Related papers: Learning to Write with Coherence From Negative Exa…
In this paper, we study sequence-to-sequence (S2S) keyphrase generation models from the perspective of diversity. Recent advances in neural natural language generation have made possible remarkable progress on the task of keyphrase…
Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…
Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…
Contrastive learning shows great potential in unpaired image-to-image translation, but sometimes the translated results are in poor quality and the contents are not preserved consistently. In this paper, we uncover that the negative…
Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to the input specification. In this paper, we show the impact of semantic noise on state-of-the-art NNLG…
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method…
To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classification problem.…
Automated evaluation of open domain natural language generation (NLG) models remains a challenge and widely used metrics such as BLEU and Perplexity can be misleading in some cases. In our paper, we propose to evaluate natural language…
Machine unlearning, the ability to erase the effect of specific training samples without retraining from scratch, is critical for privacy, regulation, and efficiency. However, most progress in unlearning has been empirical, with little…
Providing feedback is widely recognized as crucial for refining students' writing skills. Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-aligned with…
Contrastive learning has proven to be an effective method for pre-training models using weakly labeled data in the vision domain. Sentence transformers are the NLP counterparts to this architecture, and have been growing in popularity due…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…
Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…
It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…
The field of Natural Language Generation (NLG) suffers from a severe shortage of labeled data due to the extremely expensive and time-consuming process involved in manual annotation. A natural approach for coping with this problem is active…
Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…
Lifelong Reinforcement Learning (LRL) holds significant potential for addressing sequential tasks, but it still faces considerable challenges. A key difficulty lies in effectively preventing catastrophic forgetting and facilitating…
Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to the absence of ground-truth labels. While LLM-as-Judge approaches offer a scalable…
The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language…
In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e.g.,…