Related papers: MTOP: A Comprehensive Multilingual Task-Oriented S…
Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified…
As language models improve and become capable of performing more complex tasks across modalities, evaluating them automatically becomes increasingly challenging. Developing strong and robust task-specific automatic metrics gets harder, and…
Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover every example. We introduce a new dataset that includes queries…
Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging new user…
Multilingual intent classification is central to customer-service systems on global logistics platforms, where models must process noisy user queries across languages and hierarchical label spaces. Yet most existing multilingual benchmarks…
Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant…
Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…
The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex reasoning remain underexplored, with existing efforts largely…
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…
Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…
Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue…
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures…
Since the release of ChatGPT, the field of Natural Language Processing has experienced rapid advancements, particularly in Large Language Models (LLMs) and their multimodal counterparts, Large Multimodal Models (LMMs). Despite their…
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…
Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level…
Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in terms of intents and slots contained in task-specific…
The MS MARCO ranking dataset has been widely used for training deep learning models for IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this type of resource is scarce in languages other than English.…
In this paper, we introduce an important yet relatively unexplored NLP task called Multi-Narrative Semantic Overlap (MNSO), which entails generating a Semantic Overlap of multiple alternate narratives. As no benchmark dataset is readily…
Evaluation datasets are critical resources for measuring the quality of pretrained language models. However, due to the high cost of dataset annotation, these resources are scarce for most languages other than English, making it difficult…
This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text…