Related papers: CEC-Zero: Zero-Supervision Character Error Correct…
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…
The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems…
Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answers, which is…
Multi-level sentence simplification generates simplified sentences with varying language proficiency levels. We propose Label Confidence Weighted Learning (LCWL), a novel approach that incorporates a label confidence weighting scheme in the…
Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the datasets, and on how…
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…
Fine-grained labor market analysis increasingly relies on mapping unstructured job advertisements to standardized skill taxonomies such as ESCO. This mapping is naturally formulated as an Extreme Multi-Label Classification (XMLC) problem,…
We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (ESD) and Erroneous Span Correction (ESC). ESD identifies…
This paper investigates how to correct Chinese text errors with types of mistaken, missing and redundant characters, which is common for Chinese native speakers. Most existing models based on detect-correct framework can correct mistaken…
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…
Sentence Simplification is a valuable technique that can benefit language learners and children a lot. However, current research focuses more on English sentence simplification. The development of Chinese sentence simplification is…
Owing to the continuous efforts by the Chinese NLP community, more and more Chinese machine reading comprehension datasets become available. To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style…
Automatic speech Recognition (ASR) is a fundamental and important task in the field of speech and natural language processing. It is an inherent building block in many applications such as voice assistant, speech translation, etc. Despite…
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot…
Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches. Similarity-based approaches attempt to classify instances based on similarities between…
We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through…
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…
Rhetoric recognition is a critical component in automated essay scoring. By identifying rhetorical elements in student writing, AI systems can better assess linguistic and higher-order thinking skills, making it an essential task in the…
Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-supervised learning methods achieved impressive performance. In…
The next token prediction loss is the dominant self-supervised training objective for large language models and has achieved promising results in a variety of downstream tasks. However, upon closer investigation of this objective, we find…