of using such a technique on text based problems. Also, our proposed methods outperform the existing state-of-the-art results for both intent and slot prediction on two benchmark datasets
Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly improves SLU performance for multi-turn dialogues. However, collecting a large-scale human-labeled multi-turn dialogue corpus for the target domains is complex and costly. To reduce dependency on the collection and annotation effort, we propose a Context Encoding Language Transformer (CELT) model facilitating exploiting various context information for SLU. We explore different transfer learning approaches to reduce dependency on data collection and annotation. In addition to unsupervised pre-training using large-scale general purpose unlabeled corpora, such as Wikipedia, we explore unsupervised and supervised adaptive training approaches for transfer learning to benefit from other in-domain and out-of-domain dialogue corpora. Experimental results demonstrate that the proposed model with the proposed transfer learning approaches achieves significant improvement on the SLU performance over state-of-the-art models on two large-scale single-turn dialogue benchmarks and one large-scale multi-turn dialogue benchmark.
We explore a keyword-based spoken language understanding system, in which the intent of the user can directly be derived from the detection of a sequence of keywords in the query. In this paper, we focus on an open-vocabulary keyword spotting method, allowing the user to define their own keywords without having to retrain the whole model. We describe the different design choices leading to a fast and small-footprint system, able to run on tiny devices, for any arbitrary set of user-defined keywords, without training data specific to those keywords. The model, based on a quantized long short-term memory (LSTM) neural network, trained with connectionist temporal classification (CTC), weighs less than 500KB. Our approach takes advantage of some properties of the predictions of CTC-trained networks to calibrate the confidence scores and implement a fast detection algorithm. The proposed system outperforms a standard keyword-filler model approach.
This work investigates the embeddings for representing dialog history in spoken language understanding (SLU) systems. We focus on the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. We proposed to integrate dialogue history into an end-to-end signal-to-concept SLU system. The dialog history is represented in the form of dialog history embedding vectors (so-called h-vectors) and is provided as an additional information to end-to-end SLU models in order to improve the system performance. Three following types of h-vectors are proposed and experimentally evaluated in this paper: (1) supervised-all embeddings predicting bag-of-concepts expected in the answer of the user from the last dialog system response; (2) supervised-freq embeddings focusing on predicting only a selected set of semantic concept (corresponding to the most frequent errors in our experiments); and (3) unsupervised embeddings. Experiments on the MEDIA corpus for the semantic slot filling task demonstrate that the proposed h-vectors improve the model performance.
End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures give very good results in the context of domain, intent and slot detection, their application in a more complex semantic chunking and tagging task is less easy. For that, in many cases, models are combined with an external language model to enhance their performance. In this paper we introduce a data efficient system which is trained end-to-end, with no additional, pre-trained external module. One key feature of our approach is an incremental training procedure where acoustic, language and semantic models are trained sequentially one after the other. The proposed model has a reasonable size and achieves competitive results with respect to state-of-the-art while using a small training dataset. In particular, we reach 24.02% Concept Error Rate (CER) on MEDIA/test while training on MEDIA/train without any additional data.
Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the errors originate from various sources such as speech recognition errors, language understanding errors or entity resolution errors. In this work, we first propose a neural-retrieval based approach for query rewriting. Then, inspired by the wide success of pre-trained contextual language embeddings, and also as a way to compensate for insufficient QR training data, we propose a language-modeling (LM) based approach to pre-train query embeddings on historical user conversation data with a voice assistant. In addition, we propose to use the NLU hypotheses generated by the language understanding system to augment the pre-training. Our experiments show pre-training provides rich prior information and help the QR task achieve strong performance. We also show joint pre-training with NLU hypotheses has further benefit. Finally, after pre-training, we find a small set of rewrite pairs is enough to fine-tune the QR model to outperform a strong baseline by full training on all QR training data.
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained speech recognizer and natural language understanding module. The downside of end-to-end SLU is that in-domain speech data must be recorded to train the model. In this paper, we propose a strategy for overcoming this requirement in which speech synthesis is used to generate a large synthetic training dataset from several artificial speakers. Experiments on two open-source SLU datasets confirm the effectiveness of our approach, both as a sole source of training data and as a form of data augmentation.
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.
Spoken Language Understanding (SLU) systems consist of several machine learning components operating together (e.g. intent classification, named entity recognition and resolution). Deep learning models have obtained state of the art results on several of these tasks, largely attributed to their better modeling capacity. However, an increase in modeling capacity comes with added costs of higher latency and energy usage, particularly when operating on low complexity devices. To address the latency and computational complexity issues, we explore a BranchyNet scheme on an intent classification scheme within SLU systems. The BranchyNet scheme when applied to a high complexity model, adds exit points at various stages in the model allowing early decision making for a set of queries to the SLU model. We conduct experiments on the Facebook Semantic Parsing dataset with two candidate model architectures for intent classification. Our experiments show that the BranchyNet scheme provides gains in terms of computational complexity without compromising model accuracy. We also conduct analytical studies regarding the improvements in the computational cost, distribution of utterances that egress from various exit points and the impact of adding more complexity to models with the BranchyNet scheme.
The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion corpora contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with and without context. These neural models annotate the emotion corpora with dialogue act labels, and an ensemble annotator extracts the final dialogue act label. We annotated two accessible multi-modal emotion corpora: IEMOCAP and MELD. We analyzed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Acts (EDA) corpus publicly available to the research community for further study and analysis.
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 information in two different levels, i.e., representation level and task-specific (i.e., label) level. Our extensive experiments on three benchmark datasets on SF show the effectiveness of our model leading to new state-of-the-art results on all three benchmark datasets for the task of SF.
We propose two methods to capture relevant history information in a multi-turn dialogue by modeling inter-speaker relationship for spoken language understanding (SLU). Our methods are tailored for and therefore compatible with XLNet, which is a state-of-the-art pretrained model, so we verified our models built on the top of XLNet. In our experiments, all models achieved higher accuracy than state-of-the-art contextual SLU models on two benchmark datasets. Analysis on the results demonstrated that the proposed methods are effective to improve SLU accuracy of XLNet. These methods to identify important dialogue history will be useful to alleviate ambiguity in SLU of the current utterance.