paper-with-me

Papers

Deep Clustering of Text Representations for Supervision-free Probing of Syntax

2020-10-24 · Vikram Gupta, Haoyue Shi, Kevin Gimpel, Mrinmaya Sachan

We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, our approach jointly transforms the representations into a lower-dimensional cluster-friendly space and clusters them. We consider two notions of syntax: Part of speech Induction (POSI) and constituency labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as English BERT (EBERT). Our model can be used as a supervision-free probe which is arguably a less-biased way of probing. We find that unsupervised probes show benefits from higher layers as compared to supervised probes. We further note that our unsupervised probe utilizes EBERT and mBERT representations differently, especially for POSI. We validate the efficacy of our probe by demonstrating its capabilities as an unsupervised syntax induction technique. Our probe works well for both syntactic formalisms by simply adapting the input representations. We report competitive performance of our probe on 45-tag English POSI, state-of-the-art performance on 12-tag POSI across 10 languages, and competitive results on CoLab. We also perform zero-shot syntax induction on resource impoverished languages and report strong results.

📄 PDF Abstract BibTeX arXiv:2010.12784

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringDeep ClusteringTAG

Methods 이 논문이 사용한 방법론

mBERT mBERT

Similar Papers 제목 키워드 기반

Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT

2020-04-30 · ACL 2020 6 · Zhiyong Wu, Yun Chen, Ben Kao, Qun Liu

By introducing a small set of additional parameters, a probe learns to solve specific linguistic tasks (e.g., dependency parsing) in a supervised manner using feature representations (e.g., contextualized embeddings). Th…

Dependency ParsingLanguage ModelingLanguage ModellingSentiment Analysis+1

Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing

2026-06-20 · Amina Miftakhova, Alexey Zaytsev arxiv

Detecting hallucination risk before generation enables abstention, retrieval augmentation, and routing decisions without incurring the cost of decoding. While prior work has shown that such risk can be estimated from a m…

Binary Classification

A Self-Training Approach for Short Text Clustering

2019-08-01 · WS 2019 8 · Amir Hadifar, Lucas Sterckx, Thomas Demeester, Chris Develder

Short text clustering is a challenging problem when adopting traditional bag-of-words or TF-IDF representations, since these lead to sparse vector representations of the short texts. Low-dimensional continuous representa…

ClusteringDeep ClusteringSentenceSentence Embedding+3

Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations

2022-04-01 · BioNLP (ACL) 2022 5 · Sihang Zeng, Zheng Yuan, Sheng Yu

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to …

ClusteringContrastive Learninggraph constructionKnowledge Graphs

Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?

2025-07-17 · Siqi Shen, Mehar Singh, Lajanugen Logeswaran, Moontae Lee 외 arxiv

There has been extensive research on assessing the value orientation of Large Language Models (LLMs) as it can shape user experiences across demographic groups. However, several challenges remain. First, while the Multip…

Text Generation