A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English

• URL: http://arxiv.org/abs/2011.00960v1
• Date: Mon, 2 Nov 2020 13:25:39 GMT
• Title: A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English
• Authors: Marius Mosbach, Stefania Degaetano-Ortlieb, Marie-Pauline Krielke, Badr M. Abdullah, Dietrich Klakow
• Abstract summary: Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT) testing their grammatical and semantic knowledge by sentence-level probing, diagnostic cases, and masked prediction tasks.
• Score: 17.993417004424078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT), testing their grammatical and semantic knowledge by sentence-level probing, diagnostic cases, and masked prediction tasks. We focus on relative clauses (in American English) as a complex phenomenon needing contextual information and antecedent identification to be resolved. Based on a naturalistic dataset, probing shows that all three models indeed capture linguistic knowledge about grammaticality, achieving high performance. Evaluation on diagnostic cases and masked prediction tasks considering fine-grained linguistic knowledge, however, shows pronounced model-specific weaknesses especially on semantic knowledge, strongly impacting models' performance. Our results highlight the importance of (a)model comparison in evaluation task and (b) building up claims of model performance and the linguistic knowledge they capture beyond purely probing-based evaluations.

Related papers

• Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
  We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence. We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena. As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
  arXiv  Detail & Related papers  (2024-04-29T17:58:36Z)
• Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling [70.23876429382969]
  We propose a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge.
  arXiv  Detail & Related papers  (2023-07-16T15:18:25Z)
• DesCo: Learning Object Recognition with Rich Language Descriptions [93.8177229428617]
  Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. We propose a new description-conditioned (DesCo) paradigm of learning object recognition models with rich language descriptions.
  arXiv  Detail & Related papers  (2023-06-24T21:05:02Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)
• ProsAudit, a prosodic benchmark for self-supervised speech models [14.198508548718676]
  ProsAudit is a benchmark to assess structural prosodic knowledge in self-supervised learning (SSL) speech models. It consists of two subtasks, their corresponding metrics, and an evaluation dataset.
  arXiv  Detail & Related papers  (2023-02-23T14:30:23Z)
• Knowledge Graph Fusion for Language Model Fine-tuning [0.0]
  We investigate the benefits of knowledge incorporation into the fine-tuning stages of BERT. An existing K-BERT model, which enriches sentences with triplets from a Knowledge Graph, is adapted for the English language. Changes made to K-BERT for accommodating the English language also extend to other word-based languages.
  arXiv  Detail & Related papers  (2022-06-21T08:06:22Z)
• 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)
• Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding [1.827510863075184]
  Curriculum is a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality.
  arXiv  Detail & Related papers  (2022-04-13T10:32:03Z)
• Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge [59.22170796793179]
  Transformers Language Models (TLMs) were tested on a benchmark for the textitdynamic estimation of thematic fit Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge.
  arXiv  Detail & Related papers  (2021-07-22T20:52:26Z)
• The Rediscovery Hypothesis: Language Models Need to Meet Linguistics [8.293055016429863]
  We study whether linguistic knowledge is a necessary condition for good performance of modern language models. We show that language models that are significantly compressed but perform well on their pretraining objectives retain good scores when probed for linguistic structures. This result supports the rediscovery hypothesis and leads to the second contribution of our paper: an information-theoretic framework that relates language modeling objective with linguistic information.
  arXiv  Detail & Related papers  (2021-03-02T15:57:39Z)
• Labeling Explicit Discourse Relations using Pre-trained Language Models [0.0]
  State-of-the-art models achieve slightly above 45% of F-score by using hand-crafted features. We find that the pre-trained language models, when finetuned, are powerful enough to replace the linguistic features. This is the first time when a model outperforms the knowledge intensive models without employing any linguistic features.
  arXiv  Detail & Related papers  (2020-06-21T17:18:01Z)

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.