Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data. (arXiv:2212.09171v1 [cs.CL])
On Isotropy and Learning Dynamics of Contrastive-based Sentence Representation Learning. (arXiv:2212.09170v1 [cs.CL])
Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model. (arXiv:2212.09146v1 [cs.CL])
Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars. (arXiv:2212.09140v1 [cs.CL])
Recall, Expand and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing. (arXiv:2212.09125v1 [cs.CL])
Curriculum Sampling for Dense Retrieval with Document Expansion. (arXiv:2212.09114v1 [cs.CL])
LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning. (arXiv:2212.09104v1 [cs.CL])
Continually Learning from Existing Models: Knowledge Accumulation for Neural Machine Translation. (arXiv:2212.09097v1 [cs.CL])
Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale. (arXiv:2212.09095v1 [cs.CL])
PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism. (arXiv:2212.09086v1 [cs.CL])
Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons & Dragons. (arXiv:2212.09080v1 [cs.CL])
Let's Negotiate! A Survey of Negotiation Dialogue Systems. (arXiv:2212.09072v1 [cs.CL])
BEATs: Audio Pre-Training with Acoustic Tokenizers. (arXiv:2212.09058v1 [eess.AS])
Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion. (arXiv:2212.09056v1 [cs.CL])
A Better Choice: Entire-space Datasets for Aspect Sentiment Triplet Extraction. (arXiv:2212.09052v1 [cs.CL])
Task Preferences across Languages on Community Question Answering Platforms. (arXiv:2212.09045v1 [cs.CL])
Neural Coreference Resolution based on Reinforcement Learning. (arXiv:2212.09028v1 [cs.CL])
Sentence-level Feedback Generation for English Language Learners: Does Data Augmentation Help?. (arXiv:2212.08999v1 [cs.CL])
Impact of Sentiment Analysis in Fake Review Detection. (arXiv:2212.08995v1 [cs.CL])
PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment. (arXiv:2212.08992v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl