Compositional Generalization with Grounded Language Models

• URL: http://arxiv.org/abs/2406.04989v1
• Date: Fri, 7 Jun 2024 14:56:51 GMT
• Title: Compositional Generalization with Grounded Language Models
• Authors: Sondre Wold, Étienne Simon, Lucas Georges Gabriel Charpentier, Egor V. Kostylev, Erik Velldal, Lilja Øvrelid,
• Abstract summary: Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. We develop a procedure for generating natural language questions paired with knowledge graphs that targets different aspects of compositionality.
• Score: 9.96679221246835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we allow for a controlled evaluation of the degree to which these models learn and generalize from patterns in knowledge graphs. We develop a procedure for generating natural language questions paired with knowledge graphs that targets different aspects of compositionality and further avoids grounding the language models in information already encoded implicitly in their weights. We evaluate existing methods for combining language models with knowledge graphs and find them to struggle with generalization to sequences of unseen lengths and to novel combinations of seen base components. While our experimental results provide some insight into the expressive power of these models, we hope our work and released datasets motivate future research on how to better combine language models with structured knowledge representations.

Related papers

• A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation [5.661396828160973]
  We conduct an empirical analysis of conversational large language models in generating natural language text from semantic triples. We compare four large language models of varying sizes with different prompting techniques. Our findings show that the capabilities of large language models in triple verbalization can be significantly improved through few-shot prompting, post-processing, and efficient fine-tuning techniques.
  arXiv  Detail & Related papers  (2024-02-02T15:26:39Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• Commonsense Knowledge Transfer for Pre-trained Language Models [83.01121484432801]
  We introduce commonsense knowledge transfer, a framework to transfer the commonsense knowledge stored in a neural commonsense knowledge model to a general-purpose pre-trained language model. It first exploits general texts to form queries for extracting commonsense knowledge from the neural commonsense knowledge model. It then refines the language model with two self-supervised objectives: commonsense mask infilling and commonsense relation prediction.
  arXiv  Detail & Related papers  (2023-06-04T15:44:51Z)
• KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction [0.0]
  We introduce a new entity/relation embedding layer that learns to differentiate distinctive entity and relation types. We show that further pre-training the language models with this additional embedding layer using the triples extracted from the knowledge graph, followed by the standard fine-tuning phase sets a new state-of-the-art performance for the link prediction task on the benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-04T20:38:12Z)
• An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs [67.23285413610243]
  Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models. We study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
  arXiv  Detail & Related papers  (2022-05-21T19:49:04Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)
• Combining pre-trained language models and structured knowledge [9.521634184008574]
  transformer-based language models have achieved state of the art performance in various NLP benchmarks. It has proven challenging to integrate structured information, such as knowledge graphs into these models. We examine a variety of approaches to integrate structured knowledge into current language models and determine challenges, and possible opportunities to leverage both structured and unstructured information sources.
  arXiv  Detail & Related papers  (2021-01-28T21:54:03Z)
• JAKET: Joint Pre-training of Knowledge Graph and Language Understanding [73.43768772121985]
  We propose a novel joint pre-training framework, JAKET, to model both the knowledge graph and language. The knowledge module and language module provide essential information to mutually assist each other. Our design enables the pre-trained model to easily adapt to unseen knowledge graphs in new domains.
  arXiv  Detail & Related papers  (2020-10-02T05:53:36Z)
• Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning [73.0598186896953]
  We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
  arXiv  Detail & Related papers  (2020-04-29T14:22:42Z)

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.