Related papers: A Robust Semantic Frame Parsing Pipeline on a New …
Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained language models (PLMs), they exhibit limitations regarding…
This paper presents a semantic parsing approach for unrestricted texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and usually requires building expensive resources not easily portable…
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual…
The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It…
With the growth of social medias, such as Twitter, plenty of user-generated data emerge daily. The short texts published on Twitter -- the tweets -- have earned significant attention as a rich source of information to guide many…
We provide efficient support for applications that aim to continuously find pairs of similar sets in rapid streams of sets. A prototypical example setting is that of tweets. A tweet is a set of words, and Twitter emits about half a billion…
Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. Recently, recurrent neural networks (RNNs) based methods achieved the…
In Data-Oriented Parsing (DOP), an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new input sentence is constructed by combining sub-analyses from the corpus in the most probable way. This…
In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely…
Spoken Language Understanding (SLU) typically comprises of an automatic speech recognition (ASR) followed by a natural language understanding (NLU) module. The two modules process signals in a blocking sequential fashion, i.e., the NLU…
Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation criterion in a fully data driven fashion. These models allow…
Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they…
Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously,…
Twitter is one of the most popular social media. Due to the ease of availability of data, Twitter is used significantly for research purposes. Twitter is known to evolve in many aspects from what it was at its birth; nevertheless, how it…
In spoken Keyword Search, the query may contain out-of-vocabulary (OOV) words not observed when training the speech recognition system. Using subword language models (LMs) in the first-pass recognition makes it possible to recognize the OOV…
Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text,…
As Automatic Speech Processing (ASR) systems are getting better, there is an increasing interest of using the ASR output to do downstream Natural Language Processing (NLP) tasks. However, there are few open source toolkits that can be used…
Multi-intent Spoken Language Understanding has great potential for widespread implementation. Jointly modeling Intent Detection and Slot Filling in it provides a channel to exploit the correlation between intents and slots. However, current…
Nowadays, topic classification from tweets attracts considerable research attention. Different classification systems have been suggested thanks to these research efforts. Nevertheless, they face major challenges owing to low performance…
Every day, hundreds of millions of new Tweets containing over 40 languages of ever-shifting vernacular flow through Twitter. Models that attempt to extract insight from this firehose of information must face the torrential covariate shift…