Related papers: A New Data Normalization Method to Improve Dialogu…

The automatic verbalization of structured knowledge is a key task for making knowledge graphs accessible to non-expert users and supporting retrieval-augmented generation systems. Although recent advances in Data-to-Text generation have…

How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of various models to questions with multiple possible answers, comparing them with human responses. Our findings suggest…

Generating natural language text from graph-structured data is essential for conversational information seeking. Semantic triples derived from knowledge graphs can serve as a valuable source for grounding responses from conversational…

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…

Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request. In such system, the agent is responsible for serving thousands of skills…

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions…

State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens, tackling which remains a major challenge. The analysis of long-tailed phenomena in the context of structured prediction tasks is further…

Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly…

Recent advances in large language model (LLM) training have highlighted the need for diverse, high-quality instruction data. Recently, many works are exploring synthetic data generation using LLMs. However, they primarily focus on prompt…

Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have been various useful efforts on trying to eliminate them. However, these approaches either improve decoding algorithms during inference,…

In the context of the long-tail scenario, models exhibit a strong demand for high-quality data. Data-centric approaches aim to enhance both the quantity and quality of data to improve model performance. Among these approaches, information…

In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we…

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…

Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive to obtain and would be small-scale. In this paper we investigate the challenging task of…

Children learn to speak with a low amount of data and can be taught new words on a few-shot basis, making them particularly data-efficient learners. The BabyLM challenge aims at exploring language model (LM) training in the low-data regime…

Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling,…

After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution…

In our dynamic world where data arrives in a continuous stream, continual learning enables us to incrementally add new tasks/domains without the need to retrain from scratch. A major challenge in continual learning of language model is…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…