Related papers: Back to the Future: Bidirectional Information Deco…
Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…
End-to-end task-oriented dialogue is challenging since knowledge bases are usually large, dynamic and hard to incorporate into a learning framework. We propose the global-to-local memory pointer (GLMP) networks to address this issue. In our…
Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interact for automatic…
Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas. In this paper, we propose UBERT, a unified bidirectional language understanding model based on BERT…
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…
Deception detection is gaining increasing interest due to ethical and security concerns. This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of…
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…
Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks. In this paper, we focus on Spoken Language Understanding (SLU), the module of spoken dialog systems responsible for extracting a…
Natural Language Inference (NLI) is a fundamental and challenging task in Natural Language Processing (NLP). Most existing methods only apply one-pass inference process on a mixed matching feature, which is a concatenation of different…
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…
A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have…
Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…
Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching…
Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information…
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel…
Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large…
Full-duplex spoken dialogue systems significantly surpass traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and…
Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional…