Related papers: Crowd-sourcing NLG Data: Pictures Elicit Better Da…

Neural language models (LMs) based on recurrent neural networks (RNN) are some of the most successful word and character-level LMs. Why do they work so well, in particular better than linear neural LMs? Possible explanations are that RNNs…

When we read, our brain processes language and generates cognitive processing data such as gaze patterns and brain activity. These signals can be recorded while reading. Cognitive language processing data such as eye-tracking features have…

The growing spread of online misinformation has created an urgent need for scalable, reliable fact-checking solutions. Crowdsourced fact-checking - where non-experts evaluate claim veracity - offers a cost-effective alternative to expert…

Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual clarity by…

Statistical language models conventionally implement representation learning based on the contextual distribution of words or other formal units, whereas any information related to the logographic features of written text are often ignored,…

In recent years, a significant number of high-quality pretrained models have emerged, greatly impacting Natural Language Understanding (NLU), Natural Language Generation (NLG), and Text Representation tasks. Traditionally, these models are…

Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular…

Concept generation is a creative step in the conceptual design phase, where designers often turn to brainstorming, mindmapping, or crowdsourcing design ideas to complement their own knowledge of the domain. Recent advances in natural…

Natural Language Processing (NLP) has become one of the leading application areas in the current Artificial Intelligence boom. Transfer learning has enabled large deep learning neural networks trained on the language modeling task to vastly…

Many crowdsourced NLP datasets contain systematic gaps and biases that are identified only after data collection is complete. Identifying these issues from early data samples during crowdsourcing should make mitigation more efficient,…

Large language models (LLMs) have shown great potential in story generation, but challenges remain in maintaining long-form coherence and effective, user-friendly control. Retrieval-augmented generation (RAG) has proven effective in…

Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging.…

Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP, enhancing large language models (LLMs) by allowing them to access richer factual contexts through in-context retrieval. While effective in monolingual…

LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional…

Large language models (LLMs) have revolutionised many fields, with LLM-as-a-service (LLMSaaS) offering accessible, general-purpose solutions without costly task-specific training. In contrast to the widely studied prompt engineering for…

Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a robust and well-behaved dialogue model. However, due to the…

Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs…

Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural…

Robotic commands in natural language usually contain various spatial descriptions that are semantically similar but syntactically different. Mapping such syntactic variants into semantic concepts that can be understood by robots is…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…