Analysis of Language Change in Collaborative Instruction Following

• URL: http://arxiv.org/abs/2109.04452v1
• Date: Thu, 9 Sep 2021 17:51:59 GMT
• Title: Analysis of Language Change in Collaborative Instruction Following
• Authors: Anna Effenberger, Eva Yan, Rhia Singh, Alane Suhr, Yoav Artzi
• Abstract summary: We analyze language change over time in a collaborative, goal-oriented instructional task, where utility-maximizing participants form conventions and increase their expertise. We find that, given the ability to increase instruction utility, instructors increase language complexity along these previously studied dimensions to better collaborate with increasingly skilled instruction followers.
• Score: 15.605114421965045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We analyze language change over time in a collaborative, goal-oriented instructional task, where utility-maximizing participants form conventions and increase their expertise. Prior work studied such scenarios mostly in the context of reference games, and consistently found that language complexity is reduced along multiple dimensions, such as utterance length, as conventions are formed. In contrast, we find that, given the ability to increase instruction utility, instructors increase language complexity along these previously studied dimensions to better collaborate with increasingly skilled instruction followers.

Related papers

• A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models [64.79218405438871]
  Recent studies have highlighted the potential of exploiting parallel corpora to enhance multilingual large language models. We investigate the impact of parallel corpora quality and quantity, training objectives, and model size on the performance of multilingual large language models enhanced with parallel corpora.
  arXiv  Detail & Related papers  (2024-06-29T13:12:39Z)
• Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training [56.74440457571821]
  We analyze tasks covering syntax, semantics and reasoning, across 2M pre-training steps and five seeds. We identify critical learning phases across tasks and time, during which subspaces emerge, share information, and later disentangle to specialize. Our findings have implications for model interpretability, multi-task learning, and learning from limited data.
  arXiv  Detail & Related papers  (2023-10-25T09:09:55Z)
• IdEALS: Idiomatic Expressions for Advancement of Language Skills [46.42809610978052]
  We present our investigation into the task of incorporating the usage of idiomatic expressions in student writing. To facilitate our study, we curate extensive training sets and expert-annotated testing sets using real-world data and evaluate various approaches and compare their performance against human experts.
  arXiv  Detail & Related papers  (2023-05-23T03:11:41Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks [33.765874588342285]
  Infusing language models with syntactic or semantic knowledge from structural linguistic priors has shown improvements on many language understanding tasks. We conduct empirical study of replacing parsed graphs or trees with trivial ones for tasks in the GLUE benchmark. It reveals that the gains might not be significantly attributed to explicit linguistic priors but rather to more feature interactions brought by fusion layers.
  arXiv  Detail & Related papers  (2022-10-24T07:47:32Z)
• Cross-lingual Lifelong Learning [53.06904052325966]
  We present a principled Cross-lingual Continual Learning (CCL) evaluation paradigm. We provide insights into what makes multilingual sequential learning particularly challenging. The implications of this analysis include a recipe for how to measure and balance different cross-lingual continual learning desiderata.
  arXiv  Detail & Related papers  (2022-05-23T09:25:43Z)
• ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning [97.10875695679499]
  We propose a novel contrastive learning framework named ERICA in pre-training phase to obtain a deeper understanding of the entities and their relations in text. Experimental results demonstrate that our proposed ERICA framework achieves consistent improvements on several document-level language understanding tasks.
  arXiv  Detail & Related papers  (2020-12-30T03:35:22Z)
• Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences [18.19093600136057]
  We propose a framework for extracting divergence patterns for any language pair from a parallel corpus. We show that our framework provides a detailed picture of cross-language divergences, generalizes previous approaches, and lends itself to full automation.
  arXiv  Detail & Related papers  (2020-05-07T13:05:03Z)
• Compositional properties of emergent languages in deep learning [12.08369037936121]
  We analyze the emergent language resulting from two different cooperative multi-agent games with more exact measures for compositionality. Our findings suggest that solutions found by deep learning models are often lacking the ability to reason on an abstract level. Strategies for testing compositional capacities and emergence of human-level concepts are discussed.
  arXiv  Detail & Related papers  (2020-01-23T15:55:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.