One of the first steps in building a spoken language understanding (SLU) module for dialogue systems is the extraction of flat concepts out of a given word sequence, usually provided by an automatic speech recognition (ASR) system. In this paper, six different modeling approaches are investigated to tackle the task of concept tagging. These methods include classical, well-known generative and discriminative methods like Finite State Transducers (FSTs), Statistical Machine Translation (SMT), Maximum Entropy Markov Models (MEMMs), or Support Vector Machines (SVMs) as well as techniques recently applied to natural language processing such as Conditional Random Fields (CRFs) or Dynamic Bayesian Networks (DBNs). Following a detailed description of the models, experimental and comparative results are presented on three corpora in different languages and with different complexity. The French MEDIA corpus has already been exploited during an evaluation campaign and so a direct comparison with existing benchmarks is possible. Recently collected Italian and Polish corpora are used to test the robustness and portability of the modeling approaches. For all tasks, manual transcriptions as well as ASR inputs are considered. Additionally to single systems, methods for system combination are investigated. The best performing model on all tasks is based on conditional random fields. On the MEDIA evaluation corpus, a concept error rate of 12.6% could be achieved. Here, additionally to attribute names, attribute values have been extracted using a combination of a rule-based and a statistical approach. Applying system combination using weighted ROVER with all six systems, the concept error rate (CER) drops to 12.0%.

Modeling target label dependencies is important for sequence labeling tasks. This may become crucial in the case of Spoken Language Understanding (SLU) applications, especially for the slot-filling task where models have to deal often with a high number of target labels. Conditional Random Fields (CRF) were previously considered as the most efficient algorithm in these conditions. More recently, different architectures of Recurrent Neural Networks (RNNs) have been proposed for the SLU slot-filling task. Most of them, however, have been successfully evaluated on the simple ATIS database, on which it is difficult to draw significant conclusions. In this paper we propose new variants of RNNs able to learn efficiently and effectively label dependencies by integrating label embeddings. We show first that modeling label dependencies is useless on the (simple) ATIS database and unstructured models can produce state-of-the-art results on this benchmark. On ATIS our new variants achieve the same results as state-of-the-art models, while being much simpler. On the other hand, on the MEDIA benchmark, we show that the modification introduced in the proposed RNN outperforms traditional RNNs and CRF models.

No abstract

In this paper we study different architectures of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNN and we compare them to the more traditional RNN architectures of Elman and Jordan. We explain in details the advantages of these new variants of RNNs with respect to Elman's and Jordan's RNN. We evaluate all models, either new or traditional, on three different tasks: POS-tagging of the French Treebank, and two tasks of Spoken Language Understanding (SLU), namely ATIS and MEDIA. The results we obtain clearly show that the new variants of RNN are more effective than the traditional ones.

Abstract-Spoken Language Understanding (SLU) is concerned with the extraction of meaning structures from spoken utterances. Recent computational approaches to SLU, e.g. Conditional Random Fields (CRF), optimize local models by encoding several features, mainly based on simple n-grams. In contrast, recent works have shown that the accuracy of CRF can be significantly improved by modeling long-distance dependency features. In this paper, we propose novel approaches to encode all possible dependencies between features and most importantly among parts of the meaning structure, e.g. concepts and their combination. We rerank hypotheses generated by local models, e.g. Stochastic Finite State Transducers (SFSTs) or Conditional Random Fields (CRF), with a global model. The latter encodes a very large number of dependencies (in the form of trees or sequences) by applying kernel methods to the space of all meaning (sub) structures. We performed comparative experiments between SFST, CRF, Support Vector Machines (SVMs) and our proposed discriminative reranking models (DRMs) on representative conversational speech corpora in three different languages: the ATIS (English), the MEDIA (French) and the LUNA (Italian) corpora. These corpora have been collected within three different domain applications of increasing complexity: informational, transactional and problemsolving tasks, respectively. The results show that our DRMs consistently outperform the state-of-the-art models based on CRF.

No abstract

In the last few years, Recurrent Neural Networks (RNNs) have proved effective on several NLP tasks. Despite such great success, their ability to model sequence labeling is still limited. This lead research toward solutions where RNNs are combined with models which already proved effective in this domain, such as CRFs. In this work we propose a solution far simpler but very effective: an evolution of the simple Jordan RNN, where labels are re-injected as input into the network, and converted into embeddings, in the same way as words. We compare this RNN variant to all the other RNN models, Elman and Jordan RNN, LSTM and GRU, on two well-known tasks of Spoken Language Understanding (SLU). Thanks to label embeddings and their combination at the hidden layer, the proposed variant, which uses more parameters than Elman and Jordan RNNs, but far fewer than LSTM and GRU, is more effective than other RNNs, but also outperforms sophisticated CRF models.

Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA corpus (human-machine dialogs) and on a new corpus (human-machine and humanhuman dialogs) produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.